This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 4/3/2008 1 ChiSquare Psyc110 April 3, 2008 2 Outline Very quick power review + metaanalysis Introduction to chisquare (two types) Hypothesis testing Basic formula for chisquare Calculation example: goodness of fit type Handson calculation practice Contingency table calculation and example Very Quick Statistical Power Review Power = (1 ), generally use .80 as benchmark From textbook: = d * N Use with Appendix D.5 to find power Power is determined by three key factors : (1) Effect size ( d ) (2) Sample size ( N ) (3) Alpha level ( ) 4/3/2008 2 Mainstream Media Reporting of Psychological Research Yes, sometimes effect sizes are acknowledged But not often!! Researchers partly to blame (fields emphasis on p values) p < .001, but r (correlation between height and IQ) is only .03!! Practical significance (assuming causality): raising IQ from 100 to 130 would require a 14 foot increase in height! (Cohen, 1990) MetaAnalysis Quantitative way of combining results across many different studies Requires converting results of each study into a common metric (effect size or d !) Can give an estimate of overall effect in a particular area, but also what characteristics of studies might make certain ones have large effects and others small effects Janet Shibley Hyde Wellknown metaanalysis on gender differences in mathematics performance (male score minus female score) Overall d = 0.15 (shown at right) Removing studies of very high achievers, so including only representative samples: overall d = .05 Variation within each gender is MUCH larger than the differences between them 4/3/2008 3 ChiSquare: Introduction Used with frequency data (so: no means, no SD, no...
View
Full
Document
This note was uploaded on 05/05/2008 for the course PSYCH 110 taught by Professor Burt during the Spring '08 term at Vermont.
 Spring '08
 BURT

Click to edit the document details