SlideShare a Scribd company logo
1 of 65
Download to read offline
Introduction
               Statistics - I
               Statistics - II




The Statistics of Web Performance

 Philip Tellis / philip@bluesmoon.info


           ConFoo / 2010-03-12




       ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                              Statistics - I
                              Statistics - II


$ ļ¬nger philip




      Philip Tellis
      philip@bluesmoon.info
      @bluesmoon
      yahoo
      geek




                      ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                          The goal
        Statistics - I
                          Performance Measurement
        Statistics - II




      Introduction




ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                        The goal
                      Statistics - I
                                        Performance Measurement
                      Statistics - II




Accurately measure page performance
    At least, as accurately as possible




              ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                        The goal
                      Statistics - I
                                        Performance Measurement
                      Statistics - II




Accurately measure page performance
    At least, as accurately as possible




              ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                              The goal
                            Statistics - I
                                              Performance Measurement
                            Statistics - II


Be unintrusive




  If you try to measure something accurately, you will change
  something related
                                                               ā€“ Heisenbergā€™s uncertainty principle




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                            The goal
          Statistics - I
                            Performance Measurement
          Statistics - II




And one number to rule them all




  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                             The goal
                           Statistics - I
                                             Performance Measurement
                           Statistics - II


Bandwidth




     Real bandwidth v/s advertised bandwidth
     Bandwidth to your server, not to the ISP
     Bandwidth during normal internet usage
         If the userā€™s always watching movies, youā€™re not winning




                   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                             The goal
                           Statistics - I
                                             Performance Measurement
                           Statistics - II


Bandwidth




     Real bandwidth v/s advertised bandwidth
     Bandwidth to your server, not to the ISP
     Bandwidth during normal internet usage
         If the userā€™s always watching movies, youā€™re not winning




                   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                                    The goal
                                  Statistics - I
                                                    Performance Measurement
                                  Statistics - II


Latency



        How long does it take a byte to get to the user?
              Wired, wireless, mobile, satellite?
              How many hops in between?
              Speed of light is constant
        This is not a battle we will soon win.
              When was the last time you heard latency mentioned in a
              TV ad?
  http://www.stuartcheshire.org/rants/Latency.html




                          ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                                    The goal
                                  Statistics - I
                                                    Performance Measurement
                                  Statistics - II


Latency



        How long does it take a byte to get to the user?
              Wired, wireless, mobile, satellite?
              How many hops in between?
              Speed of light is constant
        This is not a battle we will soon win.
              When was the last time you heard latency mentioned in a
              TV ad?
  http://www.stuartcheshire.org/rants/Latency.html




                          ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                                    The goal
                                  Statistics - I
                                                    Performance Measurement
                                  Statistics - II


Latency



        How long does it take a byte to get to the user?
              Wired, wireless, mobile, satellite?
              How many hops in between?
              Speed of light is constant
        This is not a battle we will soon win.
              When was the last time you heard latency mentioned in a
              TV ad?
  http://www.stuartcheshire.org/rants/Latency.html




                          ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                             The goal
                           Statistics - I
                                             Performance Measurement
                           Statistics - II


User perceived page load time



     Time from ā€œclick on a linkā€ to ā€œspinner stops spinningā€
     This is what users notice
         Depends on how long your page takes to build
         Depends on whatā€™s in your page
         Depends on how long components take to load
         Depends on how long the browser takes to execute and
         render




                   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                             The goal
           Statistics - I
                             Performance Measurement
           Statistics - II




We need to measure real user data




   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                          The goal
                        Statistics - I
                                          Performance Measurement
                        Statistics - II




The statistics apply to any kind of performance data though




                ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
        Statistics - I    Margin of Error
        Statistics - II   Central Tendency




      Statistics - I




ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                         Statistics - I    Margin of Error
                         Statistics - II   Central Tendency


Disclaimer




  I am not a statistician




                 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                       Statistics - I    Margin of Error
                       Statistics - II   Central Tendency


Population



             All possible users of your system




               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                       Statistics - I    Margin of Error
                       Statistics - II   Central Tendency


Sample



         Representative subset of the population




               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                     Statistics - I    Margin of Error
                     Statistics - II   Central Tendency


Bad sample



                   Sometimes itā€™s not




             ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                                  Statistics - I    Margin of Error
                                  Statistics - II   Central Tendency


How to randomize?




        Pick 10% of users at random and always test them

                                                OR

        For each user, decide at random if they should be tested
  http://tech.bluesmoon.info/2010/01/statistics-of-performance-measurement.html




                          ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                            Statistics - I    Margin of Error
                            Statistics - II   Central Tendency


Select 10% of users - I



     if($sessionid % 10 === 0) {
        // instrument code for measurement
     }

      Once a user enters the measurement bucket, they stay
      there until they log out
      Fixed set of users, so tests may be more consistent
      Error in the sample results in positive feedback




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                           Statistics - I    Margin of Error
                           Statistics - II   Central Tendency


Select 10% of users - II



     if(rand() < 0.1 * getrandmax()) {
        // instrument code for measurement
     }

      For every request, a user has a 10% chance of being
      tested
      Gets rid of positive feedback errors, but sample size !=
      10% of population




                   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                       Statistics - I    Margin of Error
                       Statistics - II   Central Tendency


How big a sample is representative?




