SlideShare a Scribd company logo
1 of 15
Statistik
Teil 6 - Statistisches Testen

       Ulrich Schrader
http://info.ulrich-schrader.de
Statistisches Testen
• Situation
   – 2 Populationen aus denen jeweils eine Stichprobe gezogen
     wird. Ein Merkmal X wird in beiden Stichproben
     beobachtet.
• Frage
   – Unterscheidet sich der Erwartungswert des Merkmals in
     den beiden Populationen?
• 2 Hypothesen
   – quot;Die Erwartungswerte unterscheiden sich nicht in den
     beiden Populationen.quot; - Nullhypothese H0
   – quot;Die Erwartungswerte unterscheiden sich in den beiden
     Populationen.quot; - Alternativhypothese H1
z.B. Therapie A

Population
    A                             Stichprobe
                                       A
  EA(X)

              Frage : E A (X)   E B ( X ) oder E A (X)    EB (X )
                                     H 1 oder H 0

              z.B. Unterscheidet sich das erwartete Ergebnis bei
              Therapie A von dem bei Therapie B?
Population
    B                             Stichprobe
                                       B
  EB(X)
             z.B. Therapie B
Entscheidungsmatrix
                                            Es liegt tatsächlich vor

Entscheidung für        H0 – „kein Unterschied“              H1 – „Unterschied“

        H0               richtige Entscheidung falsch negative Entscheidung
„kein Unterschied“                (1 - )               – „Fehler 2. Art“

                              falsch positive
       H1                                                   richtige Entscheidung
                              Entscheidung
  „Unterschied“                                                      (1 - )
                              – „Fehler 1. Art“

  Ein statistischer Test ist eine Entscheidungsregel, welche die Wahrscheinlichkeit für
  einen Fehler 1. Art kleiner als einen vorgegebenen Wert hält und die
  Wahrscheinlichkeit für einen Fehler 2. Art möglichst gering hält.
  • 1- : Signifikanzniveau
  • : Irrtumswahrscheinlichkeit
  • 1- : Güte/Mächtigkeit des Tests
Vorgehen beim statistischen Testen
              1. Schritt
• Formulierung der Hypothesen
   – Alternativhypothese und Nullhypothese
• Festlegung der noch zulässigen
  Irrtumswahrscheinlichkeit α (Fehler 1. Art)
   – Wahrscheinlichkeit eines Fehlers im Fall der Entscheidung
     für die Alternativhypothese H1)
   – Bestimmt sich aus den möglichen Folgen einer
     Fehlentscheidung
• Auswahl eines geeigneten Tests
      • Fehler 2. Art β möglichst klein bei vorgegebenem Signifikanzniveau
        (1 - α)
        (Möglichst mächtiger Test)
Vorgehen beim statistischen Testen
              2. Schritt
• Annahme (willkürlich)
  – H0 gilt (kein Unterschied)
    (Konservativ: Die neue Therapie macht keinen
    Unterschied)
• Berechnung einer Prüfgröße, deren Verteilung
  bekannt ist, wenn die Annahme H0 erfüllt ist,
  aus den Werten der Stichproben.
Vorgehen beim statistischen Testen
              3. Schritt
• Verwerfen der ursprünglichen (willkürlichen)
  Annahme, H0 soll gelten, wenn der Wert für
  die Prüfgröße gemäß der bekannten
  Verteilung nicht erwartet wird. Dann
  Alternativhypothese H1 annehmen.
• Sonst H0 beibehalten. Konservativer Ansatz.
Statistischer Test
                 Verteilung der Prüfgröße - H0 gilt




                          Werte lassen sich
                        gut durch die Annahme
                            H0 gilt erklären.
             2               1                          2
                          H0 wird beibehalten
  Unerwartete Werte                             Unerwartete Werte
   H0 wird verworfen                            H0 wird verworfen
H1 wird angenommen                              H1 wird angenommen
p-Wert
• Oft als Ergebnis eines statistischen Tests
  angegeben.
• Geringste Irrtumswahrscheinlichkeit , deren
  Festlegung mit den beobachteten
  Stichprobenwerten gerade noch zur
  Verwerfung der Nullhypothese geführt hätte.
Beispiel
    IM Rosen, et al. : Prenatal breastfeeding education and breastfeeding outcomes. MCN. The
         American Journal of Maternal Child Nursing, Vol. 33, No. 5. (008), pp. 315-319.


