SlideShare a Scribd company logo
1 of 51
Download to read offline
EDHEC Business School   1
EDHEC Business School   2
An Empirical Study of
Macroeconomic Factors and Stock
 Market: An Indian Perspective
                         Saurabh Yadav
                     EDHEC Business School
          Master’s in Risk and Investment Management
                   saurabh.yadav@edhec.com
                        June 26, 2012




EDHEC Business School
Abstract
        This thesis is an empirical study of relationship between Indian stock
    markets and macro economy. There is a huge literature about such kind of
    empirical studies but mostly on US/UK stock markets and macroeconomic
    indicators. This study is similar to many of the earlier studies in some
    aspects, so it uses econometric tools used in earlier studies but at the same
    time this study differentiates itself from other studies in the sense it uses
    Indian markets and macroeconomic data for analysing the relationship
    and it also tries to analyse the impact of global economy on the Indian
    markets. The period that will be used for the study will be from 1990
    to 2011. We have chosen this period as it represents big regulatory and
    structural changes in Indian economy. So, an analysis of this period can
    provide us with insights to how some regulatory and structural changes
    impact the economy and asset prices in that country. In this study we will
    use Unit root tests, cointegration, Ljung-Box Q test and multivariate VAR
    analysis for analysing each macro economic and asset prices time series
    individually and to build a model that can analyse the impact of one over
    the other. Also, we will conduct Granger’s Causality test and Impulse
    response analysis between Stock market and macro economic indicators
    to analyze the impact of macro economic news/shocks on India Stock
    index (BSE).




EDHEC Business School                    4
Acknowledgment

    I am thankful to Professor Robert Kimmel for his comments and guidance
on the subject. He has been a constant source of inspiration and a good men-
tor, from whom I learned a lot. I am also grateful to Stoyan Stoyanov, Marc
Rakotomalala, Aishwarya Iyer, Wen lei, Lixia Loh for some great insights into
the subject. Their timely comments and suggestions on empirical tests helped
me improve the statistical significance of my tests. I thank EDHEC Risk In-
stitute for allowing me to use their resources to get the data from various data
providers. In the end i’ll like to thank my parents and my sister for constant
support and motivation without which it would have been impossible to climb
this arduous path.

Regards,
Saurabh YADAV




EDHEC Business School                  5
CONTENTS


Contents
1 Introduction                                                                           7

2 Literature Review                                                                       9

3 Data                                                                    13
  3.1 Description of Macroeconomic Indicators . . . . . . . . . . . . . 13
  3.2 Description of Stock Market Indices . . . . . . . . . . . . . . . . 14

4 Methodology                                                                  15
  4.1 Construction of Time Series . . . . . . . . . . . . . . . . . . . . 15
  4.2 Unit Root Test and Stationarity . . . . . . . . . . . . . . . . . . . 15
      4.2.1 Mathematical representation of Stationary series and unit
             root test . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
      4.2.2 Augmented Dickey Fuller Unit Root Test . . . . . . . . . 17
  4.3 Testing Long Term Relationships . . . . . . . . . . . . . . . . . . 18
      4.3.1 Johansen test for Cointegration . . . . . . . . . . . . . . . 18
  4.4 Impulse Response . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

5 Results                                                                                21

6 Conclusions                                                                            24

7 Graphs and Tables                                                                      25
  7.1 Graphs of Time series . . . . . . . . . . . . . . . . . . . .      .   .   .   .   25
  7.2 Graphs of Time Series - Differenced . . . . . . . . . . . .         .   .   .   .   29
  7.3 Correlograms of Time series . . . . . . . . . . . . . . . . .      .   .   .   .   33
  7.4 Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . .   .   .   .   .   40
      7.4.1 Table for Unit root test of Time series . . . . . . .        .   .   .   .   40
      7.4.2 Tables for Unit root test of Differenced time series          .   .   .   .   40
      7.4.3 Tables for Residual based test of cointegration . . .        .   .   .   .   40
      7.4.4 Johansen cointegration test . . . . . . . . . . . . .        .   .   .   .   43
      7.4.5 Impulse response tests . . . . . . . . . . . . . . . .       .   .   .   .   46
      7.4.6 Granger causality test between IP and BSE . . . .            .   .   .   .   49

8 Bibliography                                                                           50




EDHEC Business School                   6
1   INTRODUCTION


1    Introduction
In the past few decades there has been a growing interest among academicians
and practitioners about the relationship between macroeconomic variables and
asset prices, mainly stocks and house prices. In a good and expanding economy,
prices of stocks are supposed to increase as there is an increase in expectation
of large future cash flows/ profits for the companies and various role players
in the economy. Similarly, during a bad or downward spiralling economy the
expectation of large future cash flows and profits decrease and consequently the
price of stocks decrease.
Stock markets are representative of economy of a country and investors belief.
They are able to capture macro economic movements in the economy as well as
idiosyncratic factors related to each company or industry. As Stock prices are
real time and are more frequent than macroeconomic releases they are better
reflector of changes in domestic and global economy and can predict the move-
ment of macroeconomic indicators. In other words stock markets are a leading
indicator of the economy.
Markets respond to different macroeconomic indicators in different ways. The
response of Stock markets to any macroeconomic news is dependent on how the
news will effect the profits and interest rates. The price of the stock according
to the Discounted Cash Flow formula is:

                          Div1         Div2               Divt
                 Pt =              +            + ... +                      (1)
                        (1 + r1 )1   (1 + r2 )2         (1 + rt )t
    As both dividends and interest rates enter into the formula for value of a
stock the reaction of stock price to a macro news will depend on how the news
effect the discounting factor ( Interest rates ) and future profits of the com-
panies. Macro economic factors that project brighter times and more profits
for the companies like, increasing Industrial production, Increasing M1 money
supply, good consumer confidence levels will have a positive effect on the stock
prices. Whereas, macro news that point to economic recession or slow growth
like, decreasing Industrial production coupled with Rising interest rates, Rise
in inflation, rise in unemployment, etc. will have a downward effect on stock
prices.
First people to do an empirical study on this subject were Eugene Fama and
Kenneth French. In their 1981 paper ”Stock returns, Real activity, Inflation
and money” they analysed the relationship between stock returns, real activity
inflation and money supply using macro economic data. After that study there
has been a barrage of studies on relationship between stock returns and macro
economic factors based on US and UK data. Another important paper pub-
lished on this research was by Chen,Roll and Ross (1986) who analysed whether
innovations in the macroeconomic variables are risks that are awarded in the
stock markets. They found that macroeconomic variables like, spread between
long and short interest rates, expected and unexpected inflation, Industrial pro-
duction are some of the factors that are awarded by the markets. Further, the
Arbitrage pricing theory (APT) of Ross (1976) posits relation between stock
prices and certain macro-economic variables. In the last decade or so the focus
for these kind of studies have started to shift from developed world economies to
developing world economies. As developing world economies have shown signs


EDHEC Business School                    7
1   INTRODUCTION


of huge growth potential and leading the economies globally out of recessions,
this motivates us to research on developing markets, like India. Such a study
will help us to find the relation between stock market and macroeconomic indi-
cators and give a new insight to foreign investors, academicians,policy makers,
traders and domestic investors.
This study is important in a sense it provides an insight to how are Indian stock
markets are related to its macroeconomic variables and global macro/micro eco-
nomic factors. This study will also help us in analysing whether the Indian stock
markets have become coupled to global factors or are they still dominated by
domestic economic factors.
The focus of this study is on relation between Indian stock market, represented
by BSE Sensex, and domestic macroeconomic factors and global factors repre-
sented by Standard and Poor’s 500 Index. This study builds on earlier studies
done in this area but also open some new doors for further research. It is sim-
ilar to some earlier studies in a respect that it uses data, macro and micro
factors and econometrics tools used in previous studies but at the same time it
differentiates itself from earlier studies in a sense that it is done on a market
that is still developing. Also, the time period used in the analysis is a period
where Indian market has undergone lot of regulatory changes that has created
a structural change in the market. Further, in this study I’ll analyse whether
the Indian markets are driven mainly by Domestic factors or do global factors
have more influence on Indian markets. To analyse the impact of international
factors I’ll use Standard and Poor’s 500 Index and USDINR exchange rate as a
substitute of global factors and to model domestic demand I’ll use macro factors
like Industrial production, M1 money supply, Consumer Price Index and Pro-
ducer price Index. The outline of the thesis is as followings: Section 2 provides
a literature review of the studies done earlier in this area, Section 3 provides a
detailed description of the data used in the study Section 4 provides a detailed
description of the methodology and various econometric tools that will be used
in the study, Section 5 provides the results of the study and Section 6 provides
the conclusion of the study.




EDHEC Business School                   8
2   LITERATURE REVIEW


2    Literature Review
Many studies and researchers have tried to find factors that can explain stock
returns. The most famous and earliest model is the Capital Asset Pricing Model
(CAPM), developed by Sharpe (1964), Lintner (1965), Mossin (1967) and Black
(1972). The concept of this single factor model is developed from diversifi-
cation introduced by Markowitz (1952). In CAPM model the expected stock
returns can be explained with the help of Risk free rate and one risk factor,
Market. CAPM says that the systematic risk can be captured by sensitiveness
of each stock to change in overall market, which is measured by Beta. According
to CAPM, the market factor is the only factor determining the stock returns.
CAPM was a revolutionary model. It changed the way people looked at the
stock returns as something that is vary arbitrary. As it is very easy to under-
stand and use, CAPM is very popular as the model used to determine the stock
return in most of finance textbooks and used by many practitioners in stock
market.
However, the numerous set of assumptions made in deriving CAPM made it
inconsistent with the real world and led to criticism of CAPM. To overcome
the limitations and assumptions made in CAPM many scholars came up with
multi- factor models like Fama-French three factor model, APT model, etc. In
Fama-French model they try to explain stock returns with help of three factors,
market,small minus big and value minus growth. the model was able to explain
the returns based on these risk factors for some time before it failed. There
have been many studies on failure of Fama-French model and markets where it
is not applicable.
The macroeconomic models of explaining stock returns started with APT (Ar-
bitrage Pricing Theory) by Ross (1976), which was later refined by Roll and
Ross (1980). APT is a multi-factor model and claims that the stock return can
be explained by unexpected changes or shocks in multiple factors. Chen,Roll
and Ross (1986) perform the empirical study for APT model and identify that
surprise or shock in macroeconomic variables can explain the stock return sig-
nificantly. The variables used in their study are Industrial production index,
default risk premium that can measure the confidence of investors, and change
in yield curve that can be measured by term premium.
The study of macroeconomic factors in explaining stock returns have been pop-
ular since then. Stock price is present value of all discounted future cash flows.
If a firm is performing well then the expectation of large future cash flows rises
and consequently the stock price rises. On the other hand if a firm is performing
bad for couple of years then the expectation of big future cash flows decrease
and in turn the stock price fall. This is a micro and idiosyncratic explanation of
stock prices and returns. But, the future cash flows of a stock does not depend
solely on the company’s performance or profits/loss. The systematic factor can
have a huge impact on the cash flows of not only one but many companies. The
systematic factor here refers to macro economic variables. The state of Macro
economic conditions lead to changes in Monetary and regulatory policies by the
government and which in turn affects the stock prices. For example a country
with good economic conditions, represented by its Industrial production index,
GDP, CPI, Interest rates will create an environment that is conducive for the
growth of companies by lowering borrowing rates and other open market opera-
tions. So, all macroeconomic factors that can influence future cash flows or the


EDHEC Business School                   9
2    LITERATURE REVIEW


discount rate by which the cash flows are discounted should have an influence
on the stock price.
Many researcher have studies the relationship between stock prices and macro
economic variables and tried to explain the affect of one over the other. Fama
(1981) tries to establish a relationship between stock returns, real activity, infla-
tion and money. In his paper he finds that Stock returns have positive relation
with real output and money supply but a negative relation with inflation. He
explains that negative relation between stock returns and inflation is induced by
negative relation between real output, approximated by Industrial production,
and inflation. This negative relationship between inflation and real activity
is explained by money demand theory and quantity theory of money. Fama
(1990) explains that measuring the total return variation explained by shocks
to expected cash flows, time-varying expected returns, and shocks to expected
returns is one way to judge the rationality of stock prices. In his paper he
finds that growth rates of production, used to proxy for shocks to expected cash
flows, explain 45% of return variance. Chen,Roll and Ross (1986) explored the
relationship between a set of economic variables and their systematic influence
on stock market returns. They found that Industrial production, changes in
risk premium, twists in yield curve had strong relationship and impact on stock
returns. A somewhat weaker effect was found for measures of unanticipated
inflation and changes in expected inflation during periods when these variables
were highly volatile. They concluded that stock returns were exposed to sys-
tematic economic news, that they are priced in accordance to their exposures,
and that the news can be measured as innovation in state variables. Chen
(1991) found that state variables that are priced are those that can forecast
changes in the investment and consumption opportunity set. According to his
research, default spread, the term spread, the one-month T-Bill rate, the lagged
industrial production growth rate, and the dividend-price ration are important
determinants of future stock market returns. Bulmash and Trivoli (1991) show
the effect of business cycle movements on the relationship between stock returns
and money growth.
An interesting paper in this field of research is by Fama (1990) and Schwert
(1990). In the paper they claim that there are three explanations for the strong
link between stock prices and real economic activity:


      “First, information about the future real activity may be reflected in stock
      prices well before it occurs — this is essentially the notion that stock prices
      are a leading indicator for the well-being of the economy. Second, changes
      in discount rates may affect stock prices and real investment similarly, but
      the output from real investment doesn’t appear for some time after it is
      made. Third, changes in stock prices are changes in wealth, and this
      can affect the demand for consumption and investment goods” [Schwert
      (1990),p.1237]

   Campbell and Ammer (1993) use a VAR approach to model the simulta-
neous interactions between the stock and bond markets, since most previous
works do not address the channels through which the macroeconomic activity
influences the stock prices. One example could be that industrial production
could be linked to changing expectations of future cash flows (Balvers at al.
1990). On the other hand, interest rate innovations could be the driving factor


