MSIMST {MSIMST} | R Documentation |
Incorporates a Bayesian monotonic single-index mixed-effect model with a multivariate skew-t likelihood, specifically designed to handle survey weights adjustments. Features include a simulation program and an associated Gibbs sampler for model estimation. The single-index function is constrained to be monotonic increasing, utilizing a customized Gaussian process prior for precise estimation. The model assumes random effects follow a canonical skew-t distribution, while residuals are represented by a multivariate Student-t distribution. Offers robust Bayesian adjustments to integrate survey weight information effectively.
Maintainer: Qingyang Liu rh8liuqy@gmail.com (ORCID)
Authors:
Debdeep Pati debdeep@stat.tamu.edu
Dipankar Bandyopadhyay dbandyop@vcu.edu
Useful links: