Model averaging estimation of generalized linear models with imputed covariates

We address the problem of estimating generalized linear models when some covariate values are missingbut imputations are available to fill-in the missing values. This situation generates a bias-precision tradeoffin the estimation of the model parameters. Extending the generalized missing-indicator methodproposed by Dardanoni et al. (2011) for linear regression, we handle this trade-off as a problem ofmodel uncertainty using Bayesian averaging of classical maximum likelihood estimators (BAML). We alsopropose a block model averaging strategy that incorporates information on the missing-data patterns andis computationally simple. An empirical application illustrates our approach.