| 概要 |
We study identification of dynamic discrete choice models with hyperbolic discounting.
We show that the standard discount factor, present bias factor, and the perceived conditional choice probabilities for the sophisticated agent are point-identified in a finite horizon model. The main idea to achieve identification is to exploit variation of the observed conditional choice probabilities over time. We also show that, if the data have an additional state variable, the identification result is still valid with less severe requirements for the number of time periods in the data.
|