INFERENCE USING CONDITIONAL LOGISTIC-REGRESSION WITH MISSING COVARIATES

When there are many nuisance parameters in a logistic regression model , a popular method for eliminating these nuisance parameters is condit ional logistic regression. Unfortunately, another common problem in a logistic regression analysis is missing covariate data. With many nuis ance parameters to eliminate and missing covariates, many investigator s exclude any subject with missing covariates and then use conditional logistic regression, often called a complete-case analysis. In this a rticle, we derive a modified conditional logistic regression that is a ppropriate with covariates that are missing at random. Performing a co nditional logistic regression with only the complete cases is convenie nt with existing statistical packages, but it may give bias if missing ness is not completely at random.