CaltechAUTHORS
  A Caltech Library Service

Estimating Signaling Games in International Relations: Problems and Solutions

Crisman-Cox, Casey and Gibilisco, Michael (2017) Estimating Signaling Games in International Relations: Problems and Solutions. . (Unpublished) http://resolver.caltech.edu/CaltechAUTHORS:20180124-083209026

[img] PDF - Submitted Version
See Usage Policy.

796Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180124-083209026

Abstract

Signaling games are central to the study of politics but often have multiple equilibria, leading to no definitive empirical prediction. We demonstrate that these indeterminacies create substantial problems for currently used maximum likelihood techniques: they fail to uncover the parameters of the canonical crisis-signaling game, regardless of sample size, even if the equilibrium in the game generating the data is unique. To overcome this problem, we propose three estimators that outperform current best practices and are well suited to problems in international relations. We fit a signaling model to data on economic sanctions and find that standard maximum likelihood produces unintuitive estimates that are highly sensitive to modeling or software choices. Our solutions remedy the problems and uncover a novel U-shaped relationship between audience costs and the propensity for leaders to threaten sanctions.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://michaelgibilisco.com/papers/signalmultieq.pdfAuthorDiscussion Paper
Record Number:CaltechAUTHORS:20180124-083209026
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180124-083209026
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:84491
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:31 Jan 2018 19:08
Last Modified:31 Jan 2018 19:08

Repository Staff Only: item control page