Validating the Use of Vignettes for Subjective Threshold Scales
Arthur van Soest, Liam Delaney, Colm P. Harmon, Arie Kapteyn, James P. Smith
published in: Journal of the Royal Statistical Society, Series A (Statistics in Society), 2011, 174 (3), 575-595
Comparing self-assessed indicators of subjective outcomes such as health, work disability, political efficacy, job satisfaction, etc. across countries or socio-economic groups is often hampered by the fact that different groups use systematically different response scales. Anchoring vignettes have been introduced as an effective tool to correct for such differences. This paper develops an integrated framework in which objective measurements are used to validate the vignette-based corrections. The framework is applied to vignettes and objective and subjective self-assessments of drinking behavior by students in Ireland. Model comparisons using the Akaike information criterion favor a specification with response consistency and vignette corrected response scales. Put differently, vignette based corrections appear quite effective in bringing objective and subjective measures closer together.
Text: See Discussion Paper No. 2860