Title: Long-term average utility in dynamic discrete choice models
Abstract: Dynamic discrete choice models threats forward looking agents that seeks to maximize the expected long-term discounted utility of their choices in an uncertain environment. In most applications, it has been impossible to estimate the discount factor, and in some applications the model fit has improved as the discount factor approaches one, indicating that the decision makers might act as if they maximized long-term average rather than discounted utility. We will in this work show how dynamic discrete choice theory can be extended to cover this special case. We will apply the new methods to the bus engine replacement problem discussed in Rust (1987) and to a model of car ownership, to test whether the long-term average utility specification better expalins the observations.
Publication Year: 2015
Publication Date: 2015-05-18
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot