Experimental guidance for eliciting beliefs with the Stochastic Becker-DeGroot-Marschak mechanism
AuthorBurfurd, I; Wilkening, T
Source TitleJOURNAL OF THE ECONOMIC SCIENCE ASSOCIATION-JESA
University of Melbourne Author/sWilkening, Tom
Document TypeJournal Article
CitationsBurfurd, I; Wilkening, T, Experimental guidance for eliciting beliefs with the Stochastic Becker-DeGroot-Marschak mechanism, JOURNAL OF THE ECONOMIC SCIENCE ASSOCIATION-JESA, 2018, 4 (1), pp. 15 - 28
Access StatusOpen Access
We compare different implementations of the Stochastic Becker–DeGroot–Marschak (SBDM) belief elicitation mechanism, which is theoretically elegant but challenging to implement. In a first experiment, we compare three common formats of the mechanism in terms of speed and data quality. We find that all formats yield reports with similar levels of accuracy and precision, but that the instructions and reporting format adapted from Hao and Houser (J Risk Uncertain 44(2):161–180 2012) is significantly faster to implement. We use this format in a second experiment in which we vary the delivery method and quiz procedure. Dropping the pre-experiment quiz significantly compromises the accuracy of subject’s reports and leads to a dramatic spike in boundary reports. However, switching between electronic and paper-based instructions and quizzes does not affect the accuracy or precision of subjects’ reports.
- Click on "Export Reference in RIS Format" and choose "open with... Endnote".
- Click on "Export Reference in RIS Format". Login to Refworks, go to References => Import References