This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 659
Type: Topic Contributed
Date/Time: Thursday, August 5, 2010 : 10:30 AM to 12:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract - #308859
Title: The Effect of Spatial Confounding on Covariate Estimation
Author(s): Garritt Page*+ and Yajun Liu and Dongchu Sun
Companies: Duke University and University of Missouri and University of Missouri
Address: Box 90251, Durham, NC, 27708, USA
Keywords: Spatial confounding ; Spatial correlation ; Random effects
Abstract:

It is not uncommon in many applied contexts in which a spatially-varying error structure is considered for there to exist a covariate of interest or an unmeasured covariate that is also spatially-varying. In these situations it is hard to distinguish the effect of a covariate from the residual spatial variation. We investigate the effect of spatial confounding on the estimation of a covariate in terms of bias, variance, and mean squared error (MSE). We do this first by providing some analytical results for simple linear and multiple regression models with a normal spatial error structure were the full covariance structure is known. Then by way of a simulation study, we consider the effect of spatial confounding on the estimation of a covariate in a generalized linear model setting.


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 2010 program




2010 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.