                      Select n such that
                          Ļƒ
                     1.96 āˆšn ā‰¤ 5%Āµ




               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                          Statistics - I    Margin of Error
                          Statistics - II   Central Tendency


Standard Deviation

     Standard deviation tells you the spread of the curve
     The narrower the curve, the more conļ¬dent you can be




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                     Statistics - I    Margin of Error
                     Statistics - II   Central Tendency


MoE at 95% conļ¬dence




                                 Ļƒ
                           Ā±1.96 āˆšn




             ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                          Statistics - I    Margin of Error
                          Statistics - II   Central Tendency


MoE & Sample size




   There is an inverse square root correlation between sample
                     size and margin of error




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                      Statistics - I    Margin of Error
                      Statistics - II   Central Tendency




But wait... itā€™s not complicated enough.
    We have different types of margins of error
    ...more about that later




              ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                      Statistics - I    Margin of Error
                      Statistics - II   Central Tendency




But wait... itā€™s not complicated enough.
    We have different types of margins of error
    ...more about that later




              ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                      Statistics - I    Margin of Error
                      Statistics - II   Central Tendency




But wait... itā€™s not complicated enough.
    We have different types of margins of error
    ...more about that later




              ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                    Statistics - I    Margin of Error
                    Statistics - II   Central Tendency


Ding dong




            ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                         Statistics - I    Margin of Error
                         Statistics - II   Central Tendency


One number




    Mean (Arithmetic)
        Good for symmetric curves
        Affected by outliers


          Mean(10, 11, 12, 11, 109) = 30




                 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                        Statistics - I    Margin of Error
                        Statistics - II   Central Tendency


One number




    Median
       Middle value measures central tendency well
       Not trivial to pull out of a DB


        Median(10, 11, 12, 11, 109) = 11




                ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                        Statistics - I    Margin of Error
                        Statistics - II   Central Tendency


One number




    Mode
       Not often used
       Multi-modal distributions suggest problems


           Mode(10, 11, 12, 11, 109) = 11




                ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                            Statistics - I    Margin of Error
                            Statistics - II   Central Tendency


Other numbers




     A percentile point in the distribution: 95th , 98.5th or 99th
          Used to ļ¬nd out the worst user experience
          Makes more sense if you ļ¬lter data ļ¬rst


            P95th (10, 11, 12, 11, 109) = 12




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                         Statistics - I    Margin of Error
                         Statistics - II   Central Tendency


Other means




    Geometric mean
       Good if your data is exponential in nature
       (with the tail on the right)


       GMean(10, 11, 12, 11, 109) = 16.68




                 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                               Statistics - I    Margin of Error
                               Statistics - II   Central Tendency


Wait... how did I get that?




            N
                Ī N xi ā€” could lead to overļ¬‚ow
                 i=1

            Ī£N loge (xi )
             i=1
                 N
        e                   ā€” computationally simpler




                       ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                               Statistics - I    Margin of Error
                               Statistics - II   Central Tendency


Wait... how did I get that?




            N
                Ī N xi ā€” could lead to overļ¬‚ow
                 i=1

            Ī£N loge (xi )
             i=1
                 N
        e                   ā€” computationally simpler




                       ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                               Statistics - I    Margin of Error
                               Statistics - II   Central Tendency


Wait... how did I get that?




            N
                Ī N xi ā€” could lead to overļ¬‚ow
                 i=1

            Ī£N loge (xi )
             i=1
                 N
        e                   ā€” computationally simpler




                       ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                               Statistics - I    Margin of Error
                               Statistics - II   Central Tendency


Wait... how did I get that?




            N
                Ī N xi ā€” could lead to overļ¬‚ow
                 i=1

            Ī£N loge (xi )
             i=1
                 N
        e                   ā€” computationally simpler




                       ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                          Statistics - I    Margin of Error
                          Statistics - II   Central Tendency


Other means




   And there is also the Harmonic mean, but forget about that




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                            Statistics - I    Margin of Error
                            Statistics - II   Central Tendency


...though consequently



  We have other margins of error
     Geometric margin of error
          Uses geometric standard deviation
      Median margin of error
          Uses ranges of actual values from data set
      Stick to the arithmetic MoE
      ā€“ simpler to calculate, simpler to read and not incorrect




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction      Random Sampling
                            Statistics - I    Margin of Error
                            Statistics - II   Central Tendency


...though consequently



  We have other margins of error
     Geometric margin of error
          Uses geometric standard deviation
      Median margin of error
          Uses ranges of actual values from data set
      Stick to the arithmetic MoE
      ā€“ simpler to calculate, simpler to read and not incorrect




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                          Filtering
        Statistics - I
                          The Log-Normal distribution
        Statistics - II




      Statistics - II




ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                     Filtering
                   Statistics - I
                                     The Log-Normal distribution
                   Statistics - II


Outliers




                                             Out of range data points
                                             Nothing you can ļ¬x here
                                             Thereā€™s even a book about
                                             them




           ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                     Filtering
                   Statistics - I
                                     The Log-Normal distribution
                   Statistics - II


Outliers




                                             Out of range data points
                                             Nothing you can ļ¬x here
                                             Thereā€™s even a book about
                                             them




           ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                     Filtering
                   Statistics - I
                                     The Log-Normal distribution
                   Statistics - II


Outliers




                                             Out of range data points
                                             Nothing you can ļ¬x here
                                             Thereā€™s even a book about
                                             them




           ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                     Filtering
                   Statistics - I
                                     The Log-Normal distribution
                   Statistics - II


Outliers




                                             Out of range data points
                                             Nothing you can ļ¬x here
                                             Thereā€™s even a book about
                                             them




           ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                             Filtering
                           Statistics - I
                                             The Log-Normal distribution
                           Statistics - II


DNS problems can cause outliers




     2 or 3 DNS servers for an ISP
     30 second timeout if ļ¬rst fails
     ... 30 second increase in page load time
     Maybe measure both and ļ¬x what you can
     http://nms.lcs.mit.edu/papers/dns-ton2002.pdf




                   ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                         Filtering
                       Statistics - I
                                         The Log-Normal distribution
                       Statistics - II


Band-pass ļ¬ltering




               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                            Filtering
                          Statistics - I
                                            The Log-Normal distribution
                          Statistics - II


Band-pass ļ¬ltering




     Strip everything outside a reasonable range
         Bandwidth range: 4kbps - 4Gbps
         Page load time: 50ms - 120s
     You may need to relook at the ranges all the time




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                         Filtering
                       Statistics - I
                                         The Log-Normal distribution
                       Statistics - II


IQR ļ¬ltering




               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                           Filtering
                         Statistics - I
                                           The Log-Normal distribution
                         Statistics - II


IQR ļ¬ltering




           Here, we derive the range from the data




                 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                           Filtering
         Statistics - I
                           The Log-Normal distribution
         Statistics - II




Letā€™s look at some real charts




 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                          Filtering
                        Statistics - I
                                          The Log-Normal distribution
                        Statistics - II


Bandwidth distribution for web devs




                          x-axis is linear


                ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                          Filtering
                        Statistics - I
                                          The Log-Normal distribution
                        Statistics - II


Now letā€™s use log(kbps) instead of kbps




                     x-axis is exponential


                ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                            Filtering
                          Statistics - I
                                            The Log-Normal distribution
                          Statistics - II


Exponential == Geometric




     Categories/Buckets grow exponentially
     Data is related geometrically
     Use the geometric mean and geometric margin of error
                           gmean
         Error _range =              /gmoe , gmean āˆ— gmoe
     Non-linear ranges are hard for humans to grok




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                            Filtering
                          Statistics - I
                                            The Log-Normal distribution
                          Statistics - II


Exponential == Geometric




     Categories/Buckets grow exponentially
     Data is related geometrically
     Use the geometric mean and geometric margin of error
                           gmean
         Error _range =              /gmoe , gmean āˆ— gmoe
     Non-linear ranges are hard for humans to grok




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                            Filtering
                          Statistics - I
                                            The Log-Normal distribution
                          Statistics - II


Exponential == Geometric




     Categories/Buckets grow exponentially
     Data is related geometrically
     Use the geometric mean and geometric margin of error
                           gmean
         Error _range =              /gmoe , gmean āˆ— gmoe
     Non-linear ranges are hard for humans to grok




                  ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
        Statistics - I
        Statistics - II




                  So...




ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                                       Statistics - I
                                       Statistics - II


Further reading

     Web Performance - Not a Simple Number
     http://www.netforecast.com/Articles/BCR+C25+Web+Performance+-+Not+A+Simple+Number.pdf

     Revisiting statistics for web performance (introduction to
     Log-Normal)
     http://home.pacbell.net/ciemo/statistics/WhatDoYouMean.pdf

     Random Sampling
     http://tech.bluesmoon.info/2010/01/statistics-of-performance-measurement.html

     Khan Academyā€™s tutorials on statistics
     http://khanacademy.com/

     Learning about Statistical Learning
     http://measuringmeasures.blogspot.com/2010/01/learning-about-statistical-learning.html

     Wikipedia articles on Random Sampling, Central Tendency,
     Standard Error, Confounding, Means and IQR

                               ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                         Statistics - I
                         Statistics - II


Summary



    Choose a reasonable sample size and sampling factor
    Tune sample size for minimal margin of error
    Decide based on your data whether to use mode, median
    or one of the means
    Figure out whether your data is Normal, Log-Normal or
    something else
    Filter out anomalous outliers




                 ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                             Statistics - I
                             Statistics - II


contact me




     Philip Tellis
     philip@bluesmoon.info
     bluesmoon.info
     @bluesmoon




                     ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                            Statistics - I
                            Statistics - II


Photo credits




     http://www.ļ¬‚ickr.com/photos/leoffreitas/332360959/ by leoffreitas
     http://www.ļ¬‚ickr.com/photos/cobalt/56500295/ by cobalt123
     http://www.ļ¬‚ickr.com/photos/sophistechate/4264466015/ by Lisa
     Brewster
     http://www.ļ¬‚ickr.com/photos/nchoz/243216008/ by nchoz




                    ConFoo / 2010-03-12       The Statistics of Web Performance
Introduction
                             Statistics - I
                             Statistics - II


List of ļ¬gures




      http://en.wikipedia.org/wiki/File:Standard_deviation_diagram.svg
      http://en.wikipedia.org/wiki/File:Normal_Distribution_PDF.svg
      http://en.wikipedia.org/wiki/File:KilroySchematic.svg
      http://en.wikipedia.org/wiki/File:Boxplot_vs_PDF.png