EDHEC Business School                       10
2   LITERATURE REVIEW


in determining both industrial production (due to change in investment) and
stock prices (due to change in the discounted present value of future cash flows).
A VAR analysis can distinguish these possibilities. Mukherjee and Naka (1995)
show a long-term relationship between the Japanese stock price and real macroe-
conomic variables. Dr. Nishat (2004) studies the long term association among
macroeconomic variables like money supply, CPI,IPI, and foreign exchange rate
and stock markets in Pakistan. The results show that there are causal relation-
ship among the stock price and macroeconomic variables. He uses data from
1974 to 2004 in his study. As most of the financial time series are non station-
ary in levels he uses unit root technique to make data stationary. Fazal Hussian
and Tariq Massod (2001) used variables like investment, GDP and consumption
employing Granger’s causality test to find relationship between macro factors
and stock markets. They show that at two lags all macroeconomic variables
have highly significant effect on stock prices. James et al. (1985) use a VARMA
analysis for investigating relationship between macro economy and stock mar-
ket. Using VARMA analysis for finding causal relationship between factors is
a better technique as the procedure does not preclude any causal structure a
priori since it allows feedback among variables. Thus, the VARMA approach
allow whatever causal relationship exist to emerge from the data. They find
linkages between real activity and stock returns and real activity and inflation.
Also, they find that stock returns signal changes in the monetary base. Since
stock returns also signal changes in expected real activity, this suggests a link
between the money supply and expected real activity that is consistent with the
money supply explanation offered by Geske and Roll.
In recent years the focus of these kind of studies have shifted from developed
economies to developing economies. As developing economies are the economies
that see a lot of structural and monetary policy changes an analysis of relation-
ship between macro and micro can provide new insights. Also, one can analyse
the effects of monetary policies on the asset prices especially on stock prices.
Tangjitprom (2012) study of macroeconomic factors like unemployment rate,
interest rate, inflation rate and exchange rate and stock market of Thailand con-
cludes that macroeconomic factors significantly explain stock returns. He also
finds that for Thailand unemployment rate and inflation rate are insignificant to
determine the stock returns. The reason he provides is that the unemployment
rate and inflation rate are not timely and there could be some lags before the
data becomes available. Also, Granger’s test to examine lead-lag relationship
among the factors reveal that only few macroeconomic variables could predict
the future stock returns whereas the stock returns can predict most of future
macro economic variables. This implies that performance of stock markets can
be a leading indicator for future macroeconomic conditions. Ali (2011) study of
impact of macro and micro factors on stock returns reveals that inflation and
foreign remittance have negative influence and industrial production index have
positive impact on stock markets. Also he didn’t found any Granger’s Causal-
ity between stock markets and any of the explanatory variables. This lack of
Granger’s causality reveals the evidence of informationally inefficient markets.
Ali uses a multivariate regression analysis on standard OLD formula for estimat-
ing the relationship. Hosseini et al. (2011) tested the relationship between stock
markets and four macro economic variables namely crude oil prices, Money sup-
ply, Industrial production and inflation rate in China and India. They used a
period of 1999 to 2009 for analysis. As most of the economic time series have unit


EDHEC Business School                  11
2   LITERATURE REVIEW


root, they first used the Augmented Dickey Fuller unit root test and found the
underlying series to be non-stationary at levels but stationary after in difference.
Also, the use of Jhonson-Juselius (1990) Multivariate cointegration and Vector
Error Correction model technique, indicate that there are both long and short
run linkages between macroeconomic variable and stock market index in each of
the two countries. Their analysis shows that in long run the impact of increase
in prices of crude oil for China is positive but for India is negative. In terms
of money supply, the impact on Indian stock market is negative, but for China,
there is a positive impact. The effect of Industrial production is negative only
in China. In addition the effect of increases in inflation on these stock markets
is positive in both countries. Wickremasinghe (2006) analysed the relationship
between stock prices and macroeconomic variables in Sri Lanka. He used the
Unit root tests, Jhonson’s test, Error-correction model, variance decomposi-
tion and impulse response to analyse the relationships. His findings indicate
that there is both long term and short term causal relationship between stock
prices and macroeconomic variables in Sri Lanka. The result indicate that the
stock prices can be predicted from certain macroeconomic variables and hence
violate the validity of the semi-strong version of efficient market hypothesis.
Ahmed (2008) investigates the causal relationship between Indian macroeco-
nomic factors like Industrial Production, Exports, Foreign direct investment,
Money supply, exchange rate, interest rate and stock market indices NSE Nifty
Index and BSE Sensex. For finding the long term relationship he applies Jo-
hansen’s cointegration and Toda and Yamamoto Granger Causality tests. For
analysing the Impulse response and variance decomposition he uses bivariate
VAR. His findings reveal that stock prices in India lead macroeconomic activity
except movement in interest rate. Interest rate seem to lead the stock price.
The study also reveals that movement of stock prices is not only the outcome
of behaviour of key macro economic variables but it is also one of the causes
of movement in other macro dimensions in the economy. An important paper
by Bilson et al. (2001) argues that emerging markets local factors are more
important than global factors. They find that for emerging markets are at least
partially segmented from global capital markets. The global factors are proxied
by world market returns and local factors by set of macro economic variables
like money supply, prices, real activity and exchange rate. Some evidence is
found that local factors are significant in their association with emerging equity
market returns above than that explained by the world factor. When they use
a larger set of variables the explanatory power of the model improves substan-
tially such that they are able to explain a large amount of return variation for
most emerging markets.




EDHEC Business School                   12
3   DATA


3     Data
3.1    Description of Macroeconomic Indicators
One of the biggest problems when conducting a research with macroeconomic
data is the frequency of the data. Most of the macroeconomic indicator time
series are yearly,quarterly or monthly time series. This low frequency of the
macroeconomic indicators results in very few data points for conducting a anal-
ysis that is robust. A possible cure for the problem is to use longer time periods
to incorporate more data points for macroeconomic variables. But, another
problem that we face when we look at the macroeconomic indicators for Asian
countries is reporting of the data. For most of the Asian countries the macroe-
conomic data doesn’t have a long history and same can be said about history
of Indian macroeconomic variables. So, in this research we have used a time
period for which we can find data for most of the macroeconomic indicators. In
this paper we use a time period of 20 years starting from 1990 to 2011. This
time period in Indian economy is representative of many structural and mone-
tary policy changes like liberalization of India markets. Also as the time period
is long it gives us enough data point for each macroeconomic factors to do a
robust empirical analysis.
When one starts to build a model of interaction between macro and micro eco-
nomic factors one dominant and important question one faces is, among the
myriad of macro indicators available for an economy which factors to choose
to incorporate in the model. If one chooses macroeconomic factors that are
highly correlated among themselves then the power of test results decrease as
it may result in a model where the macro indicators are able to explain most
of the movement of micro factors but the macro factors may not be relevant.
To circumvent this problem we use variables that have been tested in earlier
researches and that have been proven to have effect on stock markets. I also
test a few macro factors that have some financial theory behind them that con-
nect them to stock markets. Ali (2011), Wickremasinghe (2006), Bilson et.al
(2001) and Bailey (1996) find that Industrial production, CPI, exchange rate,
M1 money supply, GDP are few of the macro economic factors that can signifi-
cantly explain stock returns. Sahu(2011), Ahmed(2008), Tripathy(2011) study
on Indian markets specifically show that Industrial Production, Exchange rate,
Inflation index are macro economic indicators that have a strong positive or
negative relationship with the stock markets. So, in our study we test 5 macro
economic variables namely M1 money supply, Consumer and Producer price In-
dex, Industrial production, Exchange rate. The time period for these indicators
is from 1990-2011. The data for Inflation indices, Industrial production and
exchange rate has been pulled from Bloomberg c and Datastream c . The data
has been processed for errors and missing values. Data for M1 money supply
has been pulled from RBI website. For most of the indices like inflation and
Industrial production index, the base year has been changed to 1990. Also, as
some of the indices are in levels and some in actual figures (M1 money supply),
we convert all of the indicators to level form (starting at 100 in 1990).




EDHEC Business School                  13
3   DATA


3.2    Description of Stock Market Indices
Compared to Macro Indicators, stock market data is relatively easy to find and
has considerably long history. Also, the stock market data is a real time data so
it has a very high frequency of seconds. Here, in our analysis we will make use of
BSE (Bombay Stock Exchange) as representation of Indian markets and SP500
(Standard and Poor’s 500 Index) as representation of global factors. BSE is a
market cap-weighted of 30 stocks. It is the oldest Index in the Asian markets
(established in 1875) and have had a long history. We choose this index as it is
the Index that represent the most liquid and traded stocks of the Indian stock
market. Also, the index is most traded index in India and a good representation
of trade prices of the stocks. Even in terms of an orderly growth, much before
the actual legislations were enacted, BSE Limited had formulated a compre-
hensive set of Rules and Regulations for the securities market. It had also laid
down best practices which were adopted subsequently by 23 stock exchanges
which were set up after India gained its independence. Our choice of SP500 is
based on the fact that it has a long history and many researchers have used
this index as a good proxy representation of global markets and economic con-
ditions. We will take the monthly returns of each of the indices from 1990-2011
in accordance with data frequency of macro economic variables. Also, as the
indices have different levels at beginning of 1990 we rebase both the indices to
base year of 1990 starting at a level of 100.




EDHEC Business School                  14
4    METHODOLOGY


4      Methodology
4.1      Construction of Time Series
The first step in constructing an econometric model is constructing time series
all of which are in same units. Most of the time series used in our analysis are in
different formats. For example CPI, PPI, BSE Index, SP500 are in levels. M1
money supply, USDINR exchange rate is in absolute current format. Industrial
production is in absolute production levels. So, first we convert all of the given
time series to level. The way we construct time series in levels is firstly taking
the initial data point of each time series as 100. We then find the percentage
change from one period to the next one for each time series using a continuous
compounding assumption (taking a natural log of change in values). In math-
ematical terms it can be stated as: Assume the original Index value at time t
to be It and at time t+1 to be It + 1. Then we can compute the new rebased
index by formula:

    RIt+1 = RIt ∗ (1 + ln(It+1 /It ))

where,
RIt = Rebased Index at time t
RIt+1 =Rebased Index at time t+1
We can use these rebased indices in building and testing our econometric model.


4.2      Unit Root Test and Stationarity
Unit root test is to find whether the series is stationary or non-stationary. A
strictly stationary process is one where, for any t1 , t2 ,...., tt ∈Z, any k ∈Z and
T=1,2,...

Fyt1 ,yt2 ,yt3 ,....,ytT (y1 , ...., yT ) = Fyt1+k ,yt2+k ,yt3+k ,....,ytT +k (y1 , ...., yT )

where F represents joint distribution function of the set of random variables.
It can also be stated that the probability measure of sequence of yt is same as
yt+k for all k. In other words a series is stationary if the distribution of its value
remain the same as time progresses. Similar to the concept of strict stationary
is weakly stationary process. A weakly stationary process is one which has a
constant mean, variance and autocovariance structure. Stationary is a necessary
condition for a time series to be tested in regression. A non-stationary series
can have several problems like:


    1. The shocks given to the series would not die of gradually, resulting in
       increase of variance as time passes.
    2. If the series is non stationary then it can lead to spurious regressions. If two
       series are generated independent of each other then if one is regressed on
       other it will result in very low R2 values. But if two series are trending over
       time then a regression of one over the other will give high R2 even though
       the series may be unrelated to each other. So, if normal regressions tools


EDHEC Business School                                 15
4   METHODOLOGY


        are used on non stationary data then it may result in good but valueless
        results.
  3. If the variables employed in a regression model are not stationary, then
     it can be proved that the standard assumptions for asymptotic analysis
     will not be valid. In other words, the usual ’t-ratios’ will not follow a
     t-distribution, and the F-statistic will not follow an F-distribution, and so
     on.
Stationarity is a desirable condition for any time series so that it can be used
in regressions and give meaningful result that have some value. to test for sta-
tionarity a quick and dirty way is looking at the autocorrelation and partial
correlation function of the series. If the series is stationary then the autocorre-
lation function should die off gradually after few lags and the partial correlation
function will me non zero for some lags and zero thereafter. Also we can use
the Ljung-Box test for testing that all m of σk autocorrelation coefficients are
zero using Q-statistic given by formula:


                                                 σk 2
                            Q = T (T + 2)Σm
                                          k=1         ∼ χ2
                                                T −k
where, T = Sample size and m = Maximum lag length
The lag length selection can be based on different Information Criteria like
Akaike’s Information criteria (AIC), Schwarz’s Bayesian information criteria
(SBIC), Hannan-Quinn criterion (HQIC). Mathematically different criteria are
represented as:

                   2k
AIC = ln(σ 2 ) +   T

                    k
SBIC = ln(σ 2 ) +   T lnT

                        2k
HQIC = ln(σ 2 ) +       T ln(ln(T ))

    For a better test for stationarity we use augmented Dickey fuller Unit root
test on each time series separately. Augmented Dickey Fuller test is test of
null hypothesis that the time series contains a unit roots against a alternative
hypothesis that the series is stationary.


4.2.1     Mathematical representation of Stationary series and unit root
          test
Assume a variable Y whose structure can be given by AR process with no drift
equation:
             yt = φ1 yt−1 + φ2 yt−2 + φ3 yt−3 + ... + φn yt−n + ut      (2)


where, ut is the residual at time t. Using a Lag operator L we can write eq.(1)
as:
              yt = φ1 L1 yt + φ2 L2 yt + φ3 L3 yt + ... + φn Ln yt + ut     (3)



EDHEC Business School                   16
4   METHODOLOGY




Rearranging eqn. (2) we get,
              yt − φ1 L1 yt − φ2 L2 yt − φ3 L3 yt + ... − φn Ln yt = ut        (4)
                            1         2         3               n
                 yt (1 − φ1 L − φ2 L − φ3 L + ... − φn L ) = ut                (5)
or,
                                     φ(L)yt = ut                               (6)

The time series is stationary if we can write eqn.(5) in form,
                                   yt = φ(L)−1 ut                              (7)

with φ(L)−1 converging to zero. It means the autocorrelation function would
decline as lag length is increased. If eqn. (6) is expanded to a MA(∞) process
the coefficients of residuals should decrease such that the the residuals that the
effect of residuals decrease with increase in lags. SO, if the process is stationary
the coefficients of residuals will converge to zero and for non-stationary series
they will and converge to zero and will have long term effect. The condition for
testing of unit root for an AR process is that the roots of eqn.(6) or ’Charac-
teristic equation’ should lie outside unit circle.


