This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: STAT 201 Handout 9 Two-Way ANOVA Simpsons Paradox revisited Recall the contingency analysis example: gender midterm performance Total Good Bad F M Total Difference among subjects with respect to extra factors, such as study habits, may mask any gender-midterm relationship. Therefore, we split the data into blocks according to the extra factor of study habits: Study habits = GOOD gender midterm performance Total Good Bad F M Total Study habits = BAD gender midterm performance Total Good Bad F M Total The split data help to bring out any gender-midterm relationship within each study habit block . We can do the same for any ANOVA study Two-way ANOVA : We collect weight loss data on subjects who underwent diet programs. There are two subjects in each program-gender block. The numbers are weight loss in pounds (numbers in parentheses are mean weight loss within a program-gender combination): Program gender (main factor) (blocking factor) F M 1 2,4 (3) 1,2 (1.5) 2 5,3 (4) 7,6 (6.5)7,6 (6....
View Full Document
This note was uploaded on 01/23/2012 for the course STAT 201 taught by Professor Staff during the Fall '03 term at Simon Fraser.
- Fall '03