Protective estimation of longitudinal categorical data with nonrandom dropout
- 1 January 1997
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 26 (1) , 65-94
- https://doi.org/10.1080/03610929708831902
Abstract
Partially observed longitudinal categorical data, where the partial classification arises due to monotone dropout, are analyzed using a protective estimator, which was first suggested by Brown (Biometrics, 1990) for normally distributed data. It is appropriate when dropout depends on the unobserved outcomes only, a particular type of nonignorable nonresponse. Estimation of measurement parameters is possible, without explicitly modelling the dropout process. Necessary and sufficient conditions are derived in order to have a unique solution in the interior of the parameter space. It is shown that precision estimates can be based on the delta method, the EM algorithm, and on multiple imputation. The relative merits of these techniques are discussed and they are contrasted with direct likelihood estimation and with pseudo-likelihood estimation. The method is illustrated using data taken from a psychiatric study.Keywords
This publication has 18 references indexed in Scilit:
- Modeling the Drop-Out Mechanism in Repeated-Measures StudiesJournal of the American Statistical Association, 1995
- Marginal Modeling of Correlated Ordinal Data Using a Multivariate Plackett DistributionJournal of the American Statistical Association, 1994
- Informative Drop-Out in Longitudinal Data AnalysisJournal of the Royal Statistical Society Series C: Applied Statistics, 1994
- Logistic Regression for Correlated Binary DataJournal of the Royal Statistical Society Series C: Applied Statistics, 1994
- Pre‐natal blood lead levels and learning difficulties in children: An analysis of non‐randomly missing categorical dataStatistics in Medicine, 1992
- Regression Analysis for Categorical Variables with Outcome Subject to Nonignorable NonresponseJournal of the American Statistical Association, 1988
- Missing data in longitudinal studiesStatistics in Medicine, 1988
- Causal Models for Patterns of NonresponseJournal of the American Statistical Association, 1986
- Maximum Likelihood Estimation and Model Selection in Contingency Tables with Missing DataJournal of the American Statistical Association, 1982
- Analyzing Panel Data With Uncontrolled AttritionPublic Opinion Quarterly, 1974