On modeling repeated binary responses and time-dependent missing covariates

We develop a novel modeling strategy for analyzing data with repeated binary responses over time as well as time-dependent missing covariates. We assume that covariates are missing at random (MAR). We use the generalized linear mixed logistic regression model for the repeated binary responses and th...

Full description

Saved in:
Bibliographic Details
Published in:Journal of agricultural, biological, and environmental statistics biological, and environmental statistics, 2008-09, Vol.13 (3), p.270-293
Main Authors: Huang, Lan, Chen, Ming-Hui, Yu, Fang, Neal, Paul R, Anderson, Gregory J
Format: Article
Language:English
Subjects:
Agriculture
Agronomy. Soil science and plant productions
algorithms
Animal, plant and microbial ecology
Biological and medical sciences
Biometrics, statistics, experimental designs, modeling, agricultural computer applications
Biostatistics
Defoliation
flowering
forest trees
Fundamental and applied biological sciences. Psychology
General aspects. Techniques
Generalities. Biometrics, experimentation. Remote sensing
Health Sciences
mathematical models
Mathematics and Statistics
Maximum likelihood estimation
Medicine
Methods and techniques (sampling, tagging, trapping, modelling...)
Modeling
Monitoring/Environmental Analysis
Monte Carlo method
Moths
Parametric models
Precipitation
statistical models
Statistics
Statistics for Life Sciences
Temperature
Tilia americana
Weather
Weather conditions
Weather stations
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We develop a novel modeling strategy for analyzing data with repeated binary responses over time as well as time-dependent missing covariates. We assume that covariates are missing at random (MAR). We use the generalized linear mixed logistic regression model for the repeated binary responses and then propose a joint model for time-dependent missing covariates using information from different sources. A Monte Carlo EM algorithm is developed for computing the maximum likelihood estimates. We propose an extended version of the AIC criterion to identify the important factors that may explain the binary responses. A real plant dataset is used to motivate and illustrate the proposed methodology.
ISSN:1085-7117
1537-2693
DOI:10.1198/108571108X338023