•   PURPOSE: To examine the impact of various breastfeeding outcomes of three
    cohorts receiving different methods of prenatal breastfeeding education.
    METHODS: Retrospective cohort design with patients attending a breastfeeding
    education class at an Army medical center. Controls were matched for sponsor rank,
    marital status, and smoking status. One hundred ninety-four mothers who expressed
    intent to breastfeed received breastfeeding education as follows: (a) a class that
    used video demonstration and group teaching by a lactation consultant, (b) a new
    mothers' support group with one-on-one teaching prenatally and weekly meetings
    postpartum, taught by a lactation consultant and a pediatrician, and (c) a control
    group educated at prenatal visits only. Descriptive statistics, chi-square, ANOVA,
    unpaired t test, and logistic regression were used to analyze the data.
•   RESULTS: Women who attended prenatal breastfeeding classes had significantly
    increased breastfeeding at 6 months when compared to controls (p = .01). There
    was no significant difference in rates between types of classes offered (p = .45).
•   CLINICAL IMPLICATIONS: Prenatal breastfeeding education can influence the amount
    of time women breastfeed. All providers of prenatal care should consider offering
    such classes in order to improve breastfeeding rates.
Tests mit unabhängigen/paarigen
               Stichproben
• Unabhängige Stichproben
   – Beobachtungseinheiten der einen Stichprobe haben
     keinen Beziehung zu Beobachtungseinheiten der anderen
     Stichprobe
   – Indiz: Stichprobenanzahlen unterschiedlich
• Paarige Stichproben
   – Jede Beobachtungseinheit der einen Stichprobe hat genau
     eine korrespondierende Beobachtungseinheit in der
     anderen Stichprobe.
   – Typisch: Vorher/Nachher
     Mutter in der einen, Kind in der anderen Stichprobe
     Zwillinge
   – Notwendig: Stichprobenanzahlen gleich
Paarige Stichproben



Stichprobe A        Stichprobe B
Übersicht über wichtige statistische
               Testverfahren
Merkmal             Prüfgröße        Unabhängige SP         Paarige SP
Quantitativ,        t-verteilt       Student's t-Test für   Student's t-Test für
normalverteilt,                      unabh. SP              paarige SP
ähnl. Streuung
Quantitativ,        standard-        Wilcoxon Rang-Test     Wilcoxon Rang-Test
beliebig verteilt   normalverteilt   für unabh. SP          für paarige SP
Ordinal             standard-        Wilcoxon Rang-Test     Wilcoxon Rang-Test
                    normalverteilt   für unabh. SP          für paarige SP
Nominal             χ2-verteilt      Chi-Quadrat-           Vorzeichentest
(dichotom,                           Vierfeldertest
zweiwertig)
Häufigkeiten
Beispiel
     MY Chang, CH Chen, KF Huang: Effects of music therapy on psychological health of women
    during pregnancy. Journal of clinical nursing, Vol. 17, No. 19. (October 2008), pp. 2580-2587.

•    AIMS AND OBJECTIVES: The purpose of this study was to examine the effects of music therapy on
     stress, anxiety and depression in Taiwanese pregnant women.
•    BACKGROUND: The value of music therapy is slowly being realized by nurses in various clinical
     areas, including obstetrics. Previous studies have demonstrated a high prevalence of psychological
     stress during pregnancy. [...]
•    DESIGN: A randomized experimental study design was developed and implemented.
•    METHODS: Two hundred and thirty-six pregnant women were randomly assigned to music
     therapy (n = 116) and control (n = 120) groups. The music therapy group received two weeks of
     music intervention. The control group received only general prenatal care. Psychological health was
     assessed using three self-report measures: Perceived Stress Scale (PSS), State Scale of the State-
     Trait Anxiety Inventory (S-STAI) and Edinburgh Postnatal Depression Scale (EPDS). RESULTS: In a
     paired t-test, the music therapy group showed significant decrease in PSS, S-STAI and EPDS after
     two weeks. The control group only showed a significant decrease in PSS after two weeks. This
     decrease was not as substantial as in the experimental group. [...]
•    CONCLUSIONS: This controlled trial provides preliminary evidence that two-week music therapy
     during pregnancy provides quantifiable psychological benefits.
•    RELEVANCE TO CLINICAL PRACTICE: The findings can be used to encourage pregnant women to use
     this cost-effective method of music in their daily life to reduce their stress, anxiety and depression.
     Further research is needed to test the long-term benefits.
Beispiel
  CL Dennis, et al.: Effect of peer support on prevention of postnatal depression among high risk
    women: multisite randomised controlled trial. BMJ (Clinical research ed.), Vol. 338 (2009)

