Incomplete Data in Generalized Linear Models
Joseph G. Ibrahim · Journal of the American Statistical Association · 1990
This article examines incomplete data for the class of generalized linear models, in which incompleteness is due to partially missing covariates on some observations. Under the assumption that the missing data are missing at random, it is shown that the E step of the EM algorithm for any generalized linear model can be expressed as a weighted complete data log-likelihood when the unobserved covariates are assumed to come from a discrete distribution with finite range. Expressing the E step in this manner allows for a straightforward maximization in the M step, thus leading to maximum likelihood estimates (MLE's) for the parameters. Asymptotic variances of the MLE's are also derived, and results are illustrated with two examples.
Cited by 344 works. doi:10.1080/01621459.1990.10474938
Authors
References
- Inference and missing data
- Moments and Distributions of Estimates of Population Parameters from Fragmentary Samples
- Estimation of Exponential Survival Probabilities with Concomitant Information
- Maximum Likelihood Estimates for a Multivariate Normal Distribution when Some Observations are Missing
- Missing Observations in Multivariate Statistics I. Review of the Literature
- Missing Values in Multivariate Analysis
- The Analysis of Incomplete Data
- Estimation of Parameters in the Multivariate Normal Distribution with Missing Observations
- Compound Poisson Regression Models
- Maximum Likelihood Estimation for Mixed Continuous and Categorical Data with Missing Values