Methods and Applications of Statistics in Clinical Trials, Volume 1: Concepts, Principles, Trials, and Designs

Chapter 42

Missing Data

Geert Molenberghs and Emmanuel Lesaffre

42.1 Introduction

Data from longitudinal studies in general, and from clinical trials in particular, are prone to incompleteness. As incompleteness usually occurs for reasons outside of the control of the investigators and may be related to the outcome measurement of interest, it is generally necessary to reflect on the process governing incompleteness. Only in special but important cases is it possible to ignore the missingness process.

When patients are examined repeatedly in a clinical trial, missing data can occur for various reasons and at various visits. When missing data result from patient dropout, the missing data have a monotone pattern. Nonmonotone missingness occurs when there are intermittent missing values as well. The focus here will be on dropout. Reasons typically encountered are adverse events, illness not related to study medication, uncooperative patient, protocol violation, ineffective study medication, loss to follow-up, and so on.

When referring to the missing-value, or nonresponse, process, we will use the terminology of Little and Rubin [1]. A nonresponse process is said to be missing completely at random (MCAR) if the missingness is independent of both unobserved and observed data and missing at random (MAR) if, conditional on the observed data, the missingness is independent of the unobserved measurements. A process that is neither MCAR nor MAR is termed nonrandom (MNAR). In the context of ...