Title :
A Survey of Estimations of Dynamic Discrete Choice Models
Author :
Lei, Wang Zhen ; Song, Qin
Author_Institution :
Stat. Sch., Zhejiang Gongshang Univ., Ningbo, China
Abstract :
The DDCM is a dynamic program (DP) with discrete controls, which is very important in understanding agents´ behavior in various settings. This paper begins with the essential features and hypothesis. On the one hand, to estimate the model with two sources of heterogeneity when the number of periods is small, it obtains non-linear bias corrected estimator (NBC) and minimized integrated mean square error (MIMSE). On the other hand, “Curse of Dimensionality” makes the estimation of the dynamic model infeasible even in a relatively simple setting, it proposes Bayesian estimation, Bayesian-MCMC-DP estimation and MCMC-ANN etc.
Keywords :
decision theory; dynamic programming; economics; nonlinear estimation; ANN; Bayesian-MCMC-DP estimation; dimensionality curse; discrete controls; dynamic discrete choice models; dynamic program; minimised integrated mean square error estimation; nonlinear bias corrected estimator; Bayesian methods; Econometrics; Educational institutions; Industrial engineering; Mean square error methods; Microeconomics; Niobium compounds; Retirement; Security; State estimation; Curse of dimensionality; DDCM; Small sample heterogeneity; Structural estimation;
Conference_Titel :
Computing, Control and Industrial Engineering (CCIE), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-4026-9
DOI :
10.1109/CCIE.2010.132