Pooling data across markets in dynamic Markov games

Taisuke Otsu, Martin Pesendorfer, Yuya Takahashi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This paper proposes several statistical tests for finite state Markov games to examine whether data from distinct markets can be pooled. We formulate homogeneity tests of (i) the conditional choice and state transition probabilities, (ii) the steady-state distribution, and (iii) the conditional state distribution given an initial state. The null hypotheses of these homogeneity tests are necessary conditions (or maintained assumptions) for poolability of the data. Thus rejections of these null imply that the data cannot be pooled across markets. Acceptances of these null are considered as supporting evidences for the maintained assumptions of estimation using pooled data. In a Monte Carlo study we find that the test based on the steady-state distribution performs well and has high power even with small numbers of markets and time periods. We apply the tests to the empirical study of Ryan (2012) that analyzes dynamics of the U.S. Portland cement industry and assess if the data across markets can be pooled.

Original languageEnglish
Pages (from-to)523-559
Number of pages37
JournalQuantitative Economics
Volume7
Issue number2
DOIs
Publication statusPublished - 2016 Jul 1
Externally publishedYes

Fingerprint

Market data
Pooling
Homogeneity
Poolability
Transition probability
Acceptance
Statistical tests
Empirical study
Monte Carlo study
Cement industry

Keywords

  • Dynamic Markov game
  • hypothesis testing
  • multiplicity of equilibria
  • poolability

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Pooling data across markets in dynamic Markov games. / Otsu, Taisuke; Pesendorfer, Martin; Takahashi, Yuya.

In: Quantitative Economics, Vol. 7, No. 2, 01.07.2016, p. 523-559.

Research output: Contribution to journalArticle

Otsu, Taisuke ; Pesendorfer, Martin ; Takahashi, Yuya. / Pooling data across markets in dynamic Markov games. In: Quantitative Economics. 2016 ; Vol. 7, No. 2. pp. 523-559.
@article{e841eb380ef74b489cc32594891ef266,
title = "Pooling data across markets in dynamic Markov games",
abstract = "This paper proposes several statistical tests for finite state Markov games to examine whether data from distinct markets can be pooled. We formulate homogeneity tests of (i) the conditional choice and state transition probabilities, (ii) the steady-state distribution, and (iii) the conditional state distribution given an initial state. The null hypotheses of these homogeneity tests are necessary conditions (or maintained assumptions) for poolability of the data. Thus rejections of these null imply that the data cannot be pooled across markets. Acceptances of these null are considered as supporting evidences for the maintained assumptions of estimation using pooled data. In a Monte Carlo study we find that the test based on the steady-state distribution performs well and has high power even with small numbers of markets and time periods. We apply the tests to the empirical study of Ryan (2012) that analyzes dynamics of the U.S. Portland cement industry and assess if the data across markets can be pooled.",
keywords = "Dynamic Markov game, hypothesis testing, multiplicity of equilibria, poolability",
author = "Taisuke Otsu and Martin Pesendorfer and Yuya Takahashi",
year = "2016",
month = "7",
day = "1",
doi = "10.3982/QE612",
language = "English",
volume = "7",
pages = "523--559",
journal = "Quantitative Economics",
issn = "1759-7323",
publisher = "The Economic Society",
number = "2",

}

TY - JOUR

T1 - Pooling data across markets in dynamic Markov games

AU - Otsu, Taisuke

AU - Pesendorfer, Martin

AU - Takahashi, Yuya

PY - 2016/7/1

Y1 - 2016/7/1

N2 - This paper proposes several statistical tests for finite state Markov games to examine whether data from distinct markets can be pooled. We formulate homogeneity tests of (i) the conditional choice and state transition probabilities, (ii) the steady-state distribution, and (iii) the conditional state distribution given an initial state. The null hypotheses of these homogeneity tests are necessary conditions (or maintained assumptions) for poolability of the data. Thus rejections of these null imply that the data cannot be pooled across markets. Acceptances of these null are considered as supporting evidences for the maintained assumptions of estimation using pooled data. In a Monte Carlo study we find that the test based on the steady-state distribution performs well and has high power even with small numbers of markets and time periods. We apply the tests to the empirical study of Ryan (2012) that analyzes dynamics of the U.S. Portland cement industry and assess if the data across markets can be pooled.

AB - This paper proposes several statistical tests for finite state Markov games to examine whether data from distinct markets can be pooled. We formulate homogeneity tests of (i) the conditional choice and state transition probabilities, (ii) the steady-state distribution, and (iii) the conditional state distribution given an initial state. The null hypotheses of these homogeneity tests are necessary conditions (or maintained assumptions) for poolability of the data. Thus rejections of these null imply that the data cannot be pooled across markets. Acceptances of these null are considered as supporting evidences for the maintained assumptions of estimation using pooled data. In a Monte Carlo study we find that the test based on the steady-state distribution performs well and has high power even with small numbers of markets and time periods. We apply the tests to the empirical study of Ryan (2012) that analyzes dynamics of the U.S. Portland cement industry and assess if the data across markets can be pooled.

KW - Dynamic Markov game

KW - hypothesis testing

KW - multiplicity of equilibria

KW - poolability

UR - http://www.scopus.com/inward/record.url?scp=84978636475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978636475&partnerID=8YFLogxK

U2 - 10.3982/QE612

DO - 10.3982/QE612

M3 - Article

AN - SCOPUS:84978636475

VL - 7

SP - 523

EP - 559

JO - Quantitative Economics

JF - Quantitative Economics

SN - 1759-7323

IS - 2

ER -