Longitudinal data analysis with non-ignorable missing data

Unsupervised Learning with Non-Ignorable Missing Data

In this paper we explore the topic of unsupervised learning in the presence of nonignorable missing data with an unknown missing data mechanism. We discuss several classes of missing data mechanisms for categorical data and develop learning and inference methods for two specific models. We present empirical results using synthetic data which show that these algorithms can recover both the unkno...

Regression Analysis in Longitudinal Studies with Non-ignorable Missing Outcomes

Analysis of Non-ignorable Missing and Left-censored Longitudinal Biomarker Data

A transition model for quality-of-life data with non-ignorable non-monotone missing data.

In this paper, we consider a full likelihood method to analyze continuous longitudinal responses with non-ignorable non-monotone missing data. We consider a transition probability model for the missingness mechanism. A first-order Markov dependence structure is assumed for both the missingness mechanism and observed data. This process fits the natural data structure in the longitudinal framewor...

A Genetic Algorithm Approach for Non-Ignorable Missing Data

The databases store data that may be subjected to missing values either in data acquisition or data storage process. The proposed approach uses the widely used optimization technique called genetic algorithm for the NMAR (Not Missing At Random) missing mechanism which prevails more in real life that are non-ignorable. Since the non-ignorable mechanism needs prior