# sol8 - STAT 426 HW8. 6.4 a. Summary of Goodness of fit...

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 Document

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.

Unformatted text preview: STAT 426 HW8. 6.4 a. Summary of Goodness of fit tests: Only (GH, GI) model (lack of HI term) is a poor fit (p-value is very small). b. Model G2 df (GH,GI) 11.6657 2 (GH, HI) 4.1267 2 (GI,HI) 2.3831 2 (GH,GI,HI) 0.3007 1 p-value 0.0029 0.127 0.3030 0.5834 95% C.I. for the G-H conditional odds ratio= (exp(-0.5945), exp(0.0913)) = (0.55, 1.10). 95% C.I. for the G-I conditional odds ratio= (exp(-0.0080), exp(0.9352)) = (0.99, 2.55). Because 1 is in both of the intervals, G is conditional independent of H and I. Therefore, gender may have no effect on opinion for these issues. True or False: 1. True 2. False. This is the conditional odds ratio, not the marginal odds ratio. 3. True (but the Pearson's chi-square test may not be approximated by the chi-square distribution with 28 degrees of freedom.) 4. False. We expect most residuals to be between -3 and 3, but if you have a large number of residuals, about 1% of them will be outside this range even if the residuals are normally distributed. 5. False. The conditional association between X2 and Y may be weak, but it does not imply no marginal association. 6. False. Only 5 free parameters. 1 2 3 4 ...
View Full Document

## This note was uploaded on 04/29/2010 for the course STAT stat 426 taught by Professor Xe during the Spring '10 term at University of Illinois at Urbana–Champaign.

### Page1 / 4

sol8 - STAT 426 HW8. 6.4 a. Summary of Goodness of fit...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online