Nonignorable Models for Intermittently Missing Categorical Longitudinal Responses
Article first published online: 30 NOV 2009
© 2009, The International Biometric Society
Volume 66, Issue 3, pages 834–844, September 2010
How to Cite
Tsonaka, R., Rizopoulos, D., Verbeke, G. and Lesaffre, E. (2010), Nonignorable Models for Intermittently Missing Categorical Longitudinal Responses. Biometrics, 66: 834–844. doi: 10.1111/j.1541-0420.2009.01365.x
- Issue published online: 30 NOV 2009
- Article first published online: 30 NOV 2009
- Received March 2009. Revised September 2009. Accepted September 2009.
- Categorical responses;
- Constrained vertex-exchange method;
- Marginalized models;
- Non-parametric maximum likelihood;
- Selection model;
- Shared parameter model
Summary A class of nonignorable models is presented for handling nonmonotone missingness in categorical longitudinal responses. This class of models includes the traditional selection models and shared parameter models. This allows us to perform a broader than usual sensitivity analysis. In particular, instead of considering variations to a chosen nonignorable model, we study sensitivity between different missing data frameworks. An appealing feature of the developed class is that parameters with a marginal interpretation are obtained, while algebraically simple models are considered. Specifically, marginalized mixed-effects models (Heagerty, 1999, Biometrics 55, 688–698) are used for the longitudinal process that model separately the marginal mean and the correlation structure. For the correlation structure, random effects are introduced and their distribution is modeled either parametrically or non-parametrically to avoid potential misspecifications.