While the theoretical importance of a distributional perspective has long between established in epidemiology, a critical gap in the field has been finding methodological approaches to empirically engage with the distributional perspective. The Kolmogorov-Smirnov test statistic tests whether overall differences between two distributions may be considered significant, but cannot identify the degree to which a given risk factor may explain these differences. Quantile regression provides estimates of how risk factors may alter an outcome within each quantile of the population distribution of a disease risk factor, but requires parametric assumptions difficult to uphold for many empirical distributions. Here we introduce a nonparametric decomposition technique, which identifies how changes in modifiable risk factors for the outcome variable could reduce disparities at different points along the distribution of an outcome variable.
For complete derivation, see:
Using Decomposition Analysis to Identify Modifiable Racial Disparities in the Distribution of Blood Pressure in the United States
American Journal of Epidemiology, Volume 182, Issue 4, 15 August 2015, Pages 345–353, https://doi.org/10.1093/aje/kwv079
Sanjay Basu*, Anthony Hong, Arjumand Siddiqi