A Bayesian approach to estimation of dynamic models with small and large number of heterogeneous players and latent serially correlated states

A. Ronald Gallant, Han Hong, Ahmed Khwaja

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We propose a Bayesian approach to estimating dynamic models that can have state variables that are latent, serially correlated, and heterogeneous. Our approach employs sequential importance sampling and is based on deriving an unbiased estimate of the likelihood within a Metropolis chain. Under fairly weak regularity conditions unbiasedness guarantees that the stationary density of the chain is the exact posterior, not an approximation. Results are verified by Monte Carlo simulation using two examples. The first is a dynamic game of entry involving a small number of firms whose heterogeneity is based on their current costs due to feedback through capacity constraints arising from past entry. The second is an Ericson and Pakes (1995) style game with a large number of firms whose heterogeneity is based on the quality of their products with firms competing through investment in product quality that affects their market share and profitability. Our approach facilitates estimation of dynamic games with either small or large number of players whose heterogeneity is determined by latent state variables, discrete or continuous, that are subject to endogenous feedback from past actions.

Original languageEnglish (US)
Pages (from-to)19-32
Number of pages14
JournalJournal of Econometrics
Volume203
Issue number1
DOIs
StatePublished - Mar 2018

Fingerprint

State variable
Dynamic games
Bayesian approach
Firm heterogeneity
Product quality
Capacity constraints
Costs
Importance sampling
Profitability
Regularity
Guarantee
Monte Carlo simulation
Market share
Unbiasedness
Approximation

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

@article{d5a1e7ba34d44064b339cdc905d6dc02,
title = "A Bayesian approach to estimation of dynamic models with small and large number of heterogeneous players and latent serially correlated states",
abstract = "We propose a Bayesian approach to estimating dynamic models that can have state variables that are latent, serially correlated, and heterogeneous. Our approach employs sequential importance sampling and is based on deriving an unbiased estimate of the likelihood within a Metropolis chain. Under fairly weak regularity conditions unbiasedness guarantees that the stationary density of the chain is the exact posterior, not an approximation. Results are verified by Monte Carlo simulation using two examples. The first is a dynamic game of entry involving a small number of firms whose heterogeneity is based on their current costs due to feedback through capacity constraints arising from past entry. The second is an Ericson and Pakes (1995) style game with a large number of firms whose heterogeneity is based on the quality of their products with firms competing through investment in product quality that affects their market share and profitability. Our approach facilitates estimation of dynamic games with either small or large number of players whose heterogeneity is determined by latent state variables, discrete or continuous, that are subject to endogenous feedback from past actions.",
author = "Gallant, {A. Ronald} and Han Hong and Ahmed Khwaja",
year = "2018",
month = "3",
doi = "10.1016/j.jeconom.2017.04.004",
language = "English (US)",
volume = "203",
pages = "19--32",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

A Bayesian approach to estimation of dynamic models with small and large number of heterogeneous players and latent serially correlated states. / Gallant, A. Ronald; Hong, Han; Khwaja, Ahmed.

In: Journal of Econometrics, Vol. 203, No. 1, 03.2018, p. 19-32.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Bayesian approach to estimation of dynamic models with small and large number of heterogeneous players and latent serially correlated states

AU - Gallant, A. Ronald

AU - Hong, Han

AU - Khwaja, Ahmed

PY - 2018/3

Y1 - 2018/3

N2 - We propose a Bayesian approach to estimating dynamic models that can have state variables that are latent, serially correlated, and heterogeneous. Our approach employs sequential importance sampling and is based on deriving an unbiased estimate of the likelihood within a Metropolis chain. Under fairly weak regularity conditions unbiasedness guarantees that the stationary density of the chain is the exact posterior, not an approximation. Results are verified by Monte Carlo simulation using two examples. The first is a dynamic game of entry involving a small number of firms whose heterogeneity is based on their current costs due to feedback through capacity constraints arising from past entry. The second is an Ericson and Pakes (1995) style game with a large number of firms whose heterogeneity is based on the quality of their products with firms competing through investment in product quality that affects their market share and profitability. Our approach facilitates estimation of dynamic games with either small or large number of players whose heterogeneity is determined by latent state variables, discrete or continuous, that are subject to endogenous feedback from past actions.

AB - We propose a Bayesian approach to estimating dynamic models that can have state variables that are latent, serially correlated, and heterogeneous. Our approach employs sequential importance sampling and is based on deriving an unbiased estimate of the likelihood within a Metropolis chain. Under fairly weak regularity conditions unbiasedness guarantees that the stationary density of the chain is the exact posterior, not an approximation. Results are verified by Monte Carlo simulation using two examples. The first is a dynamic game of entry involving a small number of firms whose heterogeneity is based on their current costs due to feedback through capacity constraints arising from past entry. The second is an Ericson and Pakes (1995) style game with a large number of firms whose heterogeneity is based on the quality of their products with firms competing through investment in product quality that affects their market share and profitability. Our approach facilitates estimation of dynamic games with either small or large number of players whose heterogeneity is determined by latent state variables, discrete or continuous, that are subject to endogenous feedback from past actions.

UR - http://www.scopus.com/inward/record.url?scp=85040345084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040345084&partnerID=8YFLogxK

U2 - 10.1016/j.jeconom.2017.04.004

DO - 10.1016/j.jeconom.2017.04.004

M3 - Article

AN - SCOPUS:85040345084

VL - 203

SP - 19

EP - 32

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -