Spatially-explicit survival modeling with discrete grouping of cancer predictors

Georgiana Onicescu; Andrew B Lawson; Jiajia Zhang; Mulugeta Gebregziabher; Kristin Wallace; Jan M Eberth

doi:10.1016/j.sste.2018.06.001

Spatially-explicit survival modeling with discrete grouping of cancer predictors

Spat Spatiotemporal Epidemiol. 2019 Jun:29:139-148. doi: 10.1016/j.sste.2018.06.001. Epub 2018 Jun 21.

Authors

Georgiana Onicescu¹, Andrew B Lawson², Jiajia Zhang³, Mulugeta Gebregziabher², Kristin Wallace², Jan M Eberth³

Affiliations

¹ Department of Statistics, Western Michigan University, Kalamazoo, MI, United States. Electronic address: [email protected].
² Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, United States.
³ Department of Epidemiology and Biostatistics, Arnold School of Public Health, University of South Carolina, Columbia, SC, United States.

Abstract

In this paper, the spatially explicit survival model is extended by allowing the relation with the explanatory covariates to be spatially adaptive using a threshold conditional autoregressive (CAR) model, further extended to allow the inclusion of multiple threshold levels. The model is applied to prostate cancer survival based on Louisiana SEER registry, which holds individual records linked to vital outcomes and is geocoded at the parish level.

Keywords: Bayesian; Latent; Prostate cancer; Spatial.

Publication types

Research Support, N.I.H., Extramural

MeSH terms

Adult
Aged
Aged, 80 and over
Demography
Humans
Louisiana / epidemiology
Male
Middle Aged
Models, Statistical
Prostatic Neoplasms / epidemiology*
Prostatic Neoplasms / mortality
Registries
SEER Program
Spatial Analysis
Survival Analysis

Grants and funding

R03 CA176702/CA/NCI NIH HHS/United States