Taste or Scale? Methodological Approach to Health Preferences Comparison across Groups

Area of Science:

• Health economics
• Behavioral economics
• Health services research

Background:

• Discrete choice experiments (DCEs) are widely used to assess health preferences across subgroups.
• Observed utility differences may stem from variations in decision consistency rather than true preference differences.
• Methodological transparency in accounting for unobserved heterogeneity in DCEs is lacking, necessitating robust approaches for credible subgroup comparisons.

Purpose of the Study:

• To improve health preference research methods by directly addressing scale heterogeneity in DCEs.
• To reduce bias when comparing subgroups in health preference research.
• To distinguish between scale heterogeneity and true preference differences across groups.

Main Methods:

• A simulated discrete choice experiment (DCE) evaluated hypothetical cancer treatments for patients and caregivers.
• Mixed logit models were estimated, with scale heterogeneity addressed using the Swait-Louviere 2-step procedure.
• Willingness to pay (WTP) was computed and compared across groups using a simulation-based test.

Main Results:

• The Swait-Louviere test confirmed significant scale heterogeneity but no meaningful taste differences between groups.
• After accounting for scale effects, a shared preference structure was observed, with variability driven by decision inconsistency.
• No statistically significant between-group differences in willingness to pay (WTP) were found, indicating no meaningful subgroup contrasts.

Conclusions:

• Adjusting for scale heterogeneity enhances DCE validity by reducing bias and enabling accurate subgroup comparisons.
• The study demonstrated that heterogeneity often reflects scale rather than true preference differences, with negligible WTP gaps.
• Routine scale diagnostics and preference tests under equalized scale are recommended for valid inference in stated-preference research.