Estimation of Discrete Choice Dynamic Programming Models

IF 1.5 4区经济学 Q2 ECONOMICS

Japanese Economic Review Pub Date : 2017-12-01 DOI:10.1111/jere.12169

Hiroyuki Kasahara, Katsumi Shimotsu

引用次数: 5

Abstract

This study reviews estimation methods for the infinite horizon discrete choice dynamic programming models and conducts Monte Carlo experiments. We consider: the maximum likelihood estimator (MLE), the two-step conditional choice probabilities estimator, sequential estimators based on policy iterations mapping under finite dependence, and sequential estimators based on value iteration mappings. Our simulation result shows that the estimation performance of the sequential estimators based on policy iterations and value iteration mappings is largely comparable to the MLE, while they achieve substantial computation gains over the MLE by a factor of 100 for a model with a moderately large state space.

查看原文本刊更多论文

离散选择动态规划模型的估计

本文综述了无限视界离散选择动态规划模型的估计方法，并进行了蒙特卡罗实验。我们考虑了极大似然估计量(MLE)、两步条件选择概率估计量、有限依赖下基于策略迭代映射的序列估计量和基于值迭代映射的序列估计量。我们的仿真结果表明，基于策略迭代和值迭代映射的序列估计器的估计性能在很大程度上与MLE相当，而对于具有中等大小状态空间的模型，它们比MLE获得了100倍的计算增益。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Japanese Economic Review ECONOMICS-

CiteScore

2.70

自引率

0.00%

发文量

期刊介绍： Started in 1950 by a group of leading Japanese economists under the title The Economic Studies Quarterly, the journal became the official publication of the Japanese Economic Association in 1959. As its successor, The Japanese Economic Review has become the Japanese counterpart of The American Economic Review, publishing substantial economic analysis of the highest quality across the whole field of economics from researchers both within and outside Japan. It also welcomes innovative and thought-provoking contributions with strong relevance to real economic issues, whether political, theoretical or policy-oriented.