4.2.2   Augmented Dickey Fuller Unit Root Test
Consider an AR(1) process of variable Y
                                   yt = φyt−1 + ut                             (8)
Subtracting yt−1 from both sides of eqn.(7) we get,
                                ∆y = (φ − 1)yt−1 + ut                          (9)
Eqn.(8) is the test equation for Dickey Fuller test. For Dickey-Fuller Unit root
test,
Null Hypothesis: The value of φ is equal to 1 or value of φ − 1 is equal to 0 v/s,
Alternate Hypothesis: The value of φ is less than one or value of φ − 1 is less
than zero Augmented Dickey-Fuller test is similar to normal Dickey-Fuller tests
except, it takes the lag structure of more than one into account.
                                           p
                        ∆y = ψyt−1 +            αi ∆yt−i + ut                 (10)
                                          i=1

If the series has one or more unit root it is said to be integrated of order n,
where n is the number of unit roots of the characteristic equation. To make
these time series stationary they needs to be differenced. Mathematically, if
                                     yt ∼ I (n)                               (11)
then
                                   ∆ (d) yt ∼ I (0)                           (12)
To make our time-series stationary we will use the natural log returns of these
series in the analysis.



EDHEC Business School                     17
4    METHODOLOGY


4.3     Testing Long Term Relationships
Engle and Granger (1987) in their seminal paper described cointegration which
forms the basis for testing for long term relationship between variables. Accord-
ing to Engle and Granger two variables are cointegrated if they are integrated
process in their natural form (of the same order), but a weighted combination
of the variables can be found such that the combined new variable is integrated
of order less than the order of individual time series. Mathematically, assume
yt to be a k X 1 vector of variables, then the components are cointegrated or
integrated of order (d,b) if:
   1. All components of yt are I(d)
   2. There is at least one vector of coefficients α such that


                                      α yt ∼ I (d − b)                              (13)

As most of the financial time series are integrated of order one we will restrict
ourselves to case d=b=1. Two or more variables are said to be cointegrated if
there exist a linear combination of these variables that is stationary. Many of
the series are non-stationary but ’move together’ over time which implies two
series are bound by some common force or factor in long run. We will test for
cointegration by a residual-based approach and Johansen’s VAR method.
Residual Based approach Consider a model,

                         yt = β1 + β2 x2t + β3 x3t + ... + ut                       (14)

where yt , x2t , x3t , ... are all integrated of order N. Now if the residual of this re-
gression, ut is stationary then we can say that the variables are cointegrated else
there exist no long term relationship between the variables. To test the resid-
ual for stationarity we will run Augmented Dickey-Fuller tests on the residuals.
Under the Null hypothesis the residual are integrated of order one or more and
under alternate hypothesis the residuals are I(0).


4.3.1    Johansen test for Cointegration
Johansen test for cointegration presents a better model for testing multiple
cointegration among multiple variables. The Residual based approach can only
find atmost one cointegration and can be tested for a model with two variables.
Even if more than two variables are present in the equation that are cointegrated,
the Residual based approach will give only one cointegration. SO we will use
Jhoansen VAR based cointegration for testing more than one cointegration.
Suppose that a set of g variables are under consideration that are I(1) and
which are thought to be cointegrated. A VAR with k lags containing these
variables could be set up.

                     yt = β1 yt−1 + β2 yt−2 + · · · + βk yt−k + ut                  (15)


        g×1      g×g       g×1      g×g         g×1    g×g          g×1   g×1


EDHEC Business School                      18
4   METHODOLOGY


   In order to use the Johansen test, the VAR above should be turned into a
vector error correction model of form,

      ∆yt = Πyt−k + ℘1 ∆yt−1 + ℘2 ∆yt−2 + · · · + ℘k−1 ∆yt−(k−1) + ut       (16)

where, Π = (Σk βi ) − Ig and ℘i = (Σi βj ) − Ig
             i=1                    j=1


The Johansen’s test centers around testing the Π matrix which is the matrix
that represents the long term cointegration between the variables. The test for
number of cointegration is calculated by looking at the rank of the Π matrix
through its eigenvalues. The rank of the matrix is equal to number of roots
(eigenvalues) λi of the matrix that are different from zero. The roots should be
less than 1 in absolute value and positive. If the variables are not cointegrated
the rank of the matrix will not be significantly different from zero i.e. λi ≈ 0.
There are two test statistics for Johansen test λtrace r and λmax
                   g            ˇ
λtrace (r) = −T i=r+1 ln(1 − λi )
and,
                             ˇ
λmax (r, r + 1) = −T ln(1 − λr+1 )

λtrace is a test statistic for joint test where the null hypothesis is that the
number of cointegration vector is less than or equal to r against an alternative
that there are more than r.
λmax conducts another separate test on eigenvalues and has null hypothesis that
the number of cointegrating vector is r against r+1.


4.4    Impulse Response
Once we have determined whether the variables have long term relationship or
not we can form a multivariate VAR model for the variables. A multivariate
VAR model between g variables is a model where the current value of a variable
depend on differnt combinations of the previous k values of all the variables and
error terms. A general representation of the model can be:

yBSEt = α + βBSE yBSE + φIP yIP + γCP I yCP I + δM 1 yM 1 + κSP 500 ySP 500 + u1t
                                                                            (17)
where all the coefficients except α are g × k matrices and all variables y are k
× 1 matrices.
Once we have formed a model like this we can use the model for Impulse re-
sponse. A VAR(p) model can be written as a linear fuction of the past innova-
tions, that is,


                      rt = µ + at + ψ1 at−1 + ψ2 at−2 + . . .               (18)

where µ = [φ(1)]−1 φ0 provided that the inverse exists, and the coefficient ma-
trices ψi can be obtained by equating the coefficients of B i in the equation


             (I − φ1 B − . . . − φP B P )(I + ψ1 B + ψ2 B 2 + . . .) = I    (19)


EDHEC Business School                    19
4   METHODOLOGY


where I is the Identity martix. This is a moving average representation of rt
with the coefficient matrix ψi being the impact of the past innovation at−i on
rt . Equivalently, ψi is the effect of at on the future observation rt+i . Therefore,
ψi is often referred to as the Impulse Response Function of rt . For our impulse
response we will use equation of variables in first differnce form like,
                       k                           k
     ∆BSEt = αt +           α11 (i)∆BSEt−i +            α12 (j)∆M It−j +   BSEt    (20)
                      i=0                         j=1



                           k                       k
        ∆M It = αt +           α21 (i)∆M It−i +         α22 (j)∆BSEt−j +    M It   (21)
                        i=0                       j=1

    Granger’s causality and Block’s F test of a VAR model will suggest which of
the variables have statistically significant impacts on the future values of other
variables in the system. But F-test results cannot explain the sign of the re-
lationship nor how long these effects require to take place. Such information
will, however, be given by an examination of the VAR’s impulse responses and
variance decompositions. Impulse response is a technique that trace out the
responsiveness of the dependent variable in the VAR to shocks of each of the
other variables. So for each variable from each equation separately we will apply
a unit shock to the error and trace the effects upon the VAR system over time.
By using the impulse response technique we can determine how responsive is
the BSE stock index to Indian macro indicators and SP500. This will help us
determine whether the BSE index is more reactive to domestic news or global
news.




EDHEC Business School                     20
5   RESULTS


5    Results
Before we use the time series for VAR analysis or cointegration tests we need to
determine whether the series are Stationary or not. If the series are stationary
in levels, we can use them directly else we need to use the differenced time series.
One way to look for autocorrelation or integrated process is to see the graphs
of the various time series used. Section 7.1 shows the graphs of variables we
use for our analysis. As we can see from the graphs all of the time series have
a trend in long run which points to an integrated process. As a second step
we plot the graphs of differenced time series in Section 5.2. We can see that
the differenced graphs in Section 7.2 don’t show a long term trend and cross
the X-axis frequently. This is usually a property of I(1) processes. So we check
the series for autocorrelations at different lag lengths. Section 7.3 shows cor-
relograms graph, autocorrelation coefficient, partial autocorrelation coefficient,
Q-Stat and p-value for various time series up to 36 lags. As can be seen in the
tables the Q-stat for all lags is zero and we can reject the joint null hypothesis
that all the autocorrelations up to 36 lags are zero. Table 7.4.1 shows that if
we conduct a Unit root test on levels of the series we find that all the 7 series
are integrated as we cannot reject the t-stat for unit root at 1% level. But if
we conduct the same test on differenced values of the series we find that we can
reject the null hypothesis of unit root at 1% significance level for all the series
except CPI. This tells us that all the series are I(1) as there first difference series
are I(0).
As our series are I(1) we will work with index levels of time series to determine
if there exist one or more cointegrating relationships between the series. Tables
in subsection 7.4.3 are based on residual approach where we run a regression of
BSE and various macroeconomic indicators and test the residuals for unit root
using Augmented Dickey-Fuller test. As we assume the two series are cointe-
grated we conduct the test with no trend and intercept. If the two series are
cointegrated then the errors should not have any trend or intercept. We see that
we can reject the null hypothesis of unit root at 1% significance for CPI,IP, M1.
We can reject the null of unit root for PPI at 5 % and for SP500 and USDINR
we can’t reject the null hypothesis of unit root at even 5% level. This points
to the fact that BSE has a strong long term relationship with IP, M1 money
supply, CPI at 1% level with IP, M1, CPI, PPI at 5% significance level. Also,
BSE has no long term relationship with SP500 and USD INR exchange rate.
To test for multiple cointegrating relationship we now employ a Johansen VAR
based cointegration test. The results of the test are displayed in subsection
7.4.4. The first panel of the test results displays the value of λt race andλm ax
of Johansen test with different assumptions about intercept and trend. We can
see from this panel that when we consider a functional form of intercept and no
Trend we have atleast and atmost three cointegrating relationships. The second
panel of the results display the value of information criteria for lag lengths. For
most of the models we see that Akalike criteria points to a lag of three and
Schwarz criteria points to a lag of one. To estimate the cointegrating model we
choose the model with intercept and no trend and run a cointegration test.Test
results are shown in Table 2 of subsection 7.4.4. At 5% significance level we
can reject the null of atmost two cointegrating factors for λt race and same for
λm ax. Now to test which all variables have a long tern relationship we perform a
Restricted cointegration with vector error correction model. As we had already


EDHEC Business School                    21
5   RESULTS


seen in our residual based test of cointegration that BSE has no cointegrating
relationship with SP500 and USDINR we create a restricted cointegration model
where we set coefficients of SP500 and USDINR as zero. The test results are
displayed in Table 3 of subsection 7.4.4. In this case as there are two restrictions,
the test statistic follow χ2 with two degrees of freedom. We can see that the
p-value for the test is 13.33 % which tells us that the restrictions are supported
by data at 10% level of significance. So we can conclude that the BSE has a
long term relationship with CPI,IP,PPI,M1 money supply but has no long term
relationship with SP500 and USDINR exchange rate. One interpretation of this
result can be that the Indian stock market, represented here by BSE Sensex,
moves more in accordance with domestic factors like Industrial production, M1
money supply, Consumer price index and Producer Price index than with global
factors or in other words, as BSE is representation of largest market cap Indian
companies we can say that the biggest companies in India are ones that are
more dependent on domestic demand rather than exports. This result presents
an opportunity for international investors to diversify their portfolio by invest-
ing in BSE Sensex as it is decoupled with global markets and macroeconomic
factors.
We use A bivariate Vector Autoregression (BVAR) technique to analyze the
dynamic interaction between real asset prices and macro economy. VAR is
preferred method to study Macroeconomy and asset prices where variables en-
dogenously effect each other.
We begin with a bivariate VAR with no restriction. Asset prices and instru-
ments are allowed to respond to each other freely. For paired variables with
cointegration relationship, VAR is performed at levels whilst for those that are
not cointegrated VAR is performed at first difference. Constant term is ignored
with loss of generality. We use the Bivariate Autoregression analysis for both
impulse response and Granger’s causality tests.
Impulse response results are displayed in subsection 7.4.5. From first graph of
impulse response of BSE to USDINR we can see that USDINR has a negative
impact on BSE. As impulse response is response of BSE to shocks given to US-
DINR we can see that a positive shock or unexpected appreciation INR value
w.r.t USD, will have a negative effect on BSE for few lags and will disappear
after few lags. If we look at the constituents of BSE Index over time we see
that most of the time, some of its constituent are companies that thrive on ex-
ports. Some of the biggest Market-Cap in India are companies in service sector
like Infosys, TCS, etc that are hugely dependent on services provided to clients
from Europe and U.S.. So, an appreciation of INR compared to USD makes
these firms costlier for the global clients and in turn reduces the income of these
companies. As the firm’s revenue/ profit decreases the value of the stock also
decreases that in turn affects the returns of BSE Sensex.
Second graph (betwen BSE and SP500) shows that increase in SP500 has a pos-
itive effect on BSE as higher returns of SP500 indicate strong global economy
which in turn results in higher trade between countries. The positive response
of BSE to one unit shock to SP500 indicates a spillover effect of global factors
on Indian economy but the response is weak as can be seen from the graph.
Moving forward, response of BSE to shocks in M1 money supply, CPI, PPI
make economic sense. As for M1 money supply one unit shock means increase
in M1 money supply. This increase in money supply allows companies to bor-
row more money from banks at lower rates, which they can use for investing


EDHEC Business School                    22
5   RESULTS


in profitable projects and generating larger cash flows. For Inflation indicators
one unit shock means increase in inflation. This increase in inflation results in
higher costs for the companies that in turn reduces their profit margins and as
a result value of stocks.
By looking at the graphs we can also see that shocks to Indian macroeconomic
indicators creates stronger response by BSE as compared to global factors like
SP500 or USDINR. This indicates that BSE Index is driven by companies that
depend hugely on domestic demand rather than exports. Response of BSE to
shocks to Industrial Production are contradictory to theory. In theory an in-
crease in industrial production should result in positive response from BSE but
our analysis shows the other way. A possible reason for this response could be
that industrial production time series is seasonal as can be seen from the graph.
So, there is a possibility of a lead/lag relationship between the two variables.
To test for possibility of lead/lag relationship we run a Granger’s causality test
between BSE and IP. The result in section 6.4.6 shows that at a lag length
of 4 we can reject the Null hypothesis of BSE does not Granger cause IP at
1% significance level. This proves that BSE is a leading indicator of industrial
production and there exist a lead/lag relationship between the two indicators.




