Maximum Likelihood Estimation of Latent Variable Models by SMC with Marginalization and Data Cloning

24 Pages Posted: 27 Sep 2017

See all articles by Jin-Chuan Duan

Jin-Chuan Duan

National University of Singapore (NUS) - Business School and Risk Management Institute

Andras Fulop

ESSEC Business School

Yu-Wei Hsieh

Amazon

Multiple version iconThere are 2 versions of this paper

Date Written: August 24, 2017

Abstract

A data-cloning SMC² method is proposed as a general purpose optimization routine for estimating latent variable models by maximum likelihood. The latent variables are first marginalized out by SMC at any fixed parameter value, and the model parameters are then estimated by density tempered SMC. The data-cloning step is employed to efficiently reduce Monte Carlo errors inherent in the SMC² algorithm and also to effectively address multi-modality present in typical objective functions. This new method has wide applicability and can be massively parallelized to take advantage of typical computers today.

Keywords: Sequential Monte Carlo, Data Clone, Latent Variable, Maximum Likelihood, Monte Carlo Optimization

JEL Classification: C15, C63

Suggested Citation

Duan, Jin-Chuan and Fulop, Andras and Hsieh, Yu-Wei, Maximum Likelihood Estimation of Latent Variable Models by SMC with Marginalization and Data Cloning (August 24, 2017). USC-INET Research Paper No. 17-27, Available at SSRN: https://ssrn.com/abstract=3043426 or http://dx.doi.org/10.2139/ssrn.3043426

Jin-Chuan Duan (Contact Author)

National University of Singapore (NUS) - Business School and Risk Management Institute ( email )

1 Business Link
Singapore, 117592
Singapore

Andras Fulop

ESSEC Business School ( email )

3 Avenue Bernard Hirsch
CS 50105 CERGY
CERGY, CERGY PONTOISE CEDEX 95021
France

Yu-Wei Hsieh

Amazon ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
64
Abstract Views
514
Rank
622,763
PlumX Metrics