Regression models with varying coefficients changing over certain underlying covariates offer great flexibility in capturing a functional relationship between the response and other covariates. This article extends such regression models to include random effects and to account for correlation and heteroscedasticity in error terms, and proposes an efficient new data-driven method to estimate varying regression coefficients via reparameterization and partial collapse. The proposed methodology is illustrated with a simulated study and longitudinal data from a study of soybean growth.
Bibliographical noteFunding Information:
Acknowledgments This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2014R1A1A2056049). We also thank the editors and referees for their many helpful comments.
© 2016 International Society for Bayesian Analysis.
All Science Journal Classification (ASJC) codes
- Statistics and Probability
- Applied Mathematics