Handling resolvable uncertainty from incomplete scenarios in future doctors' job choice – Probabilities vs discrete choices. (March 2020)

• Record Type: Journal Article
• Authors: Pedersen, Line Bjørnskov; Mørkbak, Morten Raun; Scarpa, Riccardo
• Is Part Of: Journal of choice modelling. Volume 34(2020)
• Publication Date: 2020-03
• Subjects: Discrete choice experiments -- Elicited choice probabilities -- Resolvable uncertainty -- Rural general practice; C31 -- C35 -- I11; Decision making -- Periodicals; Social choice -- Periodicals; Decision making; Social choice; Periodicals; 302.13
• DOI: 10.1016/j.jocm.2019.100199
• Languages: English
• ISSNs: 1755-5345

Abstract

Abstract: Health economists often use discrete choice experiments (DCEs) to predict behavior, as actual market data is often unavailable. Manski (1990) argues that due to the incompleteness of the hypothetical scenarios used in DCEs, substantial uncertainty surrounds stated choice. Uncertainty can be decomposed into "resolvable" and "unresolvable"; the former is expected to become resolved in actual choice, as individuals collect further information. To enable its identification, Manski suggests eliciting subjective choice probabilities (ECPs) rather than discrete choices. We introduce the ECP approach in health economics and explore its convergent validity. The context is future physicians' stated choices of job in rural general practice in Denmark. Our results are mixed, but show remarkable similarities in forecasting abilities, despite the ECP models being less econometrically demanding and relying on different preference distributional assumptions. Highlights: The elicited choice probability (ECP) approach is introduced to health economics. The validity of the ECP approach is tested against the discrete choice approach. Results are mixed. However, we find remarkable similarities in forecasting abilities for the two approaches. The ECP approach is less econometrically demanding.