                     ConFoo / 2010-03-12       The Statistics of Web Performance

More Related Content

Similar to The Statistics of Web Performance

Sunz2012 2011-2012 bi trends
Sunz2012   2011-2012 bi trendsSunz2012   2011-2012 bi trends
Sunz2012 2011-2012 bi trendsOptimalBI Limited
Ā 
Meaure Marketing Online - IABC Ottawa
Meaure Marketing Online - IABC OttawaMeaure Marketing Online - IABC Ottawa
Meaure Marketing Online - IABC OttawaPublicInsite
Ā 
Mobile Analytics
Mobile AnalyticsMobile Analytics
Mobile Analyticstchenard
Ā 
C 04-internet of things - horizon watch trend report (client version) 28jan2015
C 04-internet of things - horizon watch trend report (client version) 28jan2015C 04-internet of things - horizon watch trend report (client version) 28jan2015
C 04-internet of things - horizon watch trend report (client version) 28jan2015Diane Shimmon
Ā 
Attobahn_Reduced_Angel_070915
Attobahn_Reduced_Angel_070915Attobahn_Reduced_Angel_070915
Attobahn_Reduced_Angel_070915Darryl Gray
Ā 
Innovate 2013 session 1243 mobile testing.v3
Innovate 2013   session 1243 mobile testing.v3Innovate 2013   session 1243 mobile testing.v3
Innovate 2013 session 1243 mobile testing.v3Leigh Williamson
Ā 
MeasureWorks eFinancials - Best practices for a successfull mobile experienc...
MeasureWorks eFinancials  - Best practices for a successfull mobile experienc...MeasureWorks eFinancials  - Best practices for a successfull mobile experienc...
MeasureWorks eFinancials - Best practices for a successfull mobile experienc...MeasureWorks
Ā 
IOT - The 3rd Internet Tsunami is Here
IOT - The 3rd Internet Tsunami is HereIOT - The 3rd Internet Tsunami is Here
IOT - The 3rd Internet Tsunami is HereDr. Mazlan Abbas
Ā 
Cisco Video Data Explosion
Cisco Video Data ExplosionCisco Video Data Explosion
Cisco Video Data Explosionmenkento
Ā 
Nosql Now 2015
Nosql Now 2015Nosql Now 2015
Nosql Now 2015kaiyzen
Ā 
Wireless Network Optimization (2010)
Wireless Network Optimization (2010)Wireless Network Optimization (2010)
Wireless Network Optimization (2010)Marc Jadoul
Ā 
Forrester - Business Intelligence
Forrester - Business IntelligenceForrester - Business Intelligence
Forrester - Business IntelligenceNone
Ā 
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010telcobiaas
Ā 
Forrester wave business intelligence platforms
Forrester wave business intelligence platformsForrester wave business intelligence platforms
Forrester wave business intelligence platformsdivjeev
Ā 
G 2 Industry Analysis
G 2 Industry AnalysisG 2 Industry Analysis
G 2 Industry AnalysisRAJEEV RANJAN
Ā 
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...Computaris
Ā 
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...Bitbar
Ā 
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesData Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesMultiscope
Ā 
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...gogo6
Ā 

Similar to The Statistics of Web Performance (20)

Sunz2012 2011-2012 bi trends
Sunz2012   2011-2012 bi trendsSunz2012   2011-2012 bi trends
Sunz2012 2011-2012 bi trends
Ā 
Meaure Marketing Online - IABC Ottawa
Meaure Marketing Online - IABC OttawaMeaure Marketing Online - IABC Ottawa
Meaure Marketing Online - IABC Ottawa
Ā 
Mobile Analytics
Mobile AnalyticsMobile Analytics
Mobile Analytics
Ā 
C 04-internet of things - horizon watch trend report (client version) 28jan2015
C 04-internet of things - horizon watch trend report (client version) 28jan2015C 04-internet of things - horizon watch trend report (client version) 28jan2015
C 04-internet of things - horizon watch trend report (client version) 28jan2015
Ā 
Attobahn_Reduced_Angel_070915
Attobahn_Reduced_Angel_070915Attobahn_Reduced_Angel_070915
Attobahn_Reduced_Angel_070915
Ā 
Innovate 2013 session 1243 mobile testing.v3
Innovate 2013   session 1243 mobile testing.v3Innovate 2013   session 1243 mobile testing.v3
Innovate 2013 session 1243 mobile testing.v3
Ā 
Query at Speed of Thought
Query at Speed of ThoughtQuery at Speed of Thought
Query at Speed of Thought
Ā 
MeasureWorks eFinancials - Best practices for a successfull mobile experienc...
MeasureWorks eFinancials  - Best practices for a successfull mobile experienc...MeasureWorks eFinancials  - Best practices for a successfull mobile experienc...
MeasureWorks eFinancials - Best practices for a successfull mobile experienc...
Ā 
IOT - The 3rd Internet Tsunami is Here
IOT - The 3rd Internet Tsunami is HereIOT - The 3rd Internet Tsunami is Here
IOT - The 3rd Internet Tsunami is Here
Ā 
Cisco Video Data Explosion
Cisco Video Data ExplosionCisco Video Data Explosion
Cisco Video Data Explosion
Ā 
Nosql Now 2015
Nosql Now 2015Nosql Now 2015
Nosql Now 2015
Ā 
Wireless Network Optimization (2010)
Wireless Network Optimization (2010)Wireless Network Optimization (2010)
Wireless Network Optimization (2010)
Ā 
Forrester - Business Intelligence
Forrester - Business IntelligenceForrester - Business Intelligence
Forrester - Business Intelligence
Ā 
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010
The Forrester Wave: Enterprise Business Intelligence Platforms, Q4 2010
Ā 
Forrester wave business intelligence platforms
Forrester wave business intelligence platformsForrester wave business intelligence platforms
Forrester wave business intelligence platforms
Ā 
G 2 Industry Analysis
G 2 Industry AnalysisG 2 Industry Analysis
G 2 Industry Analysis
Ā 
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...
Sandvine Webinar ā€“ Making Cents of Internet Phenomena Through Network Busines...
Ā 
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...
The Best of Both Worlds - Combining Performance and Functional Mobile App Tes...
Ā 
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesData Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Ā 
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...
The IoT Food Chain ā€“ Picking the Right Dining Partner is Important with Dean ...
Ā 