EDHEC Business School                  23
6   CONCLUSIONS


6    Conclusions
In this paper I tested the relations between Indian stock market, represented by
BSE, and domestic and global macro economic factors. The research concludes
that the India stock markets are mainly driven by domestic demand and the
influence of global macro factors on the stock market is weak. I also tested for
Granger causality between BSE and IP and found that BSE is a leading indicator
of Industrial production and can help in predicting the industrial climate in
India.
The research is insightful for investors and professionals who are looking for
investment opportunities to diversify their risks. As Indian stock markets are
more dependent on domestic factors one can invest in Indian indices and stocks
to diversify their risks gained through investing in U.S. and European stocks.
The paper opens new doors for research in this field. One can use variance
decomposition technique to see how much variance of BSE can be explained my
various domestic and global macro factors. Also one can use different global
factors like sovereign CDS spreads, T-Bill rates, a composite indicator of global
economy for further research on interaction between Indian stock market and
global economy.One can also research on how various global macroeconomic
news affects India stock markets and for how long the effects persists.




EDHEC Business School                  24
7   GRAPHS AND TABLES


7     Graphs and Tables
7.1   Graphs of Time series




EDHEC Business School         25
7   GRAPHS AND TABLES




EDHEC Business School   26
7   GRAPHS AND TABLES




EDHEC Business School   27
7   GRAPHS AND TABLES




EDHEC Business School   28
7   GRAPHS AND TABLES


7.2   Graphs of Time Series - Differenced




EDHEC Business School      29
7   GRAPHS AND TABLES




EDHEC Business School   30
7   GRAPHS AND TABLES




EDHEC Business School   31
7   GRAPHS AND TABLES




EDHEC Business School   32
7   GRAPHS AND TABLES


7.3   Correlograms of Time series
BSE




EDHEC Business School      33
7   GRAPHS AND TABLES


  IP




EDHEC Business School   34
7   GRAPHS AND TABLES


  SP500




EDHEC Business School   35
7   GRAPHS AND TABLES


  USDINR




EDHEC Business School   36
7   GRAPHS AND TABLES


  CPI




EDHEC Business School   37
7   GRAPHS AND TABLES


  PPI




EDHEC Business School   38
7   GRAPHS AND TABLES


  M1




EDHEC Business School   39
7   GRAPHS AND TABLES


7.4     Tables
7.4.1   Table for Unit root test of Time series
 Variables   T-Stat      p-value
   BSE       -2.671      24.95 %
  SP500      -1.315      88.18 %
   CPI       -1.909      64.66 %
    IP       -1.669      8.99 %
   M1        -2.420      36.79 %
   PPI       -3.353      6.01 %
 USDINR      -2.955      14.69 %

7.4.2   Tables for Unit root test of Differenced time series
 Variables   T-Stat      p-value
   BSE       -13.848     0.00 %
  SP500      -14.832     0.00 %
   CPI        -3.344     1.40 %
    IP        -3.865     0.27 %
   M1         -3.867     0.26 %
   PPI        -9.656     0.00 %
 USDINR      -13.701     0.00 %


7.4.3   Tables for Residual based test of cointegration


                                     Table 1:
BSE - CPI
                                     t-Statistic   Prob.*
 ADF test statistic                  -2.622676     0.87%
 Test critical values:   1% level    -2.573818
                         5% level    -1.94204
                         10% level   -1.615891



                                     Table 2:
BSE - IP
                                     t-Statistic   Prob.*
 ADF test statistic                  -3.738802     0.02%
 Test critical values:   1% level    -2.574513
                         5% level    -1.942136
                         10% level   -1.615828




EDHEC Business School                   40
7   GRAPHS AND TABLES



                                     Table 3:
BSE - M1
                                     t-Statistic   Prob.*
 ADF test statistic                  -2.875518     0.41%
 Test critical values:   1% level    -2.573784
                         5% level    -1.942035
                         10% level   -1.615894



                                     Table 4:
BSE - PPI
                                     t-Statistic   Prob.*
 ADF test statistic                  -2.399055     1.62%
 Test critical values:   1% level    -2.573784
                         5% level    -1.942035
                         10% level   -1.615894



                                     Table 5:
BSE - SP500
                                     t-Statistic   Prob.*
 ADF test statistic                  -1.427184     14.30%
 Test critical values:   1% level    -2.573784
                         5% level    -1.942035
                         10% level   -1.615894




EDHEC Business School                   41
7   GRAPHS AND TABLES



                                     Table 6:
BSE - USDINR
                                     t-Statistic   Prob.*
 ADF test statistic                  -1.659522     9.17%
 Test critical values:   1% level    -2.573818
                         5% level    -1.94204
                         10% level   -1.615891




EDHEC Business School                   42
7   GRAPHS AND TABLES


7.4.4   Johansen cointegration test




EDHEC Business School            43
7   GRAPHS AND TABLES


Table 2




EDHEC Business School   44
7   GRAPHS AND TABLES


  Table 3




EDHEC Business School   45
7   GRAPHS AND TABLES


7.4.5   Impulse response tests




EDHEC Business School            46
7   GRAPHS AND TABLES




EDHEC Business School   47
7   GRAPHS AND TABLES




EDHEC Business School   48
7   GRAPHS AND TABLES




7.4.6   Granger causality test between IP and BSE




EDHEC Business School           49
8   BIBLIOGRAPHY


8    Bibliography


Eugene F. Fama, Inflation, Output and Money , Journal of Business, 1982
Eugene F. Fama, Stock Returns, Real activity and Money, The American Eco-
nomic Review, 1981
Eugene F. Fama, Stock Returns, Expected Returns and Real activity, Journal of
Finance, 1990
Pal and Mittal, Impact of macroeconomic indicators in Indian capital markets,
Journal of Risk Finance, 2011
Shahid Ahmed, Aggregate Economic Variables and Stock Markets in India, In-
ternational Research Journal of Finance and Economics, 2008
Sahu and Dhiman, Correlation and Causality between Stock Market and Macro
Economic Variables in India: An Empirical Study, 2010 International Confer-
ence on E-Business and Economics, 2011
Mohammad Bayezid Ali, Impact of Micro Variables on Emerging Stock Market
Return: A case on Dhaka Stock Exchange (DSE), Interdisciplinary Journal of
Research in Business, 2011
Napphon Tangjitprom, Macroeconomic Factors of Emerging Stock Market: The
evidence from Thailand, International Journal of Finance and Research, 2012
Sayed Mehdi Hosseini, The Role of Macroeconomic Variables on Stock Market
Index in China and India, International Journal of Economics and Finance,
2011
John Y. Campbell, Pitfalls and Opportunities: What Macroeconomists should
know about Unit Roots, NBER Working Papers, 1991
Hacker and Hatemi, The properties of Procedures Dealing with Uncertainity
about Intercept and Deterministic Trend in Unit Root Testing, CESIS Elec-
tronic Working Papers, 2010
Elder and Kennedy, Testing for Unit Roots: What should Students be Taught
Nasseh and Strauss, Stock Prices and domestic and international macroeco-
nomic activity: a cointegration approach, The Quarterly Review of Economics
and Finance, 2000
Engle and Granger, Co-Integration and Error Correction: Representation, Es-
timation and Testing, Econometrica, 1987
Eugene F. Fama, Stock Returns, Real Activity, Inflation and Money, 1981,
American Economic Association
Naliniprave Tripathy, Causal Relationship between Macro-Economic Indicators
and Stock Market in India, Asian Journal of Finance and Accounting, 2011
Rogalski and Vinso, Stock Returns, Money Supply and the Direction of Causal-
ity, The Journal of Finance, 1977
James et. al, A VARMA Analysis of the Causal Relations Among Stock Re-
turns, Real output and Nominal Interest Rates, 1985, The Journal of Finance
Bailey and Chung, Risk and return in the Philippine Equity market: A multi-
factor exploration, Pacific-Basin Finance Journal, 1996
Nai-Fu Chen, Financial Investment opportunities and the Macroeconomy, The
Journal of Finance, 1991
G.B. Wickremasinghe, Macroeconomic forces and stock prices: Some empirical
evidence from an emerging stock markets, University of Wollongong, 2006


EDHEC Business School                50
8   BIBLIOGRAPHY


Yao, Juo and Loh, On China’s Monetary Policy and Asset Prices, University of
Nottingham- China policy Institute, 2011
Bilson et. al, Selecting macroeconomic variables as explanatory factors of emerg-
ing stock market returns, Pacific-Basin Finance Journal, 2001
CHen, Roll and Ross, Economic forces and the Stock Markets, The Journal of
Business, 1986
William H. Greene, Econometric Analysis, 6th Edition, Pearson International
Edition
Ruey Tsay, Analysis of Financial Time series
Chris Brooks, Introductory Econometrics for Finance, Cambridge Publications




EDHEC Business School                  51

More Related Content

What's hot

Stock market volatility and macroeconomic variables volatility in nigeria an ...
Stock market volatility and macroeconomic variables volatility in nigeria an ...Stock market volatility and macroeconomic variables volatility in nigeria an ...
Stock market volatility and macroeconomic variables volatility in nigeria an ...
Alexander Decker
 
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
Alexander Decker
 

What's hot (18)

Choudhri et-al-2015-working-paper-1
Choudhri et-al-2015-working-paper-1Choudhri et-al-2015-working-paper-1
Choudhri et-al-2015-working-paper-1
 
Vol7no2 6
Vol7no2 6Vol7no2 6
Vol7no2 6
 
Paper (2)
Paper (2)Paper (2)
Paper (2)
 
132 article text-185-1-10-20210523
132 article text-185-1-10-20210523132 article text-185-1-10-20210523
132 article text-185-1-10-20210523
 
Causal Relationship between Stock market and Real Economy in India using Gran...
Causal Relationship between Stock market and Real Economy in India using Gran...Causal Relationship between Stock market and Real Economy in India using Gran...
Causal Relationship between Stock market and Real Economy in India using Gran...
 
Final report
Final reportFinal report
Final report
 
Dp12197
Dp12197Dp12197
Dp12197
 
Md iw mtq3nde=
Md iw mtq3nde=Md iw mtq3nde=
Md iw mtq3nde=
 
Chinh sach tien te va gia chung khoan
Chinh sach tien te va gia chung khoanChinh sach tien te va gia chung khoan
Chinh sach tien te va gia chung khoan
 
Economic indicators and stock market performance an empirical case of india
Economic indicators and stock market performance an empirical case of indiaEconomic indicators and stock market performance an empirical case of india
Economic indicators and stock market performance an empirical case of india
 
Stock market volatility and macroeconomic variables volatility in nigeria an ...
Stock market volatility and macroeconomic variables volatility in nigeria an ...Stock market volatility and macroeconomic variables volatility in nigeria an ...
Stock market volatility and macroeconomic variables volatility in nigeria an ...
 
B331321.pdf
B331321.pdfB331321.pdf
B331321.pdf
 
5.john kofi mensah 49 63
5.john kofi mensah   49 635.john kofi mensah   49 63
5.john kofi mensah 49 63
 
Macro economic factors
Macro economic factorsMacro economic factors
Macro economic factors
 
Meco and stock
Meco and stockMeco and stock
Meco and stock
 
The effects of psychology on individual investors behaviors
The effects of psychology on individual investors behaviorsThe effects of psychology on individual investors behaviors
The effects of psychology on individual investors behaviors
 
Scope book (1)
Scope book (1)Scope book (1)
Scope book (1)
 
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
6.[43 53]stock market volatility and macroeconomic variables volatility in ni...
 

Viewers also liked

1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
Alexander Decker
 
Macroeconomic and microeconomic factors Presentation
Macroeconomic and microeconomic factors PresentationMacroeconomic and microeconomic factors Presentation
Macroeconomic and microeconomic factors Presentation
Kristie Soder
 
Project report on Wealth Management
Project report on Wealth ManagementProject report on Wealth Management
Project report on Wealth Management
Khushbu Malara
 
Investment banking
Investment bankingInvestment banking
Investment banking
Dharmik
 
Macroeconomics slide
Macroeconomics slideMacroeconomics slide
Macroeconomics slide
Thao Nguyen
 
A study on Exchange Rates and its impact on stock prices
A study on Exchange Rates and its impact on stock pricesA study on Exchange Rates and its impact on stock prices
A study on Exchange Rates and its impact on stock prices
Daksh Bhatnagar
 

Viewers also liked (16)

Macroeconomic factors that affect the quality of lending in albania.
Macroeconomic factors that affect the quality of lending in albania.Macroeconomic factors that affect the quality of lending in albania.
Macroeconomic factors that affect the quality of lending in albania.
 
Stock market and the economy ppt slides
Stock market and the economy ppt slidesStock market and the economy ppt slides
Stock market and the economy ppt slides
 
Impact of Macroeconomic Factors on Income Inequality and Income Distribution ...
Impact of Macroeconomic Factors on Income Inequality and Income Distribution ...Impact of Macroeconomic Factors on Income Inequality and Income Distribution ...
Impact of Macroeconomic Factors on Income Inequality and Income Distribution ...
 
