Advances in Longitudinal Survey Methodology

20Nonparametric Estimation for Longitudinal Data with Informative Missingness

Zahoor Ahmad and Li‐Chun Zhang

Department of Social Statistics and Demography, University of Southampton, Southampton, UK

20.1 Introduction

Longitudinal data analysis is of great interest in a wide array of disciplines across the medical, economic, and social sciences. Cross‐sectional data can only provide a snapshot at a single point of time and does not possess the capacity to reflect change, growth, or development. Aware of the limitations in cross‐sectional studies, many researchers have advanced the analytic perspective by examining data with repeated measurements. By measuring the same variable of interest repeatedly over time, the change is displayed, and constructive findings can be derived with regard to the significance of pattern revealed (Lynn, 2009a). Data with repeated measurements are referred to as longitudinal data. In many longitudinal data designs, subjects are assigned specified levels of a treatment or subjected to other risk factors over a number of time points that are separated by specified intervals.

Analysing longitudinal data poses many challenges due to several unique features inherent in such data. First, a troublesome feature of longitudinal analysis is missing data in repeated measurements. In a longitudinal survey, missing observations of the variable of interest frequently occurs. For example, in a clinical trial on the effectiveness of a new medical treatment for ...