Background: Profile instruments are frequently used to assess health-related quality of life and other patient-reported outcomes. However, preference-based measures are required for health-economic cost-utility evaluations.
Results: Although regression-based approaches are commonly used to map from profile measures to preference measures, we show that this results in biased estimates because of regression to the mean.
Conclusions: Linking (scale-aligning) is proposed as an alternative.
Keywords: linking values; mapping functions; patient-reported outcomes; preference-based measures; profile instruments; scale-aligning; test equating.
Copyright © 2014 International Society for Pharmacoeconomics and Outcomes Research (ISPOR). Published by Elsevier Inc. All rights reserved.