Week 9_Ch10_ANOVA

# Week 9_Ch10_ANOVA - Chapter 10 Analysis of Variance (ANOVA)...

This preview shows pages 1–10. Sign up to view the full content.

Chapter 10 Analysis of Variance (ANOVA)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
What is ANOVA ANOVA is the primary statistical approach used to evaluate the effects of an independent variable involving more than two levels in experimental design (One-Factor, or One-way, ANOVA). E xample - does blood pressure vary by age group? ANOVA is also used to test the effects involving more than one IVs (Two- Factor, or Two-Way, ANOVA). E xample - does blood pressure vary by sex and/or age group?
Example of a study using ANOVA (from text pg. 240) Studying recall of visual stimuli Showed people 3 types of drawings Detailed Outline Incomplete Outline Which type of drawing will people recall the best?

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Example continued. .. Independent variable : Factor: type of drawing Level: 3 (Detailed, Outline Incomplete, Outline) Dependent variable : number of items recalled after viewing 30 drawings for 4 seconds each 5 subjects were in each experimental
The data: are the 3 groups really different? Incomplete  Outline  Outline  Detailed  Drawing  19  14  15  13  13  10  16  16  11  17  12  12  20  10  12  Mean = 17  Mean = 13  Mean = 12

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Are the groups really different?
Analysis strategy The mean of all the scores, the GLOBAL MEAN, is 14, but people vary around that mean. Why? Maybe the 3 groups are really different (drawing type really does affect recall) Maybe it’s just individual differences (random variation around the mean)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Analysis strategy (2) The basic concept of ANOVA is to partition variance of the dependent variable to between-group and within-group variations. Strategy: break up the total variance into 2 components: Between-groups variance - the differences between the 3 groups Within-groups variance - the differences among the subjects within each group
Null hypothesis : assume that there is no difference in the mean of the scores across the groups (all the variation in scores is caused by random error or individual differences, not by which group a subject is in). Alternative hypothesis

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 10/25/2010 for the course HP 340L taught by Professor Nezami during the Spring '05 term at USC.

### Page1 / 42

Week 9_Ch10_ANOVA - Chapter 10 Analysis of Variance (ANOVA)...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online