Analysis of missing data with regularized likelihood

Abstract
Missing data arise commonly in applications, and research on this topic has received extensive attention in the past few decades. Various inference methods have been developed under different missing data mechanisms, including missing at random and missing not at random mechanisms. It is, however, difficult to assess what missing data mechanism is feasible when handling data with missing values. In this paper, we consider a unified modeling scheme for missing data and develop an estimation procedure using regularized likelihood. Numerical studies are reported to evaluate the performance of the proposed method.