OBJECTIVE: To evaluate the effectiveness of telephone based peer support in the prevention of postnatal
depression.
DESIGN: Multisite randomised controlled trial. SETTING: Seven health regions across Ontario, Canada.
PARTICIPANTS: 701 women in the first two weeks postpartum identified as high risk for postnatal depression
with the Edinburgh postnatal depression scale and randomised with an internet based randomisation service. I
NTERVENTION: Proactive individualised telephone based peer (mother to mother) support, initiated within 48-
72 hours of randomisation, provided by a volunteer recruited from the community who had previously
experienced and recovered from self reported postnatal depression and attended a four hour training session.
MAIN OUTCOME MEASURES: Edinburgh postnatal depression scale, structured clinical interview-depression,
state-trait anxiety inventory, UCLA loneliness scale, and use of health services.
RESULTS: After web based screening of 21 470 women, 701 (72%) eligible mothers were recruited. A blinded
research nurse followed up more than 85% by telephone, including 613 at 12 weeks and 600 at 24 weeks
postpartum. At 12 weeks, 14% (40/297) of women in the intervention group and 25% (78/315) in the control
group had an Edinburgh postnatal depression scale score >12 (chi(2)=12.5, P<0.001; number need to treat 8.8,
95% confidence interval 5.9 to 19.6; relative risk reduction 0.46, 95% confidence interval 0.24 to 0.62). [...] Of
the 221 women in the intervention group who received and evaluated their experience of peer support, over
80% were satisfied and would recommend this support to a friend.
CONCLUSION: Telephone based peer support can be effective in preventing postnatal depression among
women at high risk.

More Related Content

Viewers also liked

Types of listening
Types of listeningTypes of listening
Types of listening
2461998
 
Camtasia getting started guide
Camtasia getting started guideCamtasia getting started guide
Camtasia getting started guide
Djibril Mbaye
 
AFWA_Monarch_Report_Oct_23_2015
AFWA_Monarch_Report_Oct_23_2015AFWA_Monarch_Report_Oct_23_2015
AFWA_Monarch_Report_Oct_23_2015
Jonathan Mawdsley
 
Carlos Castaneda - Segundo círculo do poder
Carlos Castaneda -  Segundo círculo do poderCarlos Castaneda -  Segundo círculo do poder
Carlos Castaneda - Segundo círculo do poder
Indioê Alan Autovicz
 

Viewers also liked (17)

Sheep Cross Breeding and Reproductive Management Dr Talaat Refaat
Sheep Cross Breeding and Reproductive Management Dr Talaat RefaatSheep Cross Breeding and Reproductive Management Dr Talaat Refaat
Sheep Cross Breeding and Reproductive Management Dr Talaat Refaat
 
Presentacion Herramientas Gerenciales Equipo 2
Presentacion Herramientas Gerenciales Equipo 2Presentacion Herramientas Gerenciales Equipo 2
Presentacion Herramientas Gerenciales Equipo 2
 
Types of listening
Types of listeningTypes of listening
Types of listening
 
Cruzadas 8° Ano
Cruzadas 8° AnoCruzadas 8° Ano
Cruzadas 8° Ano
 
La cuisinière cuisinée
La cuisinière cuisinéeLa cuisinière cuisinée
La cuisinière cuisinée
 
