This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: 1 Multi-Group Designs: One Way Analysis of Variance (chapter 10) Why do we need it? The Problem with Multiple t-tests Increase in Type I error For 3 tests, p becomes 1-(1-.05) 3 =1-(.95) 3 =1-.86=.14=14% Need to adjust the p level down to account for multiple comparisons Example: .05/3=.017 Adjusted level increases risk of Type II error The problem with Multiple Tests Number of Number of Pairs Groups of Means 3 3 4 6 5 10 6 15 7 21 8 28 To adjust the p level down to account for multiple comparisons, we divide α (e.g., 0.05) by the number of COMPARISONS we want to make, not the number of GROUPS 2 Advantages of ANOVA Allows us to evaluate the performance of three or more groups within one statistical test Allows us to minimize Type I error despite multiple comparisons Allows us to understand complex functions Low High Memory Blood Sugar Low High Memory Medium Blood Sugar Is it any different?...
View Full Document
- Spring '08