In defense of comparative statics: Specifying empirical tests of models of strategic interaction

Clifford J. Carrubba, Amy Yuen, Christopher Jon Zorn

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Beginning in 1999, Curtis Signorino challenged the use of traditional logits and probits analysis for testing discrete-choice, strategic models. Signorino argues that the complex parametric relationships generated by even the simplest strategic models can lead to wildly inaccurate inferences if one applies these traditional approaches. In their stead, Signorino proposes generating stochastic formal models, from which one can directly derive a maximum likelihood estimator. We propose a simpler, alternative methodology for theoretically and empirically accounting for strategic behavior. In particular, we propose carefully and correctly deriving one's comparative statics from one's formal model, whether it is stochastic or deterministic does not particularly matter, and using standard logit or probit estimation techniques to test the predictions. We demonstrate that this approach performs almost identically to Signorino's more complex suggestion.

Original languageEnglish (US)
Pages (from-to)465-482
Number of pages18
JournalPolitical Analysis
Volume15
Issue number4
DOIs
StatePublished - Sep 1 2007

Fingerprint

interaction
estimation procedure
methodology

All Science Journal Classification (ASJC) codes

  • Sociology and Political Science
  • Political Science and International Relations

Cite this

@article{567d7a9dc76f4dc884ac70def7da88a0,
title = "In defense of comparative statics: Specifying empirical tests of models of strategic interaction",
abstract = "Beginning in 1999, Curtis Signorino challenged the use of traditional logits and probits analysis for testing discrete-choice, strategic models. Signorino argues that the complex parametric relationships generated by even the simplest strategic models can lead to wildly inaccurate inferences if one applies these traditional approaches. In their stead, Signorino proposes generating stochastic formal models, from which one can directly derive a maximum likelihood estimator. We propose a simpler, alternative methodology for theoretically and empirically accounting for strategic behavior. In particular, we propose carefully and correctly deriving one's comparative statics from one's formal model, whether it is stochastic or deterministic does not particularly matter, and using standard logit or probit estimation techniques to test the predictions. We demonstrate that this approach performs almost identically to Signorino's more complex suggestion.",
author = "Carrubba, {Clifford J.} and Amy Yuen and Zorn, {Christopher Jon}",
year = "2007",
month = "9",
day = "1",
doi = "10.1093/pan/mpm008",
language = "English (US)",
volume = "15",
pages = "465--482",
journal = "Political Analysis",
issn = "1047-1987",
publisher = "Oxford University Press",
number = "4",

}

In defense of comparative statics : Specifying empirical tests of models of strategic interaction. / Carrubba, Clifford J.; Yuen, Amy; Zorn, Christopher Jon.

In: Political Analysis, Vol. 15, No. 4, 01.09.2007, p. 465-482.

Research output: Contribution to journalArticle

TY - JOUR

T1 - In defense of comparative statics

T2 - Specifying empirical tests of models of strategic interaction

AU - Carrubba, Clifford J.

AU - Yuen, Amy

AU - Zorn, Christopher Jon

PY - 2007/9/1

Y1 - 2007/9/1

N2 - Beginning in 1999, Curtis Signorino challenged the use of traditional logits and probits analysis for testing discrete-choice, strategic models. Signorino argues that the complex parametric relationships generated by even the simplest strategic models can lead to wildly inaccurate inferences if one applies these traditional approaches. In their stead, Signorino proposes generating stochastic formal models, from which one can directly derive a maximum likelihood estimator. We propose a simpler, alternative methodology for theoretically and empirically accounting for strategic behavior. In particular, we propose carefully and correctly deriving one's comparative statics from one's formal model, whether it is stochastic or deterministic does not particularly matter, and using standard logit or probit estimation techniques to test the predictions. We demonstrate that this approach performs almost identically to Signorino's more complex suggestion.

AB - Beginning in 1999, Curtis Signorino challenged the use of traditional logits and probits analysis for testing discrete-choice, strategic models. Signorino argues that the complex parametric relationships generated by even the simplest strategic models can lead to wildly inaccurate inferences if one applies these traditional approaches. In their stead, Signorino proposes generating stochastic formal models, from which one can directly derive a maximum likelihood estimator. We propose a simpler, alternative methodology for theoretically and empirically accounting for strategic behavior. In particular, we propose carefully and correctly deriving one's comparative statics from one's formal model, whether it is stochastic or deterministic does not particularly matter, and using standard logit or probit estimation techniques to test the predictions. We demonstrate that this approach performs almost identically to Signorino's more complex suggestion.

UR - http://www.scopus.com/inward/record.url?scp=35648959729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35648959729&partnerID=8YFLogxK

U2 - 10.1093/pan/mpm008

DO - 10.1093/pan/mpm008

M3 - Article

AN - SCOPUS:35648959729

VL - 15

SP - 465

EP - 482

JO - Political Analysis

JF - Political Analysis

SN - 1047-1987

IS - 4

ER -