Population choice and variable selection in the estimation and applicationof risk models

This paper shows that risk adjustment models based on demographic and emplo yment variables are not easily transferable from one population to the next , and that administrative variables are not useful in predicting medical ex penditures. We found statistically significant differences between models b uilt on populations of employees from a single employer enrolled in two dif ferent health plans, and between models built on populations of enrollees f rom a single health plan employed at two different companies. Employment-ba sed variables (e.g., length of employment) had little predictive power in a ny of these risk models. We conclude that policymakers should be careful in applying risk models across populations and that future versions of risk m odels for use within large employers need not include employment-based vari ables.