Congenial Multiple Imputation and Matched Pairs Models for Square Tables: An Example of patients’ self-management

Abstract

Experimental studies often measure an individual’s quality of life before and after an intervention, with the data organized into a square table and analyzed using matched pair modeling. However, it is not unusual to find missing data in either round (i.e., before and/or after) of such studies and the use of multiple imputations with matched-pair modeling remains relatively unreported in the applied statistics literature. In this paper we introduce an approach which maintains dependency of responses over time and makes a match between the imputer and the analyst. We use ‘before’ and ‘after’ quality-of-life data from a randomized controlled trial to demonstrate how multiple imputation and matched-pair modeling can be congenially combined, avoiding a possible mismatch of imputation and analyses, and to derive a properly consolidated analysis of the quality-of-life data. We illustrate this strategy with a real-life example of one item from a quality-of-life study that evaluates the effectiveness of patients’ self-management of anticoagulation versus standard care as part of a randomized controlled trial.