Abstract
The newsvendor problem is an economic decision problem with an interesting degree of complexity while still providing a quite simple and intuitive normative solution. Therefore, one should expect that decision makers find the optimal solution at least when they learn over time and become familiar with the problem. However, this is not the case. On average, decision makers in newsvendor settings tend to order too little when confronted with high-profit goods and too much in the case of low-profit goods. This inefficiency is well documented through a variety of laboratory experiments assuming symmetric demand functions and is known as pull-to-mean effect. We analyze data from an experiment that is based on an asymmetric demand function and are able to discriminate among the possible focal points, namely, mean demand, median demand, and the middle of possible demand. Interestingly, the result is not a pure pull-to-mean effect. We show that the adaptive learning model is able to better explain the ordering behavior than the models of anchoring and insufficient adjustment, demand chasing, the regretting newsvendor, reference dependence, or bounded rationality not only on the aggregate but also on the individual level. In particular, we find out that the top ranking of the adaptive learning model is not the result of mixing individual behavior according to the explanatory models with less parameters. Furthermore, we are able to improve the explanatory and predictive power of the adaptive learning model by modifying the demand indicator that is used.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.