Mapnik and Node.js
Mapnik and Node.jsMapnik and Node.js
Mapnik and Node.js
 
Camtasia getting started guide
Camtasia getting started guideCamtasia getting started guide
Camtasia getting started guide
 
Japon
JaponJapon
Japon
 
AFWA_Monarch_Report_Oct_23_2015
AFWA_Monarch_Report_Oct_23_2015AFWA_Monarch_Report_Oct_23_2015
AFWA_Monarch_Report_Oct_23_2015
 
Carlos Castaneda - Segundo círculo do poder
Carlos Castaneda -  Segundo círculo do poderCarlos Castaneda -  Segundo círculo do poder
Carlos Castaneda - Segundo círculo do poder
 
Bergamo quest eng
Bergamo quest engBergamo quest eng
Bergamo quest eng
 
Mάτσου Πίτσου,Ελένη Παρσάλογλου
Mάτσου Πίτσου,Ελένη Παρσάλογλου Mάτσου Πίτσου,Ελένη Παρσάλογλου
Mάτσου Πίτσου,Ελένη Παρσάλογλου
 
Cronocias
CronociasCronocias
Cronocias
 
Mayas 8
Mayas 8Mayas 8
Mayas 8
 
[포트폴리오]LG 휴대폰 G-FLEX 크리에이티브 전략
[포트폴리오]LG 휴대폰 G-FLEX 크리에이티브 전략[포트폴리오]LG 휴대폰 G-FLEX 크리에이티브 전략
[포트폴리오]LG 휴대폰 G-FLEX 크리에이티브 전략
 
WE CARE PROJECT FLYER
WE CARE PROJECT FLYERWE CARE PROJECT FLYER
WE CARE PROJECT FLYER
 
Trabajo final economia
Trabajo final economiaTrabajo final economia
Trabajo final economia
 

Similar to Statistik - Teil 6

Day-2_Presentation for SPSS parametric workshop.pptx
Day-2_Presentation for SPSS parametric workshop.pptxDay-2_Presentation for SPSS parametric workshop.pptx
Day-2_Presentation for SPSS parametric workshop.pptx
rjaisankar
 
Lecture 7 Hypothesis testing.pptx
Lecture 7 Hypothesis testing.pptxLecture 7 Hypothesis testing.pptx
Lecture 7 Hypothesis testing.pptx
shakirRahman10
 
Assessment 3 ContextYou will review the theory, logic, and a.docx
Assessment 3 ContextYou will review the theory, logic, and a.docxAssessment 3 ContextYou will review the theory, logic, and a.docx
Assessment 3 ContextYou will review the theory, logic, and a.docx
galerussel59292
 
Malimu statistical significance testing.
Malimu statistical significance testing.Malimu statistical significance testing.
Malimu statistical significance testing.
Miharbi Ignasm
 
Topic 7 stat inference
Topic 7 stat inferenceTopic 7 stat inference
Topic 7 stat inference
Sizwan Ahammed
 
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesis
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesisTesting of Hypothesis, p-value, Gaussian distribution, null hypothesis
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesis
svmmcradonco1
 

Similar to Statistik - Teil 6 (20)

L hypo testing
L hypo testingL hypo testing
L hypo testing
 
Day-2_Presentation for SPSS parametric workshop.pptx
Day-2_Presentation for SPSS parametric workshop.pptxDay-2_Presentation for SPSS parametric workshop.pptx
Day-2_Presentation for SPSS parametric workshop.pptx
 
Spss session 1 and 2
Spss session 1 and 2Spss session 1 and 2
Spss session 1 and 2
 
Overview of statistics: Statistical testing (Part I)
Overview of statistics: Statistical testing (Part I)Overview of statistics: Statistical testing (Part I)
Overview of statistics: Statistical testing (Part I)
 
Unit 4 Tests of Significance
Unit 4 Tests of SignificanceUnit 4 Tests of Significance
Unit 4 Tests of Significance
 
Hypothesis and t-tests
Hypothesis and t-testsHypothesis and t-tests
Hypothesis and t-tests
 
Lecture 7 Hypothesis testing.pptx
Lecture 7 Hypothesis testing.pptxLecture 7 Hypothesis testing.pptx
Lecture 7 Hypothesis testing.pptx
 
Hypothesis Testing
Hypothesis TestingHypothesis Testing
Hypothesis Testing
 
Assessment 3 ContextYou will review the theory, logic, and a.docx
Assessment 3 ContextYou will review the theory, logic, and a.docxAssessment 3 ContextYou will review the theory, logic, and a.docx
Assessment 3 ContextYou will review the theory, logic, and a.docx
 
Malimu statistical significance testing.
Malimu statistical significance testing.Malimu statistical significance testing.
Malimu statistical significance testing.
 