1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
1.[1 14]the impact of macroeconomic indicators on stock prices in nigeria
 
A Study on Exchange Rate Volatility and its Macro Economic Determinants in India
A Study on Exchange Rate Volatility and its Macro Economic Determinants in IndiaA Study on Exchange Rate Volatility and its Macro Economic Determinants in India
A Study on Exchange Rate Volatility and its Macro Economic Determinants in India
 
Macroeconomic and microeconomic factors Presentation
Macroeconomic and microeconomic factors PresentationMacroeconomic and microeconomic factors Presentation
Macroeconomic and microeconomic factors Presentation
 
Macroeconomic Performance - India
Macroeconomic Performance - IndiaMacroeconomic Performance - India
Macroeconomic Performance - India
 
Devanayagam_Impact of Macroeconomic Variables on Global Stock Markets
Devanayagam_Impact of Macroeconomic Variables on Global Stock MarketsDevanayagam_Impact of Macroeconomic Variables on Global Stock Markets
Devanayagam_Impact of Macroeconomic Variables on Global Stock Markets
 
Project report on Wealth Management
Project report on Wealth ManagementProject report on Wealth Management
Project report on Wealth Management
 
Investment banking
Investment bankingInvestment banking
Investment banking
 
Investment Banking
Investment BankingInvestment Banking
Investment Banking
 
Macroeconomics slide
Macroeconomics slideMacroeconomics slide
Macroeconomics slide
 
Finance projects topics
Finance projects topicsFinance projects topics
Finance projects topics
 
A study on Exchange Rates and its impact on stock prices
A study on Exchange Rates and its impact on stock pricesA study on Exchange Rates and its impact on stock prices
A study on Exchange Rates and its impact on stock prices
 
Project on investment banking
Project on investment bankingProject on investment banking
Project on investment banking
 
KEY PERFORMANCE INDICATOR
KEY PERFORMANCE INDICATORKEY PERFORMANCE INDICATOR
KEY PERFORMANCE INDICATOR
 

Similar to An empirical study of macroeconomic factors and stock market an indian perspective

Nduati Michelle Wanjiku Undergraduate Project
Nduati Michelle Wanjiku Undergraduate ProjectNduati Michelle Wanjiku Undergraduate Project
Nduati Michelle Wanjiku Undergraduate Project
Michelle Nduati
 
Kostadinov.T._6346839._MSc.BS
Kostadinov.T._6346839._MSc.BSKostadinov.T._6346839._MSc.BS
Kostadinov.T._6346839._MSc.BS
Todor Kostadinov
 
Teemu Blomqvist Pro Gradu Final 12122016
Teemu Blomqvist Pro Gradu Final 12122016Teemu Blomqvist Pro Gradu Final 12122016
Teemu Blomqvist Pro Gradu Final 12122016
Teemu Blomqvist
 
Dissertation_Capital Structure final
Dissertation_Capital Structure finalDissertation_Capital Structure final
Dissertation_Capital Structure final
Jasmin Taylor
 

Similar to An empirical study of macroeconomic factors and stock market an indian perspective (20)

PREDICTABILITY OF MARKET RETURNS USING BOOK TO MARKET RATIO
PREDICTABILITY OF MARKET RETURNS USING BOOK TO  MARKET RATIOPREDICTABILITY OF MARKET RETURNS USING BOOK TO  MARKET RATIO
PREDICTABILITY OF MARKET RETURNS USING BOOK TO MARKET RATIO
 
Nduati Michelle Wanjiku Undergraduate Project
Nduati Michelle Wanjiku Undergraduate ProjectNduati Michelle Wanjiku Undergraduate Project
Nduati Michelle Wanjiku Undergraduate Project
 
Prévisions des crises
Prévisions des crises Prévisions des crises
Prévisions des crises
 
68
6868
68
 
solomonaddai
solomonaddaisolomonaddai
solomonaddai
 
Master thesis
Master thesisMaster thesis
Master thesis
 
Sales and operations planning a research synthesis
Sales and operations planning  a research synthesisSales and operations planning  a research synthesis
Sales and operations planning a research synthesis
 
PhD_Thesis_Dimos_Andronoudis
PhD_Thesis_Dimos_AndronoudisPhD_Thesis_Dimos_Andronoudis
PhD_Thesis_Dimos_Andronoudis
 
Kostadinov.T._6346839._MSc.BS
Kostadinov.T._6346839._MSc.BSKostadinov.T._6346839._MSc.BS
Kostadinov.T._6346839._MSc.BS
 
okafor2021.pdf
okafor2021.pdfokafor2021.pdf
okafor2021.pdf
 
D0962227
D0962227D0962227
D0962227
 
FYP
FYPFYP
FYP
 
tkacik_final
tkacik_finaltkacik_final
tkacik_final
 
The value at risk
The value at risk The value at risk
The value at risk
 
Teemu Blomqvist Pro Gradu Final 12122016
Teemu Blomqvist Pro Gradu Final 12122016Teemu Blomqvist Pro Gradu Final 12122016
Teemu Blomqvist Pro Gradu Final 12122016
 
Bma
BmaBma
Bma
 
Forecasting Economic Activity using Asset Prices
Forecasting Economic Activity using Asset PricesForecasting Economic Activity using Asset Prices
Forecasting Economic Activity using Asset Prices
 
A Quantitative Analysis of Indian Banks’ Performance and Efficiency-A Panel R...
A Quantitative Analysis of Indian Banks’ Performance and Efficiency-A Panel R...A Quantitative Analysis of Indian Banks’ Performance and Efficiency-A Panel R...
A Quantitative Analysis of Indian Banks’ Performance and Efficiency-A Panel R...
 
Dissertation_Capital Structure final
Dissertation_Capital Structure finalDissertation_Capital Structure final
Dissertation_Capital Structure final
 
EC331_a2
EC331_a2EC331_a2
EC331_a2
 

Recently uploaded

Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
Anamikakaur10
 
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
lizamodels9
 
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
amitlee9823
 
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
dlhescort
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
lizamodels9
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
amitlee9823
 

Recently uploaded (20)

The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
The Path to Product Excellence: Avoiding Common Pitfalls and Enhancing Commun...
 
(Anamika) VIP Call Girls Napur Call Now 8617697112 Napur Escorts 24x7
(Anamika) VIP Call Girls Napur Call Now 8617697112 Napur Escorts 24x7(Anamika) VIP Call Girls Napur Call Now 8617697112 Napur Escorts 24x7
(Anamika) VIP Call Girls Napur Call Now 8617697112 Napur Escorts 24x7
 
Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
Call Now ☎️🔝 9332606886🔝 Call Girls ❤ Service In Bhilwara Female Escorts Serv...
 
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
Call Girls From Pari Chowk Greater Noida ❤️8448577510 ⊹Best Escorts Service I...
 
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
Enhancing and Restoring Safety & Quality Cultures - Dave Litwiller - May 2024...
 
Monthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptxMonthly Social Media Update April 2024 pptx.pptx
Monthly Social Media Update April 2024 pptx.pptx
 
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
Nelamangala Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore...
 
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
Call Girls in Delhi, Escort Service Available 24x7 in Delhi 959961-/-3876
 
It will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 MayIt will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 May
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023Mondelez State of Snacking and Future Trends 2023
Mondelez State of Snacking and Future Trends 2023
 
VVVIP Call Girls In Greater Kailash ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Greater Kailash ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...VVVIP Call Girls In Greater Kailash ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Greater Kailash ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
 
Eluru Call Girls Service ☎ ️93326-06886 ❤️‍🔥 Enjoy 24/7 Escort Service
Eluru Call Girls Service ☎ ️93326-06886 ❤️‍🔥 Enjoy 24/7 Escort ServiceEluru Call Girls Service ☎ ️93326-06886 ❤️‍🔥 Enjoy 24/7 Escort Service
Eluru Call Girls Service ☎ ️93326-06886 ❤️‍🔥 Enjoy 24/7 Escort Service
 
How to Get Started in Social Media for Art League City
How to Get Started in Social Media for Art League CityHow to Get Started in Social Media for Art League City
How to Get Started in Social Media for Art League City
 
Uneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration PresentationUneak White's Personal Brand Exploration Presentation
Uneak White's Personal Brand Exploration Presentation
 
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRLBAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
 
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
 
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
 
Value Proposition canvas- Customer needs and pains
Value Proposition canvas- Customer needs and painsValue Proposition canvas- Customer needs and pains
Value Proposition canvas- Customer needs and pains
 

An empirical study of macroeconomic factors and stock market an indian perspective

