The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
448
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 1, 2012 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistics in Epidemiology
|
Abstract - #306073 |
Title:
|
Bayesian Inference on Constrained Parameter Spaces of Functional Mixed Models
|
Author(s):
|
Sarat C Dass*+
|
Companies:
|
Michigan State University
|
Address:
|
Department of Statistics and Probability, East Lansing, MI, , USA
|
Keywords:
|
functional data analysis ;
linear mixed models ;
splines ;
Bayesian analysis
|
Abstract:
|
This talk develops estimation and testing methodology for multivariate functional response data modeled non-parametrically using fixed and random spline coefficients. Of particular interest is the development of methodology for pre-specified covariance matrix forms of the random coefficients, which translate to constraints on the (matrix) entries. The Bayesian testing approach proposed requires the development of default prior elicitation on the constrained positive definite spaces. The statistical methodology is developed in direct response to studying the impact of human activity on biodiversity in the Upper Peninsula of Michigan. Audio measurements taken at regular time intervals are converted to energy readings corresponding to 12 frequency bands for different categories of wildlife. These energy readings thus constitute multivariate functional data; pre-specified constraints on the covariance matrix entries determine the extent of impact of human activity on wildlife at the different frequency bands. Methodology is also developed for determining whether these constraints differ for spatial locations that vary according to their degree of pristineness.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.