20200519073328de6dca404c.pdfkshhjejhehdhd
20200519073328de6dca404c.pdfkshhjejhehdhd20200519073328de6dca404c.pdfkshhjejhehdhd
20200519073328de6dca404c.pdfkshhjejhehdhd
 
Testing of Hypothesis
Testing of Hypothesis Testing of Hypothesis
Testing of Hypothesis
 
Hypothesis testing
Hypothesis testingHypothesis testing
Hypothesis testing
 
Hypothesistesting2
Hypothesistesting2Hypothesistesting2
Hypothesistesting2
 
teast mean one and two sample
teast mean one and two sampleteast mean one and two sample
teast mean one and two sample
 
Abc4
Abc4Abc4
Abc4
 
Hypothesis testing
Hypothesis testingHypothesis testing
Hypothesis testing
 
Topic 7 stat inference
Topic 7 stat inferenceTopic 7 stat inference
Topic 7 stat inference
 
Hypothesis testing1
Hypothesis testing1Hypothesis testing1
Hypothesis testing1
 
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesis
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesisTesting of Hypothesis, p-value, Gaussian distribution, null hypothesis
Testing of Hypothesis, p-value, Gaussian distribution, null hypothesis
 

More from Ulrich Schrader

More from Ulrich Schrader (20)

Babylon in der pflege
Babylon in der pflegeBabylon in der pflege
Babylon in der pflege
 
Pflegeinformatik - Internationale Entwicklung
Pflegeinformatik - Internationale EntwicklungPflegeinformatik - Internationale Entwicklung
Pflegeinformatik - Internationale Entwicklung
 
Web 2 - Vom Ich zum Wir
Web 2 - Vom Ich zum WirWeb 2 - Vom Ich zum Wir
Web 2 - Vom Ich zum Wir
 
ICNP Version 2.0
ICNP Version 2.0ICNP Version 2.0
ICNP Version 2.0
 
Erfahrungen mit Screencasting und Podcasting
Erfahrungen mit Screencasting und PodcastingErfahrungen mit Screencasting und Podcasting
Erfahrungen mit Screencasting und Podcasting
 
The ICNP BaT from translation tool to translation server
The ICNP BaT from translation tool to translation serverThe ICNP BaT from translation tool to translation server
The ICNP BaT from translation tool to translation server
 
Statistik - Teil 5
Statistik - Teil 5Statistik - Teil 5
Statistik - Teil 5
 
Statistik - Teil 4
Statistik - Teil 4Statistik - Teil 4
Statistik - Teil 4
 
Statistik - Teil 3
Statistik - Teil 3Statistik - Teil 3
Statistik - Teil 3
 
Statistik - Teil 1
Statistik - Teil 1Statistik - Teil 1
Statistik - Teil 1
 
Statistik - Teil 2
Statistik - Teil 2Statistik - Teil 2
Statistik - Teil 2
 
Umgang Mit Risiken
Umgang Mit RisikenUmgang Mit Risiken
Umgang Mit Risiken
 
Patienteninformation und Pflege
Patienteninformation und PflegePatienteninformation und Pflege
Patienteninformation und Pflege
 
Auswirkungen von Informationstechnologie bei Pflegenden
Auswirkungen von Informationstechnologie bei PflegendenAuswirkungen von Informationstechnologie bei Pflegenden
Auswirkungen von Informationstechnologie bei Pflegenden
 
Blogs und Wiki in der Lehre - Web 2.0 für Pflegemanager
Blogs und Wiki in der Lehre - Web 2.0 für PflegemanagerBlogs und Wiki in der Lehre - Web 2.0 für Pflegemanager
Blogs und Wiki in der Lehre - Web 2.0 für Pflegemanager
 