  • 3. An Empirical Study of Macroeconomic Factors and Stock Market: An Indian Perspective Saurabh Yadav EDHEC Business School Master’s in Risk and Investment Management saurabh.yadav@edhec.com June 26, 2012 EDHEC Business School
  • 4. Abstract This thesis is an empirical study of relationship between Indian stock markets and macro economy. There is a huge literature about such kind of empirical studies but mostly on US/UK stock markets and macroeconomic indicators. This study is similar to many of the earlier studies in some aspects, so it uses econometric tools used in earlier studies but at the same time this study differentiates itself from other studies in the sense it uses Indian markets and macroeconomic data for analysing the relationship and it also tries to analyse the impact of global economy on the Indian markets. The period that will be used for the study will be from 1990 to 2011. We have chosen this period as it represents big regulatory and structural changes in Indian economy. So, an analysis of this period can provide us with insights to how some regulatory and structural changes impact the economy and asset prices in that country. In this study we will use Unit root tests, cointegration, Ljung-Box Q test and multivariate VAR analysis for analysing each macro economic and asset prices time series individually and to build a model that can analyse the impact of one over the other. Also, we will conduct Granger’s Causality test and Impulse response analysis between Stock market and macro economic indicators to analyze the impact of macro economic news/shocks on India Stock index (BSE). EDHEC Business School 4
  • 5. Acknowledgment I am thankful to Professor Robert Kimmel for his comments and guidance on the subject. He has been a constant source of inspiration and a good men- tor, from whom I learned a lot. I am also grateful to Stoyan Stoyanov, Marc Rakotomalala, Aishwarya Iyer, Wen lei, Lixia Loh for some great insights into the subject. Their timely comments and suggestions on empirical tests helped me improve the statistical significance of my tests. I thank EDHEC Risk In- stitute for allowing me to use their resources to get the data from various data providers. In the end i’ll like to thank my parents and my sister for constant support and motivation without which it would have been impossible to climb this arduous path. Regards, Saurabh YADAV EDHEC Business School 5
  • 6. CONTENTS Contents 1 Introduction 7 2 Literature Review 9 3 Data 13 3.1 Description of Macroeconomic Indicators . . . . . . . . . . . . . 13 3.2 Description of Stock Market Indices . . . . . . . . . . . . . . . . 14 4 Methodology 15 4.1 Construction of Time Series . . . . . . . . . . . . . . . . . . . . 15 4.2 Unit Root Test and Stationarity . . . . . . . . . . . . . . . . . . . 15 4.2.1 Mathematical representation of Stationary series and unit root test . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.2.2 Augmented Dickey Fuller Unit Root Test . . . . . . . . . 17 4.3 Testing Long Term Relationships . . . . . . . . . . . . . . . . . . 18 4.3.1 Johansen test for Cointegration . . . . . . . . . . . . . . . 18 4.4 Impulse Response . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 5 Results 21 6 Conclusions 24 7 Graphs and Tables 25 7.1 Graphs of Time series . . . . . . . . . . . . . . . . . . . . . . . . 25 7.2 Graphs of Time Series - Differenced . . . . . . . . . . . . . . . . 29 7.3 Correlograms of Time series . . . . . . . . . . . . . . . . . . . . . 33 7.4 Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 7.4.1 Table for Unit root test of Time series . . . . . . . . . . . 40 7.4.2 Tables for Unit root test of Differenced time series . . . . 40 7.4.3 Tables for Residual based test of cointegration . . . . . . . 40 7.4.4 Johansen cointegration test . . . . . . . . . . . . . . . . . 43 7.4.5 Impulse response tests . . . . . . . . . . . . . . . . . . . . 46 7.4.6 Granger causality test between IP and BSE . . . . . . . . 49 8 Bibliography 50 EDHEC Business School 6
  • 7. 1 INTRODUCTION 1 Introduction In the past few decades there has been a growing interest among academicians and practitioners about the relationship between macroeconomic variables and asset prices, mainly stocks and house prices. In a good and expanding economy, prices of stocks are supposed to increase as there is an increase in expectation of large future cash flows/ profits for the companies and various role players in the economy. Similarly, during a bad or downward spiralling economy the expectation of large future cash flows and profits decrease and consequently the price of stocks decrease. Stock markets are representative of economy of a country and investors belief. They are able to capture macro economic movements in the economy as well as idiosyncratic factors related to each company or industry. As Stock prices are real time and are more frequent than macroeconomic releases they are better reflector of changes in domestic and global economy and can predict the move- ment of macroeconomic indicators. In other words stock markets are a leading indicator of the economy. Markets respond to different macroeconomic indicators in different ways. The response of Stock markets to any macroeconomic news is dependent on how the news will effect the profits and interest rates. The price of the stock according to the Discounted Cash Flow formula is: Div1 Div2 Divt Pt = + + ... + (1) (1 + r1 )1 (1 + r2 )2 (1 + rt )t As both dividends and interest rates enter into the formula for value of a stock the reaction of stock price to a macro news will depend on how the news effect the discounting factor ( Interest rates ) and future profits of the com- panies. Macro economic factors that project brighter times and more profits for the companies like, increasing Industrial production, Increasing M1 money supply, good consumer confidence levels will have a positive effect on the stock prices. Whereas, macro news that point to economic recession or slow growth like, decreasing Industrial production coupled with Rising interest rates, Rise in inflation, rise in unemployment, etc. will have a downward effect on stock prices. First people to do an empirical study on this subject were Eugene Fama and Kenneth French. In their 1981 paper ”Stock returns, Real activity, Inflation and money” they analysed the relationship between stock returns, real activity inflation and money supply using macro economic data. After that study there has been a barrage of studies on relationship between stock returns and macro economic factors based on US and UK data. Another important paper pub- lished on this research was by Chen,Roll and Ross (1986) who analysed whether innovations in the macroeconomic variables are risks that are awarded in the stock markets. They found that macroeconomic variables like, spread between long and short interest rates, expected and unexpected inflation, Industrial pro- duction are some of the factors that are awarded by the markets. Further, the Arbitrage pricing theory (APT) of Ross (1976) posits relation between stock prices and certain macro-economic variables. In the last decade or so the focus for these kind of studies have started to shift from developed world economies to developing world economies. As developing world economies have shown signs EDHEC Business School 7
  • 8. 1 INTRODUCTION of huge growth potential and leading the economies globally out of recessions, this motivates us to research on developing markets, like India. Such a study will help us to find the relation between stock market and macroeconomic indi- cators and give a new insight to foreign investors, academicians,policy makers, traders and domestic investors. This study is important in a sense it provides an insight to how are Indian stock markets are related to its macroeconomic variables and global macro/micro eco- nomic factors. This study will also help us in analysing whether the Indian stock markets have become coupled to global factors or are they still dominated by domestic economic factors. The focus of this study is on relation between Indian stock market, represented by BSE Sensex, and domestic macroeconomic factors and global factors repre- sented by Standard and Poor’s 500 Index. This study builds on earlier studies done in this area but also open some new doors for further research. It is sim- ilar to some earlier studies in a respect that it uses data, macro and micro factors and econometrics tools used in previous studies but at the same time it differentiates itself from earlier studies in a sense that it is done on a market that is still developing. Also, the time period used in the analysis is a period where Indian market has undergone lot of regulatory changes that has created a structural change in the market. Further, in this study I’ll analyse whether the Indian markets are driven mainly by Domestic factors or do global factors have more influence on Indian markets. To analyse the impact of international factors I’ll use Standard and Poor’s 500 Index and USDINR exchange rate as a substitute of global factors and to model domestic demand I’ll use macro factors like Industrial production, M1 money supply, Consumer Price Index and Pro- ducer price Index. The outline of the thesis is as followings: Section 2 provides a literature review of the studies done earlier in this area, Section 3 provides a detailed description of the data used in the study Section 4 provides a detailed description of the methodology and various econometric tools that will be used in the study, Section 5 provides the results of the study and Section 6 provides the conclusion of the study. EDHEC Business School 8
  • 9. 2 LITERATURE REVIEW 2 Literature Review Many studies and researchers have tried to find factors that can explain stock returns. The most famous and earliest model is the Capital Asset Pricing Model (CAPM), developed by Sharpe (1964), Lintner (1965), Mossin (1967) and Black (1972). The concept of this single factor model is developed from diversifi- cation introduced by Markowitz (1952). In CAPM model the expected stock returns can be explained with the help of Risk free rate and one risk factor, Market. CAPM says that the systematic risk can be captured by sensitiveness of each stock to change in overall market, which is measured by Beta. According to CAPM, the market factor is the only factor determining the stock returns. CAPM was a revolutionary model. It changed the way people looked at the stock returns as something that is vary arbitrary. As it is very easy to under- stand and use, CAPM is very popular as the model used to determine the stock return in most of finance textbooks and used by many practitioners in stock market. However, the numerous set of assumptions made in deriving CAPM made it inconsistent with the real world and led to criticism of CAPM. To overcome the limitations and assumptions made in CAPM many scholars came up with multi- factor models like Fama-French three factor model, APT model, etc. In Fama-French model they try to explain stock returns with help of three factors, market,small minus big and value minus growth. the model was able to explain the returns based on these risk factors for some time before it failed. There have been many studies on failure of Fama-French model and markets where it is not applicable. The macroeconomic models of explaining stock returns started with APT (Ar- bitrage Pricing Theory) by Ross (1976), which was later refined by Roll and Ross (1980). APT is a multi-factor model and claims that the stock return can be explained by unexpected changes or shocks in multiple factors. Chen,Roll and Ross (1986) perform the empirical study for APT model and identify that surprise or shock in macroeconomic variables can explain the stock return sig- nificantly. The variables used in their study are Industrial production index, default risk premium that can measure the confidence of investors, and change in yield curve that can be measured by term premium. The study of macroeconomic factors in explaining stock returns have been pop- ular since then. Stock price is present value of all discounted future cash flows. If a firm is performing well then the expectation of large future cash flows rises and consequently the stock price rises. On the other hand if a firm is performing bad for couple of years then the expectation of big future cash flows decrease and in turn the stock price fall. This is a micro and idiosyncratic explanation of stock prices and returns. But, the future cash flows of a stock does not depend solely on the company’s performance or profits/loss. The systematic factor can have a huge impact on the cash flows of not only one but many companies. The systematic factor here refers to macro economic variables. The state of Macro economic conditions lead to changes in Monetary and regulatory policies by the government and which in turn affects the stock prices. For example a country with good economic conditions, represented by its Industrial production index, GDP, CPI, Interest rates will create an environment that is conducive for the growth of companies by lowering borrowing rates and other open market opera- tions. So, all macroeconomic factors that can influence future cash flows or the EDHEC Business School 9
  • 10. 2 LITERATURE REVIEW discount rate by which the cash flows are discounted should have an influence on the stock price. Many researcher have studies the relationship between stock prices and macro economic variables and tried to explain the affect of one over the other. Fama (1981) tries to establish a relationship between stock returns, real activity, infla- tion and money. In his paper he finds that Stock returns have positive relation with real output and money supply but a negative relation with inflation. He explains that negative relation between stock returns and inflation is induced by negative relation between real output, approximated by Industrial production, and inflation. This negative relationship between inflation and real activity is explained by money demand theory and quantity theory of money. Fama (1990) explains that measuring the total return variation explained by shocks to expected cash flows, time-varying expected returns, and shocks to expected returns is one way to judge the rationality of stock prices. In his paper he finds that growth rates of production, used to proxy for shocks to expected cash flows, explain 45% of return variance. Chen,Roll and Ross (1986) explored the relationship between a set of economic variables and their systematic influence on stock market returns. They found that Industrial production, changes in risk premium, twists in yield curve had strong relationship and impact on stock returns. A somewhat weaker effect was found for measures of unanticipated inflation and changes in expected inflation during periods when these variables were highly volatile. They concluded that stock returns were exposed to sys- tematic economic news, that they are priced in accordance to their exposures, and that the news can be measured as innovation in state variables. Chen (1991) found that state variables that are priced are those that can forecast changes in the investment and consumption opportunity set. According to his research, default spread, the term spread, the one-month T-Bill rate, the lagged industrial production growth rate, and the dividend-price ration are important determinants of future stock market returns. Bulmash and Trivoli (1991) show the effect of business cycle movements on the relationship between stock returns and money growth. An interesting paper in this field of research is by Fama (1990) and Schwert (1990). In the paper they claim that there are three explanations for the strong link between stock prices and real economic activity: “First, information about the future real activity may be reflected in stock prices well before it occurs — this is essentially the notion that stock prices are a leading indicator for the well-being of the economy. Second, changes in discount rates may affect stock prices and real investment similarly, but the output from real investment doesn’t appear for some time after it is made. Third, changes in stock prices are changes in wealth, and this can affect the demand for consumption and investment goods” [Schwert (1990),p.1237] Campbell and Ammer (1993) use a VAR approach to model the simulta- neous interactions between the stock and bond markets, since most previous works do not address the channels through which the macroeconomic activity influences the stock prices. One example could be that industrial production could be linked to changing expectations of future cash flows (Balvers at al. 1990). On the other hand, interest rate innovations could be the driving factor EDHEC Business School 10
  • 11. 2 LITERATURE REVIEW in determining both industrial production (due to change in investment) and stock prices (due to change in the discounted present value of future cash flows). A VAR analysis can distinguish these possibilities. Mukherjee and Naka (1995) show a long-term relationship between the Japanese stock price and real macroe- conomic variables. Dr. Nishat (2004) studies the long term association among macroeconomic variables like money supply, CPI,IPI, and foreign exchange rate and stock markets in Pakistan. The results show that there are causal relation- ship among the stock price and macroeconomic variables. He uses data from 1974 to 2004 in his study. As most of the financial time series are non station- ary in levels he uses unit root technique to make data stationary. Fazal Hussian and Tariq Massod (2001) used variables like investment, GDP and consumption employing Granger’s causality test to find relationship between macro factors and stock markets. They show that at two lags all macroeconomic variables have highly significant effect on stock prices. James et al. (1985) use a VARMA analysis for investigating relationship between macro economy and stock mar- ket. Using VARMA analysis for finding causal relationship between factors is a better technique as the procedure does not preclude any causal structure a priori since it allows feedback among variables. Thus, the VARMA approach allow whatever causal relationship exist to emerge from the data. They find linkages between real activity and stock returns and real activity and inflation. Also, they find that stock returns signal changes in the monetary base. Since stock returns also signal changes in expected real activity, this suggests a link between the money supply and expected real activity that is consistent with the money supply explanation offered by Geske and Roll. In recent years the focus of these kind of studies have shifted from developed economies to developing economies. As developing economies are the economies that see a lot of structural and monetary policy changes an analysis of relation- ship between macro and micro can provide new insights. Also, one can analyse the effects of monetary policies on the asset prices especially on stock prices. Tangjitprom (2012) study of macroeconomic factors like unemployment rate, interest rate, inflation rate and exchange rate and stock market of Thailand con- cludes that macroeconomic factors significantly explain stock returns. He also finds that for Thailand unemployment rate and inflation rate are insignificant to determine the stock returns. The reason he provides is that the unemployment rate and inflation rate are not timely and there could be some lags before the data becomes available. Also, Granger’s test to examine lead-lag relationship among the factors reveal that only few macroeconomic variables could predict the future stock returns whereas the stock returns can predict most of future macro economic variables. This implies that performance of stock markets can be a leading indicator for future macroeconomic conditions. Ali (2011) study of impact of macro and micro factors on stock returns reveals that inflation and foreign remittance have negative influence and industrial production index have positive impact on stock markets. Also he didn’t found any Granger’s Causal- ity between stock markets and any of the explanatory variables. This lack of Granger’s causality reveals the evidence of informationally inefficient markets. Ali uses a multivariate regression analysis on standard OLD formula for estimat- ing the relationship. Hosseini et al. (2011) tested the relationship between stock markets and four macro economic variables namely crude oil prices, Money sup- ply, Industrial production and inflation rate in China and India. They used a period of 1999 to 2009 for analysis. As most of the economic time series have unit EDHEC Business School 11