More from Philip Tellis

Improving D3 Performance with CANVAS and other Hacks
Improving D3 Performance with CANVAS and other HacksImproving D3 Performance with CANVAS and other Hacks
Improving D3 Performance with CANVAS and other HacksPhilip Tellis
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonPhilip Tellis
Ā 
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou Furieux
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou FurieuxFrontend Performance: De dƩbutant Ơ Expert Ơ Fou Furieux
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou FurieuxPhilip Tellis
Ā 
Frontend Performance: Expert to Crazy Person
Frontend Performance: Expert to Crazy PersonFrontend Performance: Expert to Crazy Person
Frontend Performance: Expert to Crazy PersonPhilip Tellis
Ā 
Beyond Page Level Metrics
Beyond Page Level MetricsBeyond Page Level Metrics
Beyond Page Level MetricsPhilip Tellis
Ā 
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...Philip Tellis
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonPhilip Tellis
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonPhilip Tellis
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonPhilip Tellis
Ā 
mmm... beacons
mmm... beaconsmmm... beacons
mmm... beaconsPhilip Tellis
Ā 
RUM Distillation 101 -- Part I
RUM Distillation 101 -- Part IRUM Distillation 101 -- Part I
RUM Distillation 101 -- Part IPhilip Tellis
Ā 
Improving 3rd Party Script Performance With IFrames
Improving 3rd Party Script Performance With IFramesImproving 3rd Party Script Performance With IFrames
Improving 3rd Party Script Performance With IFramesPhilip Tellis
Ā 
Extending Boomerang
Extending BoomerangExtending Boomerang
Extending BoomerangPhilip Tellis
Ā 
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"Philip Tellis
Ā 
Abusing JavaScript to Measure Web Performance
Abusing JavaScript to Measure Web PerformanceAbusing JavaScript to Measure Web Performance
Abusing JavaScript to Measure Web PerformancePhilip Tellis
Ā 
Rum for Breakfast
Rum for BreakfastRum for Breakfast
Rum for BreakfastPhilip Tellis
Ā 
Analysing network characteristics with JavaScript
Analysing network characteristics with JavaScriptAnalysing network characteristics with JavaScript
Analysing network characteristics with JavaScriptPhilip Tellis
Ā 
A Node.JS bag of goodies for analyzing Web Traffic
A Node.JS bag of goodies for analyzing Web TrafficA Node.JS bag of goodies for analyzing Web Traffic
A Node.JS bag of goodies for analyzing Web TrafficPhilip Tellis
Ā 
Input sanitization
Input sanitizationInput sanitization
Input sanitizationPhilip Tellis
Ā 
Messing with JavaScript and the DOM to measure network characteristics
Messing with JavaScript and the DOM to measure network characteristicsMessing with JavaScript and the DOM to measure network characteristics
Messing with JavaScript and the DOM to measure network characteristicsPhilip Tellis
Ā 

More from Philip Tellis (20)

Improving D3 Performance with CANVAS and other Hacks
Improving D3 Performance with CANVAS and other HacksImproving D3 Performance with CANVAS and other Hacks
Improving D3 Performance with CANVAS and other Hacks
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy Person
Ā 
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou Furieux
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou FurieuxFrontend Performance: De dƩbutant Ơ Expert Ơ Fou Furieux
Frontend Performance: De dƩbutant Ơ Expert Ơ Fou Furieux
Ā 
Frontend Performance: Expert to Crazy Person
Frontend Performance: Expert to Crazy PersonFrontend Performance: Expert to Crazy Person
Frontend Performance: Expert to Crazy Person
Ā 
Beyond Page Level Metrics
Beyond Page Level MetricsBeyond Page Level Metrics
Beyond Page Level Metrics
Ā 
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...
Frontend Performance: Beginner to Expert to Crazy Person (San Diego Web Perf ...
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy Person
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy Person
Ā 
Frontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy PersonFrontend Performance: Beginner to Expert to Crazy Person
Frontend Performance: Beginner to Expert to Crazy Person
Ā 
mmm... beacons
mmm... beaconsmmm... beacons
mmm... beacons
Ā 
RUM Distillation 101 -- Part I
RUM Distillation 101 -- Part IRUM Distillation 101 -- Part I
RUM Distillation 101 -- Part I
Ā 
Improving 3rd Party Script Performance With IFrames
Improving 3rd Party Script Performance With IFramesImproving 3rd Party Script Performance With IFrames
Improving 3rd Party Script Performance With IFrames
Ā 
Extending Boomerang
Extending BoomerangExtending Boomerang
Extending Boomerang
Ā 
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"
Abusing JavaScript to measure Web Performance, or, "how does boomerang work?"
Ā 
Abusing JavaScript to Measure Web Performance
Abusing JavaScript to Measure Web PerformanceAbusing JavaScript to Measure Web Performance
Abusing JavaScript to Measure Web Performance
Ā 
Rum for Breakfast
Rum for BreakfastRum for Breakfast
Rum for Breakfast
Ā 
Analysing network characteristics with JavaScript
Analysing network characteristics with JavaScriptAnalysing network characteristics with JavaScript
Analysing network characteristics with JavaScript
Ā 
A Node.JS bag of goodies for analyzing Web Traffic
A Node.JS bag of goodies for analyzing Web TrafficA Node.JS bag of goodies for analyzing Web Traffic
A Node.JS bag of goodies for analyzing Web Traffic
Ā 
Input sanitization
Input sanitizationInput sanitization
Input sanitization
Ā 
Messing with JavaScript and the DOM to measure network characteristics
Messing with JavaScript and the DOM to measure network characteristicsMessing with JavaScript and the DOM to measure network characteristics
Messing with JavaScript and the DOM to measure network characteristics
Ā 

