BACKGROUND: Reliably mapping from generic or disease-specific health status measures into health state utilities would assist health economists. Existing studies mainly use ordinary least squares (OLS) regression equations to predict utility values for particular health states. The authors examine an alternative approach to map between 2 generic health status instruments, the SF-12 and the EQ-5D. METHODS: Multinomial logit regression is used to estimate the probability that a respondent will select a particular level of response to questions in the EQ-5D, using individual question responses and summary scores from the SF-12 as predictors. Monte Carlo simulation methods are used to generate predicted EQ-5D responses, and utility scores (tariffs) are then attached. Results are compared with an alternative approach based on direct mapping to utility scores using OLS. DATA: The authors estimate equations using 12,967 adult survey responses-from the 2000 US Medical Expenditure Panel Survey. They report mean squared error (MSE) and mean absolute error (MAE) of their predicted utilities within this sample, and out-of-sample using 13,304 adults from the 1996 Health Survey for England. RESULTS: The authors obtain an in-sample and out-of-sample MSE of 0.03, compared with 0.02 for the OLS approach. Their MAE of 0.11 is similar to OLS results. The authors' method predicts group mean utility scores and differentiates between groups with or without known existing illness. CONCLUSIONS: The authors' approach has higher MSE than the direct OLS approach but gives more descriptive data on domains of health effects. Further out of sample prediction work will help test the validity of these methods.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below