  • 12. 2 LITERATURE REVIEW root, they first used the Augmented Dickey Fuller unit root test and found the underlying series to be non-stationary at levels but stationary after in difference. Also, the use of Jhonson-Juselius (1990) Multivariate cointegration and Vector Error Correction model technique, indicate that there are both long and short run linkages between macroeconomic variable and stock market index in each of the two countries. Their analysis shows that in long run the impact of increase in prices of crude oil for China is positive but for India is negative. In terms of money supply, the impact on Indian stock market is negative, but for China, there is a positive impact. The effect of Industrial production is negative only in China. In addition the effect of increases in inflation on these stock markets is positive in both countries. Wickremasinghe (2006) analysed the relationship between stock prices and macroeconomic variables in Sri Lanka. He used the Unit root tests, Jhonson’s test, Error-correction model, variance decomposi- tion and impulse response to analyse the relationships. His findings indicate that there is both long term and short term causal relationship between stock prices and macroeconomic variables in Sri Lanka. The result indicate that the stock prices can be predicted from certain macroeconomic variables and hence violate the validity of the semi-strong version of efficient market hypothesis. Ahmed (2008) investigates the causal relationship between Indian macroeco- nomic factors like Industrial Production, Exports, Foreign direct investment, Money supply, exchange rate, interest rate and stock market indices NSE Nifty Index and BSE Sensex. For finding the long term relationship he applies Jo- hansen’s cointegration and Toda and Yamamoto Granger Causality tests. For analysing the Impulse response and variance decomposition he uses bivariate VAR. His findings reveal that stock prices in India lead macroeconomic activity except movement in interest rate. Interest rate seem to lead the stock price. The study also reveals that movement of stock prices is not only the outcome of behaviour of key macro economic variables but it is also one of the causes of movement in other macro dimensions in the economy. An important paper by Bilson et al. (2001) argues that emerging markets local factors are more important than global factors. They find that for emerging markets are at least partially segmented from global capital markets. The global factors are proxied by world market returns and local factors by set of macro economic variables like money supply, prices, real activity and exchange rate. Some evidence is found that local factors are significant in their association with emerging equity market returns above than that explained by the world factor. When they use a larger set of variables the explanatory power of the model improves substan- tially such that they are able to explain a large amount of return variation for most emerging markets. EDHEC Business School 12
  • 13. 3 DATA 3 Data 3.1 Description of Macroeconomic Indicators One of the biggest problems when conducting a research with macroeconomic data is the frequency of the data. Most of the macroeconomic indicator time series are yearly,quarterly or monthly time series. This low frequency of the macroeconomic indicators results in very few data points for conducting a anal- ysis that is robust. A possible cure for the problem is to use longer time periods to incorporate more data points for macroeconomic variables. But, another problem that we face when we look at the macroeconomic indicators for Asian countries is reporting of the data. For most of the Asian countries the macroe- conomic data doesn’t have a long history and same can be said about history of Indian macroeconomic variables. So, in this research we have used a time period for which we can find data for most of the macroeconomic indicators. In this paper we use a time period of 20 years starting from 1990 to 2011. This time period in Indian economy is representative of many structural and mone- tary policy changes like liberalization of India markets. Also as the time period is long it gives us enough data point for each macroeconomic factors to do a robust empirical analysis. When one starts to build a model of interaction between macro and micro eco- nomic factors one dominant and important question one faces is, among the myriad of macro indicators available for an economy which factors to choose to incorporate in the model. If one chooses macroeconomic factors that are highly correlated among themselves then the power of test results decrease as it may result in a model where the macro indicators are able to explain most of the movement of micro factors but the macro factors may not be relevant. To circumvent this problem we use variables that have been tested in earlier researches and that have been proven to have effect on stock markets. I also test a few macro factors that have some financial theory behind them that con- nect them to stock markets. Ali (2011), Wickremasinghe (2006), Bilson et.al (2001) and Bailey (1996) find that Industrial production, CPI, exchange rate, M1 money supply, GDP are few of the macro economic factors that can signifi- cantly explain stock returns. Sahu(2011), Ahmed(2008), Tripathy(2011) study on Indian markets specifically show that Industrial Production, Exchange rate, Inflation index are macro economic indicators that have a strong positive or negative relationship with the stock markets. So, in our study we test 5 macro economic variables namely M1 money supply, Consumer and Producer price In- dex, Industrial production, Exchange rate. The time period for these indicators is from 1990-2011. The data for Inflation indices, Industrial production and exchange rate has been pulled from Bloomberg c and Datastream c . The data has been processed for errors and missing values. Data for M1 money supply has been pulled from RBI website. For most of the indices like inflation and Industrial production index, the base year has been changed to 1990. Also, as some of the indices are in levels and some in actual figures (M1 money supply), we convert all of the indicators to level form (starting at 100 in 1990). EDHEC Business School 13
  • 14. 3 DATA 3.2 Description of Stock Market Indices Compared to Macro Indicators, stock market data is relatively easy to find and has considerably long history. Also, the stock market data is a real time data so it has a very high frequency of seconds. Here, in our analysis we will make use of BSE (Bombay Stock Exchange) as representation of Indian markets and SP500 (Standard and Poor’s 500 Index) as representation of global factors. BSE is a market cap-weighted of 30 stocks. It is the oldest Index in the Asian markets (established in 1875) and have had a long history. We choose this index as it is the Index that represent the most liquid and traded stocks of the Indian stock market. Also, the index is most traded index in India and a good representation of trade prices of the stocks. Even in terms of an orderly growth, much before the actual legislations were enacted, BSE Limited had formulated a compre- hensive set of Rules and Regulations for the securities market. It had also laid down best practices which were adopted subsequently by 23 stock exchanges which were set up after India gained its independence. Our choice of SP500 is based on the fact that it has a long history and many researchers have used this index as a good proxy representation of global markets and economic con- ditions. We will take the monthly returns of each of the indices from 1990-2011 in accordance with data frequency of macro economic variables. Also, as the indices have different levels at beginning of 1990 we rebase both the indices to base year of 1990 starting at a level of 100. EDHEC Business School 14
  • 15. 4 METHODOLOGY 4 Methodology 4.1 Construction of Time Series The first step in constructing an econometric model is constructing time series all of which are in same units. Most of the time series used in our analysis are in different formats. For example CPI, PPI, BSE Index, SP500 are in levels. M1 money supply, USDINR exchange rate is in absolute current format. Industrial production is in absolute production levels. So, first we convert all of the given time series to level. The way we construct time series in levels is firstly taking the initial data point of each time series as 100. We then find the percentage change from one period to the next one for each time series using a continuous compounding assumption (taking a natural log of change in values). In math- ematical terms it can be stated as: Assume the original Index value at time t to be It and at time t+1 to be It + 1. Then we can compute the new rebased index by formula: RIt+1 = RIt ∗ (1 + ln(It+1 /It )) where, RIt = Rebased Index at time t RIt+1 =Rebased Index at time t+1 We can use these rebased indices in building and testing our econometric model. 4.2 Unit Root Test and Stationarity Unit root test is to find whether the series is stationary or non-stationary. A strictly stationary process is one where, for any t1 , t2 ,...., tt ∈Z, any k ∈Z and T=1,2,... Fyt1 ,yt2 ,yt3 ,....,ytT (y1 , ...., yT ) = Fyt1+k ,yt2+k ,yt3+k ,....,ytT +k (y1 , ...., yT ) where F represents joint distribution function of the set of random variables. It can also be stated that the probability measure of sequence of yt is same as yt+k for all k. In other words a series is stationary if the distribution of its value remain the same as time progresses. Similar to the concept of strict stationary is weakly stationary process. A weakly stationary process is one which has a constant mean, variance and autocovariance structure. Stationary is a necessary condition for a time series to be tested in regression. A non-stationary series can have several problems like: 1. The shocks given to the series would not die of gradually, resulting in increase of variance as time passes. 2. If the series is non stationary then it can lead to spurious regressions. If two series are generated independent of each other then if one is regressed on other it will result in very low R2 values. But if two series are trending over time then a regression of one over the other will give high R2 even though the series may be unrelated to each other. So, if normal regressions tools EDHEC Business School 15
  • 16. 4 METHODOLOGY are used on non stationary data then it may result in good but valueless results. 3. If the variables employed in a regression model are not stationary, then it can be proved that the standard assumptions for asymptotic analysis will not be valid. In other words, the usual ’t-ratios’ will not follow a t-distribution, and the F-statistic will not follow an F-distribution, and so on. Stationarity is a desirable condition for any time series so that it can be used in regressions and give meaningful result that have some value. to test for sta- tionarity a quick and dirty way is looking at the autocorrelation and partial correlation function of the series. If the series is stationary then the autocorre- lation function should die off gradually after few lags and the partial correlation function will me non zero for some lags and zero thereafter. Also we can use the Ljung-Box test for testing that all m of σk autocorrelation coefficients are zero using Q-statistic given by formula: σk 2 Q = T (T + 2)Σm k=1 ∼ χ2 T −k where, T = Sample size and m = Maximum lag length The lag length selection can be based on different Information Criteria like Akaike’s Information criteria (AIC), Schwarz’s Bayesian information criteria (SBIC), Hannan-Quinn criterion (HQIC). Mathematically different criteria are represented as: 2k AIC = ln(σ 2 ) + T k SBIC = ln(σ 2 ) + T lnT 2k HQIC = ln(σ 2 ) + T ln(ln(T )) For a better test for stationarity we use augmented Dickey fuller Unit root test on each time series separately. Augmented Dickey Fuller test is test of null hypothesis that the time series contains a unit roots against a alternative hypothesis that the series is stationary. 4.2.1 Mathematical representation of Stationary series and unit root test Assume a variable Y whose structure can be given by AR process with no drift equation: yt = φ1 yt−1 + φ2 yt−2 + φ3 yt−3 + ... + φn yt−n + ut (2) where, ut is the residual at time t. Using a Lag operator L we can write eq.(1) as: yt = φ1 L1 yt + φ2 L2 yt + φ3 L3 yt + ... + φn Ln yt + ut (3) EDHEC Business School 16
  • 17. 4 METHODOLOGY Rearranging eqn. (2) we get, yt − φ1 L1 yt − φ2 L2 yt − φ3 L3 yt + ... − φn Ln yt = ut (4) 1 2 3 n yt (1 − φ1 L − φ2 L − φ3 L + ... − φn L ) = ut (5) or, φ(L)yt = ut (6) The time series is stationary if we can write eqn.(5) in form, yt = φ(L)−1 ut (7) with φ(L)−1 converging to zero. It means the autocorrelation function would decline as lag length is increased. If eqn. (6) is expanded to a MA(∞) process the coefficients of residuals should decrease such that the the residuals that the effect of residuals decrease with increase in lags. SO, if the process is stationary the coefficients of residuals will converge to zero and for non-stationary series they will and converge to zero and will have long term effect. The condition for testing of unit root for an AR process is that the roots of eqn.(6) or ’Charac- teristic equation’ should lie outside unit circle. 4.2.2 Augmented Dickey Fuller Unit Root Test Consider an AR(1) process of variable Y yt = φyt−1 + ut (8) Subtracting yt−1 from both sides of eqn.(7) we get, ∆y = (φ − 1)yt−1 + ut (9) Eqn.(8) is the test equation for Dickey Fuller test. For Dickey-Fuller Unit root test, Null Hypothesis: The value of φ is equal to 1 or value of φ − 1 is equal to 0 v/s, Alternate Hypothesis: The value of φ is less than one or value of φ − 1 is less than zero Augmented Dickey-Fuller test is similar to normal Dickey-Fuller tests except, it takes the lag structure of more than one into account. p ∆y = ψyt−1 + αi ∆yt−i + ut (10) i=1 If the series has one or more unit root it is said to be integrated of order n, where n is the number of unit roots of the characteristic equation. To make these time series stationary they needs to be differenced. Mathematically, if yt ∼ I (n) (11) then ∆ (d) yt ∼ I (0) (12) To make our time-series stationary we will use the natural log returns of these series in the analysis. EDHEC Business School 17
  • 18. 4 METHODOLOGY 4.3 Testing Long Term Relationships Engle and Granger (1987) in their seminal paper described cointegration which forms the basis for testing for long term relationship between variables. Accord- ing to Engle and Granger two variables are cointegrated if they are integrated process in their natural form (of the same order), but a weighted combination of the variables can be found such that the combined new variable is integrated of order less than the order of individual time series. Mathematically, assume yt to be a k X 1 vector of variables, then the components are cointegrated or integrated of order (d,b) if: 1. All components of yt are I(d) 2. There is at least one vector of coefficients α such that α yt ∼ I (d − b) (13) As most of the financial time series are integrated of order one we will restrict ourselves to case d=b=1. Two or more variables are said to be cointegrated if there exist a linear combination of these variables that is stationary. Many of the series are non-stationary but ’move together’ over time which implies two series are bound by some common force or factor in long run. We will test for cointegration by a residual-based approach and Johansen’s VAR method. Residual Based approach Consider a model, yt = β1 + β2 x2t + β3 x3t + ... + ut (14) where yt , x2t , x3t , ... are all integrated of order N. Now if the residual of this re- gression, ut is stationary then we can say that the variables are cointegrated else there exist no long term relationship between the variables. To test the resid- ual for stationarity we will run Augmented Dickey-Fuller tests on the residuals. Under the Null hypothesis the residual are integrated of order one or more and under alternate hypothesis the residuals are I(0). 4.3.1 Johansen test for Cointegration Johansen test for cointegration presents a better model for testing multiple cointegration among multiple variables. The Residual based approach can only find atmost one cointegration and can be tested for a model with two variables. Even if more than two variables are present in the equation that are cointegrated, the Residual based approach will give only one cointegration. SO we will use Jhoansen VAR based cointegration for testing more than one cointegration. Suppose that a set of g variables are under consideration that are I(1) and which are thought to be cointegrated. A VAR with k lags containing these variables could be set up. yt = β1 yt−1 + β2 yt−2 + · · · + βk yt−k + ut (15) g×1 g×g g×1 g×g g×1 g×g g×1 g×1 EDHEC Business School 18
