FILLING THE GAP WITH MISSING DATA

Abstract

So far, methods of missing data imputation have been extensively studied to incorporate various data types. However, existing literatures focus mainly on its application in inference analysis when data incompleteness is present, and there is no silver bullet —the choice of imputation methods is dependent on data type, and study objective. This thesis discusses methods to use missing data to our advantage, in the perspective of three pillars of application. Firstly, imputation is integrated into a conflict detection strategy for summary statistics in likelihood free inference. Secondly, a streamlined machine learning algorithm pipeline is demonstrated, based on an irregularly spaced time-dependent or longitudinal dataset, showing the benefit of uncovering insights from the rich dataset. Lastly, on the methodological side of classifying longitudinal dataset, a Bayesian projection-based clustering method is proposed, facilitating customised choice of random effects in the mixed linear regression setting.