Recently uploaded

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationRadu Cotescu
Ā 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
Ā 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
Ā 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
Ā 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
Ā 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
Ā 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜RTylerCroy
Ā 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
Ā 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
Ā 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
Ā 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
Ā 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
Ā 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
Ā 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
Ā 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
Ā 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
Ā 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
Ā 

Recently uploaded (20)

Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organization
Ā 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
Ā 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Ā 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
Ā 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
Ā 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
Ā 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜
Ā 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
Ā 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
Ā 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
Ā 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
Ā 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
Ā 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
Ā 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
Ā 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Ā 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Ā 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
Ā 

The Statistics of Web Performance

  • 1. Introduction Statistics - I Statistics - II The Statistics of Web Performance Philip Tellis / philip@bluesmoon.info ConFoo / 2010-03-12 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 2. Introduction Statistics - I Statistics - II $ ļ¬nger philip Philip Tellis philip@bluesmoon.info @bluesmoon yahoo geek ConFoo / 2010-03-12 The Statistics of Web Performance
  • 3. Introduction The goal Statistics - I Performance Measurement Statistics - II Introduction ConFoo / 2010-03-12 The Statistics of Web Performance
  • 4. Introduction The goal Statistics - I Performance Measurement Statistics - II Accurately measure page performance At least, as accurately as possible ConFoo / 2010-03-12 The Statistics of Web Performance
  • 5. Introduction The goal Statistics - I Performance Measurement Statistics - II Accurately measure page performance At least, as accurately as possible ConFoo / 2010-03-12 The Statistics of Web Performance
  • 6. Introduction The goal Statistics - I Performance Measurement Statistics - II Be unintrusive If you try to measure something accurately, you will change something related ā€“ Heisenbergā€™s uncertainty principle ConFoo / 2010-03-12 The Statistics of Web Performance
  • 7. Introduction The goal Statistics - I Performance Measurement Statistics - II And one number to rule them all ConFoo / 2010-03-12 The Statistics of Web Performance
  • 8. Introduction The goal Statistics - I Performance Measurement Statistics - II Bandwidth Real bandwidth v/s advertised bandwidth Bandwidth to your server, not to the ISP Bandwidth during normal internet usage If the userā€™s always watching movies, youā€™re not winning ConFoo / 2010-03-12 The Statistics of Web Performance
  • 9. Introduction The goal Statistics - I Performance Measurement Statistics - II Bandwidth Real bandwidth v/s advertised bandwidth Bandwidth to your server, not to the ISP Bandwidth during normal internet usage If the userā€™s always watching movies, youā€™re not winning ConFoo / 2010-03-12 The Statistics of Web Performance
  • 10. Introduction The goal Statistics - I Performance Measurement Statistics - II Latency How long does it take a byte to get to the user? Wired, wireless, mobile, satellite? How many hops in between? Speed of light is constant This is not a battle we will soon win. When was the last time you heard latency mentioned in a TV ad? http://www.stuartcheshire.org/rants/Latency.html ConFoo / 2010-03-12 The Statistics of Web Performance
  • 11. Introduction The goal Statistics - I Performance Measurement Statistics - II Latency How long does it take a byte to get to the user? Wired, wireless, mobile, satellite? How many hops in between? Speed of light is constant This is not a battle we will soon win. When was the last time you heard latency mentioned in a TV ad? http://www.stuartcheshire.org/rants/Latency.html ConFoo / 2010-03-12 The Statistics of Web Performance
  • 12. Introduction The goal Statistics - I Performance Measurement Statistics - II Latency How long does it take a byte to get to the user? Wired, wireless, mobile, satellite? How many hops in between? Speed of light is constant This is not a battle we will soon win. When was the last time you heard latency mentioned in a TV ad? http://www.stuartcheshire.org/rants/Latency.html ConFoo / 2010-03-12 The Statistics of Web Performance
  • 13. Introduction The goal Statistics - I Performance Measurement Statistics - II User perceived page load time Time from ā€œclick on a linkā€ to ā€œspinner stops spinningā€ This is what users notice Depends on how long your page takes to build Depends on whatā€™s in your page Depends on how long components take to load Depends on how long the browser takes to execute and render ConFoo / 2010-03-12 The Statistics of Web Performance
  • 14. Introduction The goal Statistics - I Performance Measurement Statistics - II We need to measure real user data ConFoo / 2010-03-12 The Statistics of Web Performance
  • 15. Introduction The goal Statistics - I Performance Measurement Statistics - II The statistics apply to any kind of performance data though ConFoo / 2010-03-12 The Statistics of Web Performance
