Likelihood-based Inference with Nonignorable Missing Responses and Covariates in Models for Discrete Longitudinal Data

@inproceedings{Stubbendick2006LikelihoodbasedIW,
  title={Likelihood-based Inference with Nonignorable Missing Responses and Covariates in Models for Discrete Longitudinal Data},
  author={Amy L. Stubbendick and Joseph G. Ibrahim},
  year={2006}
}
We propose methods for estimating parameters in two types of models for discrete longitudinal data in the presence of nonignorable missing responses and covariates. We first present the generalized linear model with random effects, also known as the generalized linear mixed model. We specify a missing data mechanism and a missing covariate distribution and incorporate them into the complete data log-likelihood. Parameters are estimated via maximum likelihood using the Gibbs sampler and a Monte… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 30 references

Analysis of multivariate probit models

  • S. Chib, E. Greenberg
  • Biometrika 85, 347-361.
  • 1998
Highly Influential
9 Excerpts

A Monte Carlo implementation of the EM algorithm and the poor man’s data augmentation algorithms

  • G. C. Wei, M. A. Tanner
  • J. Amer. Statist. Assoc. 85, 699-704.
  • 1990
Highly Influential
3 Excerpts

Incomplete data in generalized linear models

  • J. G. Ibrahim
  • J. Amer. Statist. Assoc. 85, 765-769.
  • 1990
Highly Influential
10 Excerpts

Adaptive rejection sampling for Gibbs sampling

  • W. R. Gilks, P. Wild
  • Appl. Statist. 41, 337-348.
  • 1992
Highly Influential
2 Excerpts

Similar Papers

Loading similar papers…