An examination of disparities in cancer incidence in Texas using Bayesian random coefficient models

Abstract

Disparities in cancer risk exist between ethnic groups in the United States. These disparities often result from differential access to healthcare, differences in socioeconomic status and differential exposure to carcinogens. This study uses cancer incidence data from the population based Texas Cancer Registry to investigate the disparities in digestive and respiratory cancers from 2000 to 2008. A Bayesian hierarchical regression approach is used. All models are fit using the INLA method of Bayesian model estimation. Specifically, a spatially varying coefficient model of the disparity between Hispanic and Non-Hispanic incidence is used. Results suggest that a spatio-temporal heterogeneity model best accounts for the observed Hispanic disparity in cancer risk. Overall, there is a significant disadvantage for the Hispanic population of Texas with respect to both of these cancers, and this disparity varies significantly over space. The greatest disparities between Hispanics and Non-Hispanics in digestive and respiratory cancers occur in eastern Texas, with patterns emerging as early as 2000 and continuing until 2008.

Keywords: Bayesian modeling; Cancer incidence; Health disparities; INLA.

Figure 1. Hispanic relative risk from Models 2 and 3.

Figure 2. Hispanic fitted SIR from 2000 to 2008—digestive cancers.

Figure 3. Hispanic fitted SIR from 2000 to 2008—respiratory cancers.

Figure 4. Exceedence probabilities for digestive cancer clusters.

Figure 5. Exceedence probabilities for digestive respiratory clusters.

Figure 6. Marginal densities for model hyperparameters.