  • 19. 4 METHODOLOGY In order to use the Johansen test, the VAR above should be turned into a vector error correction model of form, ∆yt = Πyt−k + ℘1 ∆yt−1 + ℘2 ∆yt−2 + · · · + ℘k−1 ∆yt−(k−1) + ut (16) where, Π = (Σk βi ) − Ig and ℘i = (Σi βj ) − Ig i=1 j=1 The Johansen’s test centers around testing the Π matrix which is the matrix that represents the long term cointegration between the variables. The test for number of cointegration is calculated by looking at the rank of the Π matrix through its eigenvalues. The rank of the matrix is equal to number of roots (eigenvalues) λi of the matrix that are different from zero. The roots should be less than 1 in absolute value and positive. If the variables are not cointegrated the rank of the matrix will not be significantly different from zero i.e. λi ≈ 0. There are two test statistics for Johansen test λtrace r and λmax g ˇ λtrace (r) = −T i=r+1 ln(1 − λi ) and, ˇ λmax (r, r + 1) = −T ln(1 − λr+1 ) λtrace is a test statistic for joint test where the null hypothesis is that the number of cointegration vector is less than or equal to r against an alternative that there are more than r. λmax conducts another separate test on eigenvalues and has null hypothesis that the number of cointegrating vector is r against r+1. 4.4 Impulse Response Once we have determined whether the variables have long term relationship or not we can form a multivariate VAR model for the variables. A multivariate VAR model between g variables is a model where the current value of a variable depend on differnt combinations of the previous k values of all the variables and error terms. A general representation of the model can be: yBSEt = α + βBSE yBSE + φIP yIP + γCP I yCP I + δM 1 yM 1 + κSP 500 ySP 500 + u1t (17) where all the coefficients except α are g × k matrices and all variables y are k × 1 matrices. Once we have formed a model like this we can use the model for Impulse re- sponse. A VAR(p) model can be written as a linear fuction of the past innova- tions, that is, rt = µ + at + ψ1 at−1 + ψ2 at−2 + . . . (18) where µ = [φ(1)]−1 φ0 provided that the inverse exists, and the coefficient ma- trices ψi can be obtained by equating the coefficients of B i in the equation (I − φ1 B − . . . − φP B P )(I + ψ1 B + ψ2 B 2 + . . .) = I (19) EDHEC Business School 19
  • 20. 4 METHODOLOGY where I is the Identity martix. This is a moving average representation of rt with the coefficient matrix ψi being the impact of the past innovation at−i on rt . Equivalently, ψi is the effect of at on the future observation rt+i . Therefore, ψi is often referred to as the Impulse Response Function of rt . For our impulse response we will use equation of variables in first differnce form like, k k ∆BSEt = αt + α11 (i)∆BSEt−i + α12 (j)∆M It−j + BSEt (20) i=0 j=1 k k ∆M It = αt + α21 (i)∆M It−i + α22 (j)∆BSEt−j + M It (21) i=0 j=1 Granger’s causality and Block’s F test of a VAR model will suggest which of the variables have statistically significant impacts on the future values of other variables in the system. But F-test results cannot explain the sign of the re- lationship nor how long these effects require to take place. Such information will, however, be given by an examination of the VAR’s impulse responses and variance decompositions. Impulse response is a technique that trace out the responsiveness of the dependent variable in the VAR to shocks of each of the other variables. So for each variable from each equation separately we will apply a unit shock to the error and trace the effects upon the VAR system over time. By using the impulse response technique we can determine how responsive is the BSE stock index to Indian macro indicators and SP500. This will help us determine whether the BSE index is more reactive to domestic news or global news. EDHEC Business School 20
  • 21. 5 RESULTS 5 Results Before we use the time series for VAR analysis or cointegration tests we need to determine whether the series are Stationary or not. If the series are stationary in levels, we can use them directly else we need to use the differenced time series. One way to look for autocorrelation or integrated process is to see the graphs of the various time series used. Section 7.1 shows the graphs of variables we use for our analysis. As we can see from the graphs all of the time series have a trend in long run which points to an integrated process. As a second step we plot the graphs of differenced time series in Section 5.2. We can see that the differenced graphs in Section 7.2 don’t show a long term trend and cross the X-axis frequently. This is usually a property of I(1) processes. So we check the series for autocorrelations at different lag lengths. Section 7.3 shows cor- relograms graph, autocorrelation coefficient, partial autocorrelation coefficient, Q-Stat and p-value for various time series up to 36 lags. As can be seen in the tables the Q-stat for all lags is zero and we can reject the joint null hypothesis that all the autocorrelations up to 36 lags are zero. Table 7.4.1 shows that if we conduct a Unit root test on levels of the series we find that all the 7 series are integrated as we cannot reject the t-stat for unit root at 1% level. But if we conduct the same test on differenced values of the series we find that we can reject the null hypothesis of unit root at 1% significance level for all the series except CPI. This tells us that all the series are I(1) as there first difference series are I(0). As our series are I(1) we will work with index levels of time series to determine if there exist one or more cointegrating relationships between the series. Tables in subsection 7.4.3 are based on residual approach where we run a regression of BSE and various macroeconomic indicators and test the residuals for unit root using Augmented Dickey-Fuller test. As we assume the two series are cointe- grated we conduct the test with no trend and intercept. If the two series are cointegrated then the errors should not have any trend or intercept. We see that we can reject the null hypothesis of unit root at 1% significance for CPI,IP, M1. We can reject the null of unit root for PPI at 5 % and for SP500 and USDINR we can’t reject the null hypothesis of unit root at even 5% level. This points to the fact that BSE has a strong long term relationship with IP, M1 money supply, CPI at 1% level with IP, M1, CPI, PPI at 5% significance level. Also, BSE has no long term relationship with SP500 and USD INR exchange rate. To test for multiple cointegrating relationship we now employ a Johansen VAR based cointegration test. The results of the test are displayed in subsection 7.4.4. The first panel of the test results displays the value of λt race andλm ax of Johansen test with different assumptions about intercept and trend. We can see from this panel that when we consider a functional form of intercept and no Trend we have atleast and atmost three cointegrating relationships. The second panel of the results display the value of information criteria for lag lengths. For most of the models we see that Akalike criteria points to a lag of three and Schwarz criteria points to a lag of one. To estimate the cointegrating model we choose the model with intercept and no trend and run a cointegration test.Test results are shown in Table 2 of subsection 7.4.4. At 5% significance level we can reject the null of atmost two cointegrating factors for λt race and same for λm ax. Now to test which all variables have a long tern relationship we perform a Restricted cointegration with vector error correction model. As we had already EDHEC Business School 21
  • 22. 5 RESULTS seen in our residual based test of cointegration that BSE has no cointegrating relationship with SP500 and USDINR we create a restricted cointegration model where we set coefficients of SP500 and USDINR as zero. The test results are displayed in Table 3 of subsection 7.4.4. In this case as there are two restrictions, the test statistic follow χ2 with two degrees of freedom. We can see that the p-value for the test is 13.33 % which tells us that the restrictions are supported by data at 10% level of significance. So we can conclude that the BSE has a long term relationship with CPI,IP,PPI,M1 money supply but has no long term relationship with SP500 and USDINR exchange rate. One interpretation of this result can be that the Indian stock market, represented here by BSE Sensex, moves more in accordance with domestic factors like Industrial production, M1 money supply, Consumer price index and Producer Price index than with global factors or in other words, as BSE is representation of largest market cap Indian companies we can say that the biggest companies in India are ones that are more dependent on domestic demand rather than exports. This result presents an opportunity for international investors to diversify their portfolio by invest- ing in BSE Sensex as it is decoupled with global markets and macroeconomic factors. We use A bivariate Vector Autoregression (BVAR) technique to analyze the dynamic interaction between real asset prices and macro economy. VAR is preferred method to study Macroeconomy and asset prices where variables en- dogenously effect each other. We begin with a bivariate VAR with no restriction. Asset prices and instru- ments are allowed to respond to each other freely. For paired variables with cointegration relationship, VAR is performed at levels whilst for those that are not cointegrated VAR is performed at first difference. Constant term is ignored with loss of generality. We use the Bivariate Autoregression analysis for both impulse response and Granger’s causality tests. Impulse response results are displayed in subsection 7.4.5. From first graph of impulse response of BSE to USDINR we can see that USDINR has a negative impact on BSE. As impulse response is response of BSE to shocks given to US- DINR we can see that a positive shock or unexpected appreciation INR value w.r.t USD, will have a negative effect on BSE for few lags and will disappear after few lags. If we look at the constituents of BSE Index over time we see that most of the time, some of its constituent are companies that thrive on ex- ports. Some of the biggest Market-Cap in India are companies in service sector like Infosys, TCS, etc that are hugely dependent on services provided to clients from Europe and U.S.. So, an appreciation of INR compared to USD makes these firms costlier for the global clients and in turn reduces the income of these companies. As the firm’s revenue/ profit decreases the value of the stock also decreases that in turn affects the returns of BSE Sensex. Second graph (betwen BSE and SP500) shows that increase in SP500 has a pos- itive effect on BSE as higher returns of SP500 indicate strong global economy which in turn results in higher trade between countries. The positive response of BSE to one unit shock to SP500 indicates a spillover effect of global factors on Indian economy but the response is weak as can be seen from the graph. Moving forward, response of BSE to shocks in M1 money supply, CPI, PPI make economic sense. As for M1 money supply one unit shock means increase in M1 money supply. This increase in money supply allows companies to bor- row more money from banks at lower rates, which they can use for investing EDHEC Business School 22
  • 23. 5 RESULTS in profitable projects and generating larger cash flows. For Inflation indicators one unit shock means increase in inflation. This increase in inflation results in higher costs for the companies that in turn reduces their profit margins and as a result value of stocks. By looking at the graphs we can also see that shocks to Indian macroeconomic indicators creates stronger response by BSE as compared to global factors like SP500 or USDINR. This indicates that BSE Index is driven by companies that depend hugely on domestic demand rather than exports. Response of BSE to shocks to Industrial Production are contradictory to theory. In theory an in- crease in industrial production should result in positive response from BSE but our analysis shows the other way. A possible reason for this response could be that industrial production time series is seasonal as can be seen from the graph. So, there is a possibility of a lead/lag relationship between the two variables. To test for possibility of lead/lag relationship we run a Granger’s causality test between BSE and IP. The result in section 6.4.6 shows that at a lag length of 4 we can reject the Null hypothesis of BSE does not Granger cause IP at 1% significance level. This proves that BSE is a leading indicator of industrial production and there exist a lead/lag relationship between the two indicators. EDHEC Business School 23
  • 24. 6 CONCLUSIONS 6 Conclusions In this paper I tested the relations between Indian stock market, represented by BSE, and domestic and global macro economic factors. The research concludes that the India stock markets are mainly driven by domestic demand and the influence of global macro factors on the stock market is weak. I also tested for Granger causality between BSE and IP and found that BSE is a leading indicator of Industrial production and can help in predicting the industrial climate in India. The research is insightful for investors and professionals who are looking for investment opportunities to diversify their risks. As Indian stock markets are more dependent on domestic factors one can invest in Indian indices and stocks to diversify their risks gained through investing in U.S. and European stocks. The paper opens new doors for research in this field. One can use variance decomposition technique to see how much variance of BSE can be explained my various domestic and global macro factors. Also one can use different global factors like sovereign CDS spreads, T-Bill rates, a composite indicator of global economy for further research on interaction between Indian stock market and global economy.One can also research on how various global macroeconomic news affects India stock markets and for how long the effects persists. EDHEC Business School 24
  • 25. 7 GRAPHS AND TABLES 7 Graphs and Tables 7.1 Graphs of Time series EDHEC Business School 25
  • 26. 7 GRAPHS AND TABLES EDHEC Business School 26
  • 27. 7 GRAPHS AND TABLES EDHEC Business School 27
  • 28. 7 GRAPHS AND TABLES EDHEC Business School 28
  • 29. 7 GRAPHS AND TABLES 7.2 Graphs of Time Series - Differenced EDHEC Business School 29
  • 30. 7 GRAPHS AND TABLES EDHEC Business School 30
  • 31. 7 GRAPHS AND TABLES EDHEC Business School 31
  • 32. 7 GRAPHS AND TABLES EDHEC Business School 32
  • 33. 7 GRAPHS AND TABLES 7.3 Correlograms of Time series BSE EDHEC Business School 33
  • 34. 7 GRAPHS AND TABLES IP EDHEC Business School 34
  • 35. 7 GRAPHS AND TABLES SP500 EDHEC Business School 35
  • 36. 7 GRAPHS AND TABLES USDINR EDHEC Business School 36
  • 37. 7 GRAPHS AND TABLES CPI EDHEC Business School 37
  • 38. 7 GRAPHS AND TABLES PPI EDHEC Business School 38
  • 39. 7 GRAPHS AND TABLES M1 EDHEC Business School 39
  • 40. 7 GRAPHS AND TABLES 7.4 Tables 7.4.1 Table for Unit root test of Time series Variables T-Stat p-value BSE -2.671 24.95 % SP500 -1.315 88.18 % CPI -1.909 64.66 % IP -1.669 8.99 % M1 -2.420 36.79 % PPI -3.353 6.01 % USDINR -2.955 14.69 % 7.4.2 Tables for Unit root test of Differenced time series Variables T-Stat p-value BSE -13.848 0.00 % SP500 -14.832 0.00 % CPI -3.344 1.40 % IP -3.865 0.27 % M1 -3.867 0.26 % PPI -9.656 0.00 % USDINR -13.701 0.00 % 7.4.3 Tables for Residual based test of cointegration Table 1: BSE - CPI t-Statistic Prob.* ADF test statistic -2.622676 0.87% Test critical values: 1% level -2.573818 5% level -1.94204 10% level -1.615891 Table 2: BSE - IP t-Statistic Prob.* ADF test statistic -3.738802 0.02% Test critical values: 1% level -2.574513 5% level -1.942136 10% level -1.615828 EDHEC Business School 40
  • 41. 7 GRAPHS AND TABLES Table 3: BSE - M1 t-Statistic Prob.* ADF test statistic -2.875518 0.41% Test critical values: 1% level -2.573784 5% level -1.942035 10% level -1.615894 Table 4: BSE - PPI t-Statistic Prob.* ADF test statistic -2.399055 1.62% Test critical values: 1% level -2.573784 5% level -1.942035 10% level -1.615894 Table 5: BSE - SP500 t-Statistic Prob.* ADF test statistic -1.427184 14.30% Test critical values: 1% level -2.573784 5% level -1.942035 10% level -1.615894 EDHEC Business School 41
  • 42. 7 GRAPHS AND TABLES Table 6: BSE - USDINR t-Statistic Prob.* ADF test statistic -1.659522 9.17% Test critical values: 1% level -2.573818 5% level -1.94204 10% level -1.615891 EDHEC Business School 42
  • 43. 7 GRAPHS AND TABLES 7.4.4 Johansen cointegration test EDHEC Business School 43
  • 44. 7 GRAPHS AND TABLES Table 2 EDHEC Business School 44
  • 45. 7 GRAPHS AND TABLES Table 3 EDHEC Business School 45
  • 46. 7 GRAPHS AND TABLES 7.4.5 Impulse response tests EDHEC Business School 46
  • 47. 7 GRAPHS AND TABLES EDHEC Business School 47
  • 48. 7 GRAPHS AND TABLES EDHEC Business School 48
  • 49. 7 GRAPHS AND TABLES 7.4.6 Granger causality test between IP and BSE EDHEC Business School 49
  • 50. 8 BIBLIOGRAPHY 8 Bibliography Eugene F. Fama, Inflation, Output and Money , Journal of Business, 1982 Eugene F. Fama, Stock Returns, Real activity and Money, The American Eco- nomic Review, 1981 Eugene F. Fama, Stock Returns, Expected Returns and Real activity, Journal of Finance, 1990 Pal and Mittal, Impact of macroeconomic indicators in Indian capital markets, Journal of Risk Finance, 2011 Shahid Ahmed, Aggregate Economic Variables and Stock Markets in India, In- ternational Research Journal of Finance and Economics, 2008 Sahu and Dhiman, Correlation and Causality between Stock Market and Macro Economic Variables in India: An Empirical Study, 2010 International Confer- ence on E-Business and Economics, 2011 Mohammad Bayezid Ali, Impact of Micro Variables on Emerging Stock Market Return: A case on Dhaka Stock Exchange (DSE), Interdisciplinary Journal of Research in Business, 2011 Napphon Tangjitprom, Macroeconomic Factors of Emerging Stock Market: The evidence from Thailand, International Journal of Finance and Research, 2012 Sayed Mehdi Hosseini, The Role of Macroeconomic Variables on Stock Market Index in China and India, International Journal of Economics and Finance, 2011 John Y. Campbell, Pitfalls and Opportunities: What Macroeconomists should know about Unit Roots, NBER Working Papers, 1991 Hacker and Hatemi, The properties of Procedures Dealing with Uncertainity about Intercept and Deterministic Trend in Unit Root Testing, CESIS Elec- tronic Working Papers, 2010 Elder and Kennedy, Testing for Unit Roots: What should Students be Taught Nasseh and Strauss, Stock Prices and domestic and international macroeco- nomic activity: a cointegration approach, The Quarterly Review of Economics and Finance, 2000 Engle and Granger, Co-Integration and Error Correction: Representation, Es- timation and Testing, Econometrica, 1987 Eugene F. Fama, Stock Returns, Real Activity, Inflation and Money, 1981, American Economic Association Naliniprave Tripathy, Causal Relationship between Macro-Economic Indicators and Stock Market in India, Asian Journal of Finance and Accounting, 2011 Rogalski and Vinso, Stock Returns, Money Supply and the Direction of Causal- ity, The Journal of Finance, 1977 James et. al, A VARMA Analysis of the Causal Relations Among Stock Re- turns, Real output and Nominal Interest Rates, 1985, The Journal of Finance Bailey and Chung, Risk and return in the Philippine Equity market: A multi- factor exploration, Pacific-Basin Finance Journal, 1996 Nai-Fu Chen, Financial Investment opportunities and the Macroeconomy, The Journal of Finance, 1991 G.B. Wickremasinghe, Macroeconomic forces and stock prices: Some empirical evidence from an emerging stock markets, University of Wollongong, 2006 EDHEC Business School 50
  • 51. 8 BIBLIOGRAPHY Yao, Juo and Loh, On China’s Monetary Policy and Asset Prices, University of Nottingham- China policy Institute, 2011 Bilson et. al, Selecting macroeconomic variables as explanatory factors of emerg- ing stock market returns, Pacific-Basin Finance Journal, 2001 CHen, Roll and Ross, Economic forces and the Stock Markets, The Journal of Business, 1986 William H. Greene, Econometric Analysis, 6th Edition, Pearson International Edition Ruey Tsay, Analysis of Financial Time series Chris Brooks, Introductory Econometrics for Finance, Cambridge Publications EDHEC Business School 51