Multiple imputation has become a highly useful technique for handling missing values in many settings. In this paper, we compare the performance of a multiple imputation model based on empirical Bayes techniques to a direct maximum likelihood analysis approach that is known to be robust in the presence of missing observations. Specifically, we focus on handling of missing item scores in multilevel cross-classification item response data structures that may require more complex imputation techniques, and for situations where an imputation model can be more general than the analysis model. Through a simulation study and an empirical example, we show that multiple imputation is more effective in estimating missing item scores and produces unbiased parameter estimates of explanatory item response theory models formulated as cross-classified mixed models.
Keywords: Explanatory Item Response Models, Missing Data, Multiple Imputation