This preview shows pages 1–6. 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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Analysis of Variance Continued October 8, 2007 ANOVA table Source Sum of Squares df Mean square F p eta 2 Between 32 2 16 7.2 <.05 .62 Within 20 9 2.22 Total 52 11 Reporting in APA style F(2,9) = 7.2, p < .05, eta 2 = .62 Can write out eta 2 or can write 2 What can we conclude thus far? There was a significant effect of memory test type on how many words were remembered, F(2,9) = 7.2, p < .05, eta 2 = .62, with a large effect. So far, all can say Need to conduct posthoc tests Post hoc tests means after the fact do ONLY after reject the null hypothesis that all population means equal each test compares pair of means, like independent ttest many possible posthoc tests; covering two Tukeys HSD  use when have equal ns in each group or SPSS can do it for you Fishers protected t  use when dont have equal ns and cant use SPSS Tukeys HSD Will use because have equal ns Single test  get single value thats a critical value Calculates amount any pair of means need to be apart to be significant Absolute value of mean difference needs to be larger...
View Full
Document
 Fall '08
 Wiseman

Click to edit the document details