Online Program Home
My Program

Abstract Details

Activity Number: 640 - Quantile Based Modeling for a Variety of Heteroscedastic Data
Type: Invited
Date/Time: Thursday, August 2, 2018 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract #326812
Title: Bayesian Single-Index Model for Bounded Mental Health Response with Functional Covariates
Author(s): Debajyoti Sinha* and STUART LIPSITZ
Companies: Florida State University and HARVARD MEDICAL SCHOOL
Keywords: Markov Chain Monte Carlo; Single-index model; Quantile regression
Abstract:

For many biomedical with unknown non-linear relationship between the response and its multiple predictors, single index model provides practical dimension reduction and good physical interpretation. However widespread uses of existing Bayesian analysis for such models are lacking in biostatistics due to some major impediments including slow mixing of the Markov Chain Monte Carlo (MCMC), inability to deal with missing covariates and skewed response, and lack of theoretical justi cations. We present a new Bayesian single index model and associated MCMC algorithm with an efficient Metropolis Hastings (MH) step for sampling of the index vector. Our method leads to a model with good biological interpretation and prediction, implementable Bayesian inference, fast convergence of the MCMC, and a first time extension to accommodate skewed response and missing covariates. We also obtain for the first time, the set of sufficient conditions for obtaining optimal rate of convergence of the overall regression function. We illustrate the practical advantages of our method and computational tool via re-analysis of a mental health study with skewed response and functional covariate.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program