Offene Lehrveranstaltungen mit Web 2.0 Technologien
Offene Lehrveranstaltungen mit Web 2.0 TechnologienOffene Lehrveranstaltungen mit Web 2.0 Technologien
Offene Lehrveranstaltungen mit Web 2.0 Technologien
 
Screencasting - Vorlesungsaufzeichnungen leicht gemacht
Screencasting - Vorlesungsaufzeichnungen leicht gemachtScreencasting - Vorlesungsaufzeichnungen leicht gemacht
Screencasting - Vorlesungsaufzeichnungen leicht gemacht
 
DatenqualitäT
DatenqualitäTDatenqualitäT
DatenqualitäT
 
It Projekte
It  ProjekteIt  Projekte
It Projekte
 
2 Pflegeterminologien
2 Pflegeterminologien2 Pflegeterminologien
2 Pflegeterminologien
 

Recently uploaded

Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
fonyou31
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
SoniaTolstoy
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
QucHHunhnh
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 

Recently uploaded (20)

Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13The Most Excellent Way | 1 Corinthians 13
The Most Excellent Way | 1 Corinthians 13
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
Ecosystem Interactions Class Discussion Presentation in Blue Green Lined Styl...
 
social pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajansocial pharmacy d-pharm 1st year by Pragati K. Mahajan
social pharmacy d-pharm 1st year by Pragati K. Mahajan
 
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
BAG TECHNIQUE Bag technique-a tool making use of public health bag through wh...
 
IGNOU MSCCFT and PGDCFT Exam Question Pattern: MCFT003 Counselling and Family...
IGNOU MSCCFT and PGDCFT Exam Question Pattern: MCFT003 Counselling and Family...IGNOU MSCCFT and PGDCFT Exam Question Pattern: MCFT003 Counselling and Family...
IGNOU MSCCFT and PGDCFT Exam Question Pattern: MCFT003 Counselling and Family...
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdfBASLIQ CURRENT LOOKBOOK  LOOKBOOK(1) (1).pdf
BASLIQ CURRENT LOOKBOOK LOOKBOOK(1) (1).pdf
 
1029 - Danh muc Sach Giao Khoa 10 . pdf
1029 -  Danh muc Sach Giao Khoa 10 . pdf1029 -  Danh muc Sach Giao Khoa 10 . pdf
1029 - Danh muc Sach Giao Khoa 10 . pdf
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 

Statistik - Teil 6

  • 1. Statistik Teil 6 - Statistisches Testen Ulrich Schrader http://info.ulrich-schrader.de
  • 2. Statistisches Testen • Situation – 2 Populationen aus denen jeweils eine Stichprobe gezogen wird. Ein Merkmal X wird in beiden Stichproben beobachtet. • Frage – Unterscheidet sich der Erwartungswert des Merkmals in den beiden Populationen? • 2 Hypothesen – quot;Die Erwartungswerte unterscheiden sich nicht in den beiden Populationen.quot; - Nullhypothese H0 – quot;Die Erwartungswerte unterscheiden sich in den beiden Populationen.quot; - Alternativhypothese H1
  • 3. z.B. Therapie A Population A Stichprobe A EA(X) Frage : E A (X) E B ( X ) oder E A (X) EB (X ) H 1 oder H 0 z.B. Unterscheidet sich das erwartete Ergebnis bei Therapie A von dem bei Therapie B? Population B Stichprobe B EB(X) z.B. Therapie B
  • 4. Entscheidungsmatrix Es liegt tatsächlich vor Entscheidung für H0 – „kein Unterschied“ H1 – „Unterschied“ H0 richtige Entscheidung falsch negative Entscheidung „kein Unterschied“ (1 - ) – „Fehler 2. Art“ falsch positive H1 richtige Entscheidung Entscheidung „Unterschied“ (1 - ) – „Fehler 1. Art“ Ein statistischer Test ist eine Entscheidungsregel, welche die Wahrscheinlichkeit für einen Fehler 1. Art kleiner als einen vorgegebenen Wert hält und die Wahrscheinlichkeit für einen Fehler 2. Art möglichst gering hält. • 1- : Signifikanzniveau • : Irrtumswahrscheinlichkeit • 1- : Güte/Mächtigkeit des Tests
  • 5. Vorgehen beim statistischen Testen 1. Schritt • Formulierung der Hypothesen – Alternativhypothese und Nullhypothese • Festlegung der noch zulässigen Irrtumswahrscheinlichkeit α (Fehler 1. Art) – Wahrscheinlichkeit eines Fehlers im Fall der Entscheidung für die Alternativhypothese H1) – Bestimmt sich aus den möglichen Folgen einer Fehlentscheidung • Auswahl eines geeigneten Tests • Fehler 2. Art β möglichst klein bei vorgegebenem Signifikanzniveau (1 - α) (Möglichst mächtiger Test)
  • 6. Vorgehen beim statistischen Testen 2. Schritt • Annahme (willkürlich) – H0 gilt (kein Unterschied) (Konservativ: Die neue Therapie macht keinen Unterschied) • Berechnung einer Prüfgröße, deren Verteilung bekannt ist, wenn die Annahme H0 erfüllt ist, aus den Werten der Stichproben.
  • 7. Vorgehen beim statistischen Testen 3. Schritt • Verwerfen der ursprünglichen (willkürlichen) Annahme, H0 soll gelten, wenn der Wert für die Prüfgröße gemäß der bekannten Verteilung nicht erwartet wird. Dann Alternativhypothese H1 annehmen. • Sonst H0 beibehalten. Konservativer Ansatz.
  • 8. Statistischer Test Verteilung der Prüfgröße - H0 gilt Werte lassen sich gut durch die Annahme H0 gilt erklären. 2 1 2 H0 wird beibehalten Unerwartete Werte Unerwartete Werte H0 wird verworfen H0 wird verworfen H1 wird angenommen H1 wird angenommen
  • 9. p-Wert • Oft als Ergebnis eines statistischen Tests angegeben. • Geringste Irrtumswahrscheinlichkeit , deren Festlegung mit den beobachteten Stichprobenwerten gerade noch zur Verwerfung der Nullhypothese geführt hätte.
  • 10. Beispiel IM Rosen, et al. : Prenatal breastfeeding education and breastfeeding outcomes. MCN. The American Journal of Maternal Child Nursing, Vol. 33, No. 5. (008), pp. 315-319. • PURPOSE: To examine the impact of various breastfeeding outcomes of three cohorts receiving different methods of prenatal breastfeeding education. METHODS: Retrospective cohort design with patients attending a breastfeeding education class at an Army medical center. Controls were matched for sponsor rank, marital status, and smoking status. One hundred ninety-four mothers who expressed intent to breastfeed received breastfeeding education as follows: (a) a class that used video demonstration and group teaching by a lactation consultant, (b) a new mothers' support group with one-on-one teaching prenatally and weekly meetings postpartum, taught by a lactation consultant and a pediatrician, and (c) a control group educated at prenatal visits only. Descriptive statistics, chi-square, ANOVA, unpaired t test, and logistic regression were used to analyze the data. • RESULTS: Women who attended prenatal breastfeeding classes had significantly increased breastfeeding at 6 months when compared to controls (p = .01). There was no significant difference in rates between types of classes offered (p = .45). • CLINICAL IMPLICATIONS: Prenatal breastfeeding education can influence the amount of time women breastfeed. All providers of prenatal care should consider offering such classes in order to improve breastfeeding rates.
