Closed form estimates for missing counts in multidimensional incomplete tables

TL;DR

This paper develops closed-form estimation methods for missing data in multidimensional tables using log-linear models, covering various missing data mechanisms and providing explicit boundary estimates, demonstrated on real data.

Contribution

It introduces simple closed-form estimators for arbitrary incomplete tables under different missing data mechanisms, including nonignorable nonresponse models.

Findings

Closed-form estimates for expected cell counts

Explicit boundary estimates under nonignorable nonresponse

Application to real-world incomplete data

Abstract

A useful technique for analyzing incomplete tables is to model the missing data mechanisms of the variables using log-linear models. In this paper, we use log-linear parametrization and propose estimation methods for arbitrary three-way and $n$-dimensional incomplete tables. All possible cases in which data on one or more of the variables may be missing are considered. We provide simple closed form estimates of expected cell counts and parameters for the various missing data models. We also obtain explicit boundary estimates under nonignorable nonresponse models. Finally, a real-life dataset is analyzed to illustrate our results for modelling and estimation in multidimensional incomplete tables.