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: LOGISTIC REGRESSION EXAMPLES As In linear regression, logistic regression models can be used to adjust for confounding variables Can perform essentially the same analysis as a MH analysis, adjusting for categorical variables, with logistic regression Can adjust for continuous variables as well (this we cant do with MH) Can also examine whether the OR(s) associated with the variable of interest differ by the values of another variable As in linear regression, this is done using interaction terms Epidemiologists call this effect modification because the effect (OR) of interest is modified by the additional variable Age adjusted odds ratio for association between Arcus senills and CHD In STATA Adjusted for age group, the OR for CHD associated with Arcus senilis is 1.5, 95% CI 1.1, 1.9 Z Wald test for whether adjusted OR=1 We are interested, whether adjusted for age whether Arcus Senills is associated with CHD Here, likelihood ratio test whether both the...
View Full Document
This note was uploaded on 02/09/2012 for the course STAT 513 taught by Professor Barbaramc.knight during the Spring '11 term at University of Washington.
- Spring '11
- Linear Regression