Effect of non‐random missing data mechanisms in clinical trials
- 30 December 1995
- journal article
- research article
- Published by Wiley in Statistics in Medicine
- Vol. 14 (24), 2675-2684
- https://doi.org/10.1002/sim.4780142407
Abstract
A simple form of non-ignorable missing data mechanisms based on two parameters is used to characterize the amount of missing data and the severity of non-randomness in clinical trials. Based on the formulation, the effect of non-randomly missing data on simple analyses which ignore the missing data is studied for binary and normally distributed response variables. In general, the effect of the non-randomly missing data on the bias and the power increases with the severity of non-randomness. The bias can be positive or negative and the power can be less than or greater than when the data are missing at random. The results of the analysis, ignoring the missing data, can be seriously flawed if the non-randomness is severe, even when only a small proportion of the sample is missing. The problem is more pronounced in the case of normally distributed response variables with unequal variances.Keywords
This publication has 9 references indexed in Scilit:
- Analysis of incomplete data under non-random mechanisms: bayesian inferenceCommunications in Statistics - Simulation and Computation, 1994
- Relationship between Glasgow Outcome Scale and Neuropsychological Measures after Brain InjuryNeurosurgery, 1993
- Statistical handling of drop‐outs in longitudinal clinical trialsStatistics in Medicine, 1992
- Monitoring Clinical Trials Based on Predictive Probability of SignificanceBiometrics, 1989
- Correcting for the bias caused by drop‐outs in hypertension trialsStatistics in Medicine, 1988
- Comparing incomplete paired binomial data under non‐random mechanismsStatistics in Medicine, 1988
- Model-Based Direct AdjustmentJournal of the American Statistical Association, 1987
- Post StratificationJournal of the Royal Statistical Society. Series A (General), 1979