|
Activity Number:
|
344
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #300780 |
|
Title:
|
Semiparametric Spatial Modeling of Binary Outcomes with Application to Aberrant Crypt Foci in Colon Carcinogenesis Experiments
|
|
Author(s):
|
Tatiyana V. Apanasovich*+ and Raymond J. Carroll
|
|
Companies:
|
Texas A&M University and Texas A&M University
|
|
Address:
|
Dept. of Statistics, College Station, TX, 77840,
|
|
Keywords:
|
|
|
Abstract:
|
Our work is directed towards the analysis of aberrant crypt foci (ACF) in colon carcinogenesis. ACF are morphologically changed colonic crypts that are known to be precursors of colon cancer development. The colon is laid out as a gridded rectangle and the occurrence of an ACF within the grid is noted. The biological question of interest is whether these binary responses occur at random; if not, this suggests that the effect of environmental exposures is localized regionally. To understand the extent of the correlation, we cast the problem as a spatial binary regression with underlying Gaussian latent process. Marginal probabilities of ACF indicators are modeled semiparametrically, using fixed-knot penalized regression splines and single-index models. We modeled the underlying latent process in a nonstationary manner as the convolution of latent stationary processes. The dependency of the correlation function on location is also modeled semiparametrically. We fit the models using pairwise pseudo-likelihood methods. Assuming that the underlying latent process is strongly mixing, we proved asymptotic normality and derived the optimal rate of convergence for penalty parameters.
|