  • 16. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Statistics - I ConFoo / 2010-03-12 The Statistics of Web Performance
  • 17. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Disclaimer I am not a statistician ConFoo / 2010-03-12 The Statistics of Web Performance
  • 18. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Population All possible users of your system ConFoo / 2010-03-12 The Statistics of Web Performance
  • 19. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Sample Representative subset of the population ConFoo / 2010-03-12 The Statistics of Web Performance
  • 20. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Bad sample Sometimes itā€™s not ConFoo / 2010-03-12 The Statistics of Web Performance
  • 21. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency How to randomize? Pick 10% of users at random and always test them OR For each user, decide at random if they should be tested http://tech.bluesmoon.info/2010/01/statistics-of-performance-measurement.html ConFoo / 2010-03-12 The Statistics of Web Performance
  • 22. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Select 10% of users - I if($sessionid % 10 === 0) { // instrument code for measurement } Once a user enters the measurement bucket, they stay there until they log out Fixed set of users, so tests may be more consistent Error in the sample results in positive feedback ConFoo / 2010-03-12 The Statistics of Web Performance
  • 23. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Select 10% of users - II if(rand() < 0.1 * getrandmax()) { // instrument code for measurement } For every request, a user has a 10% chance of being tested Gets rid of positive feedback errors, but sample size != 10% of population ConFoo / 2010-03-12 The Statistics of Web Performance
  • 24. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency How big a sample is representative? Select n such that Ļƒ 1.96 āˆšn ā‰¤ 5%Āµ ConFoo / 2010-03-12 The Statistics of Web Performance
  • 25. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Standard Deviation Standard deviation tells you the spread of the curve The narrower the curve, the more conļ¬dent you can be ConFoo / 2010-03-12 The Statistics of Web Performance
  • 26. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency MoE at 95% conļ¬dence Ļƒ Ā±1.96 āˆšn ConFoo / 2010-03-12 The Statistics of Web Performance
  • 27. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency MoE & Sample size There is an inverse square root correlation between sample size and margin of error ConFoo / 2010-03-12 The Statistics of Web Performance
  • 28. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency But wait... itā€™s not complicated enough. We have different types of margins of error ...more about that later ConFoo / 2010-03-12 The Statistics of Web Performance
  • 29. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency But wait... itā€™s not complicated enough. We have different types of margins of error ...more about that later ConFoo / 2010-03-12 The Statistics of Web Performance
  • 30. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency But wait... itā€™s not complicated enough. We have different types of margins of error ...more about that later ConFoo / 2010-03-12 The Statistics of Web Performance
  • 31. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Ding dong ConFoo / 2010-03-12 The Statistics of Web Performance
  • 32. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency One number Mean (Arithmetic) Good for symmetric curves Affected by outliers Mean(10, 11, 12, 11, 109) = 30 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 33. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency One number Median Middle value measures central tendency well Not trivial to pull out of a DB Median(10, 11, 12, 11, 109) = 11 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 34. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency One number Mode Not often used Multi-modal distributions suggest problems Mode(10, 11, 12, 11, 109) = 11 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 35. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Other numbers A percentile point in the distribution: 95th , 98.5th or 99th Used to ļ¬nd out the worst user experience Makes more sense if you ļ¬lter data ļ¬rst P95th (10, 11, 12, 11, 109) = 12 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 36. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Other means Geometric mean Good if your data is exponential in nature (with the tail on the right) GMean(10, 11, 12, 11, 109) = 16.68 ConFoo / 2010-03-12 The Statistics of Web Performance
  • 37. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Wait... how did I get that? N Ī N xi ā€” could lead to overļ¬‚ow i=1 Ī£N loge (xi ) i=1 N e ā€” computationally simpler ConFoo / 2010-03-12 The Statistics of Web Performance
  • 38. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Wait... how did I get that? N Ī N xi ā€” could lead to overļ¬‚ow i=1 Ī£N loge (xi ) i=1 N e ā€” computationally simpler ConFoo / 2010-03-12 The Statistics of Web Performance
  • 39. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Wait... how did I get that? N Ī N xi ā€” could lead to overļ¬‚ow i=1 Ī£N loge (xi ) i=1 N e ā€” computationally simpler ConFoo / 2010-03-12 The Statistics of Web Performance
  • 40. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Wait... how did I get that? N Ī N xi ā€” could lead to overļ¬‚ow i=1 Ī£N loge (xi ) i=1 N e ā€” computationally simpler ConFoo / 2010-03-12 The Statistics of Web Performance
  • 41. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency Other means And there is also the Harmonic mean, but forget about that ConFoo / 2010-03-12 The Statistics of Web Performance
  • 42. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency ...though consequently We have other margins of error Geometric margin of error Uses geometric standard deviation Median margin of error Uses ranges of actual values from data set Stick to the arithmetic MoE ā€“ simpler to calculate, simpler to read and not incorrect ConFoo / 2010-03-12 The Statistics of Web Performance
