Health disparities are abundantly recorded in literature, but is much less
understood within a rural-urban context. In this paper, four major diseases in Virginia
are studied: cancer, stroke, cardiovascular disease (heart disease) and chronic
obstructive pulmonary disease (COPD). Separate count data regressions are estimated
at regional level to provide a primary understanding of those factors. A simultaneous
equations model with rural-urban specification are then estimated via seemingly
unrelated regression (SUR) techniques to take account of possible causalities among
these diseases as well as error correlations, which is followed by Blinder-Oaxaca
decomposition of the disparity proportions explained by observed characteristics and
unobserved mechanisms. The results suggest that regional-level factors are
significantly correlated with health disparities between rural and urban areas. The
unknown mechanisms behind these linkages are different between rural and urban
areas, and explain an even larger proportion of these disparities.