  • 11. Tests mit unabhängigen/paarigen Stichproben • Unabhängige Stichproben – Beobachtungseinheiten der einen Stichprobe haben keinen Beziehung zu Beobachtungseinheiten der anderen Stichprobe – Indiz: Stichprobenanzahlen unterschiedlich • Paarige Stichproben – Jede Beobachtungseinheit der einen Stichprobe hat genau eine korrespondierende Beobachtungseinheit in der anderen Stichprobe. – Typisch: Vorher/Nachher Mutter in der einen, Kind in der anderen Stichprobe Zwillinge – Notwendig: Stichprobenanzahlen gleich
  • 13. Übersicht über wichtige statistische Testverfahren Merkmal Prüfgröße Unabhängige SP Paarige SP Quantitativ, t-verteilt Student's t-Test für Student's t-Test für normalverteilt, unabh. SP paarige SP ähnl. Streuung Quantitativ, standard- Wilcoxon Rang-Test Wilcoxon Rang-Test beliebig verteilt normalverteilt für unabh. SP für paarige SP Ordinal standard- Wilcoxon Rang-Test Wilcoxon Rang-Test normalverteilt für unabh. SP für paarige SP Nominal χ2-verteilt Chi-Quadrat- Vorzeichentest (dichotom, Vierfeldertest zweiwertig) Häufigkeiten
  • 14. Beispiel MY Chang, CH Chen, KF Huang: Effects of music therapy on psychological health of women during pregnancy. Journal of clinical nursing, Vol. 17, No. 19. (October 2008), pp. 2580-2587. • AIMS AND OBJECTIVES: The purpose of this study was to examine the effects of music therapy on stress, anxiety and depression in Taiwanese pregnant women. • BACKGROUND: The value of music therapy is slowly being realized by nurses in various clinical areas, including obstetrics. Previous studies have demonstrated a high prevalence of psychological stress during pregnancy. [...] • DESIGN: A randomized experimental study design was developed and implemented. • METHODS: Two hundred and thirty-six pregnant women were randomly assigned to music therapy (n = 116) and control (n = 120) groups. The music therapy group received two weeks of music intervention. The control group received only general prenatal care. Psychological health was assessed using three self-report measures: Perceived Stress Scale (PSS), State Scale of the State- Trait Anxiety Inventory (S-STAI) and Edinburgh Postnatal Depression Scale (EPDS). RESULTS: In a paired t-test, the music therapy group showed significant decrease in PSS, S-STAI and EPDS after two weeks. The control group only showed a significant decrease in PSS after two weeks. This decrease was not as substantial as in the experimental group. [...] • CONCLUSIONS: This controlled trial provides preliminary evidence that two-week music therapy during pregnancy provides quantifiable psychological benefits. • RELEVANCE TO CLINICAL PRACTICE: The findings can be used to encourage pregnant women to use this cost-effective method of music in their daily life to reduce their stress, anxiety and depression. Further research is needed to test the long-term benefits.
  • 15. Beispiel CL Dennis, et al.: Effect of peer support on prevention of postnatal depression among high risk women: multisite randomised controlled trial. BMJ (Clinical research ed.), Vol. 338 (2009) OBJECTIVE: To evaluate the effectiveness of telephone based peer support in the prevention of postnatal depression. DESIGN: Multisite randomised controlled trial. SETTING: Seven health regions across Ontario, Canada. PARTICIPANTS: 701 women in the first two weeks postpartum identified as high risk for postnatal depression with the Edinburgh postnatal depression scale and randomised with an internet based randomisation service. I NTERVENTION: Proactive individualised telephone based peer (mother to mother) support, initiated within 48- 72 hours of randomisation, provided by a volunteer recruited from the community who had previously experienced and recovered from self reported postnatal depression and attended a four hour training session. MAIN OUTCOME MEASURES: Edinburgh postnatal depression scale, structured clinical interview-depression, state-trait anxiety inventory, UCLA loneliness scale, and use of health services. RESULTS: After web based screening of 21 470 women, 701 (72%) eligible mothers were recruited. A blinded research nurse followed up more than 85% by telephone, including 613 at 12 weeks and 600 at 24 weeks postpartum. At 12 weeks, 14% (40/297) of women in the intervention group and 25% (78/315) in the control group had an Edinburgh postnatal depression scale score >12 (chi(2)=12.5, P<0.001; number need to treat 8.8, 95% confidence interval 5.9 to 19.6; relative risk reduction 0.46, 95% confidence interval 0.24 to 0.62). [...] Of the 221 women in the intervention group who received and evaluated their experience of peer support, over 80% were satisfied and would recommend this support to a friend. CONCLUSION: Telephone based peer support can be effective in preventing postnatal depression among women at high risk.