  • 43. Introduction Random Sampling Statistics - I Margin of Error Statistics - II Central Tendency ...though consequently We have other margins of error Geometric margin of error Uses geometric standard deviation Median margin of error Uses ranges of actual values from data set Stick to the arithmetic MoE ā€“ simpler to calculate, simpler to read and not incorrect ConFoo / 2010-03-12 The Statistics of Web Performance
  • 44. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Statistics - II ConFoo / 2010-03-12 The Statistics of Web Performance
  • 45. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Outliers Out of range data points Nothing you can ļ¬x here Thereā€™s even a book about them ConFoo / 2010-03-12 The Statistics of Web Performance
  • 46. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Outliers Out of range data points Nothing you can ļ¬x here Thereā€™s even a book about them ConFoo / 2010-03-12 The Statistics of Web Performance
  • 47. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Outliers Out of range data points Nothing you can ļ¬x here Thereā€™s even a book about them ConFoo / 2010-03-12 The Statistics of Web Performance
  • 48. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Outliers Out of range data points Nothing you can ļ¬x here Thereā€™s even a book about them ConFoo / 2010-03-12 The Statistics of Web Performance
  • 49. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II DNS problems can cause outliers 2 or 3 DNS servers for an ISP 30 second timeout if ļ¬rst fails ... 30 second increase in page load time Maybe measure both and ļ¬x what you can http://nms.lcs.mit.edu/papers/dns-ton2002.pdf ConFoo / 2010-03-12 The Statistics of Web Performance
  • 50. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Band-pass ļ¬ltering ConFoo / 2010-03-12 The Statistics of Web Performance
  • 51. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Band-pass ļ¬ltering Strip everything outside a reasonable range Bandwidth range: 4kbps - 4Gbps Page load time: 50ms - 120s You may need to relook at the ranges all the time ConFoo / 2010-03-12 The Statistics of Web Performance
  • 52. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II IQR ļ¬ltering ConFoo / 2010-03-12 The Statistics of Web Performance
  • 53. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II IQR ļ¬ltering Here, we derive the range from the data ConFoo / 2010-03-12 The Statistics of Web Performance
  • 54. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Letā€™s look at some real charts ConFoo / 2010-03-12 The Statistics of Web Performance
  • 55. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Bandwidth distribution for web devs x-axis is linear ConFoo / 2010-03-12 The Statistics of Web Performance
  • 56. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Now letā€™s use log(kbps) instead of kbps x-axis is exponential ConFoo / 2010-03-12 The Statistics of Web Performance
  • 57. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Exponential == Geometric Categories/Buckets grow exponentially Data is related geometrically Use the geometric mean and geometric margin of error gmean Error _range = /gmoe , gmean āˆ— gmoe Non-linear ranges are hard for humans to grok ConFoo / 2010-03-12 The Statistics of Web Performance
  • 58. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Exponential == Geometric Categories/Buckets grow exponentially Data is related geometrically Use the geometric mean and geometric margin of error gmean Error _range = /gmoe , gmean āˆ— gmoe Non-linear ranges are hard for humans to grok ConFoo / 2010-03-12 The Statistics of Web Performance
  • 59. Introduction Filtering Statistics - I The Log-Normal distribution Statistics - II Exponential == Geometric Categories/Buckets grow exponentially Data is related geometrically Use the geometric mean and geometric margin of error gmean Error _range = /gmoe , gmean āˆ— gmoe Non-linear ranges are hard for humans to grok ConFoo / 2010-03-12 The Statistics of Web Performance
  • 60. Introduction Statistics - I Statistics - II So... ConFoo / 2010-03-12 The Statistics of Web Performance
  • 61. Introduction Statistics - I Statistics - II Further reading Web Performance - Not a Simple Number http://www.netforecast.com/Articles/BCR+C25+Web+Performance+-+Not+A+Simple+Number.pdf Revisiting statistics for web performance (introduction to Log-Normal) http://home.pacbell.net/ciemo/statistics/WhatDoYouMean.pdf Random Sampling http://tech.bluesmoon.info/2010/01/statistics-of-performance-measurement.html Khan Academyā€™s tutorials on statistics http://khanacademy.com/ Learning about Statistical Learning http://measuringmeasures.blogspot.com/2010/01/learning-about-statistical-learning.html Wikipedia articles on Random Sampling, Central Tendency, Standard Error, Confounding, Means and IQR ConFoo / 2010-03-12 The Statistics of Web Performance
  • 62. Introduction Statistics - I Statistics - II Summary Choose a reasonable sample size and sampling factor Tune sample size for minimal margin of error Decide based on your data whether to use mode, median or one of the means Figure out whether your data is Normal, Log-Normal or something else Filter out anomalous outliers ConFoo / 2010-03-12 The Statistics of Web Performance
  • 63. Introduction Statistics - I Statistics - II contact me Philip Tellis philip@bluesmoon.info bluesmoon.info @bluesmoon ConFoo / 2010-03-12 The Statistics of Web Performance
  • 64. Introduction Statistics - I Statistics - II Photo credits http://www.ļ¬‚ickr.com/photos/leoffreitas/332360959/ by leoffreitas http://www.ļ¬‚ickr.com/photos/cobalt/56500295/ by cobalt123 http://www.ļ¬‚ickr.com/photos/sophistechate/4264466015/ by Lisa Brewster http://www.ļ¬‚ickr.com/photos/nchoz/243216008/ by nchoz ConFoo / 2010-03-12 The Statistics of Web Performance
  • 65. Introduction Statistics - I Statistics - II List of ļ¬gures http://en.wikipedia.org/wiki/File:Standard_deviation_diagram.svg http://en.wikipedia.org/wiki/File:Normal_Distribution_PDF.svg http://en.wikipedia.org/wiki/File:KilroySchematic.svg http://en.wikipedia.org/wiki/File:Boxplot_vs_PDF.png ConFoo / 2010-03-12 The Statistics of Web Performance