Bayesian Approaches for Limited Dependent Variable Change Point Problems

Author:

Spirling Arthur

Abstract

Limited dependent variable (LDV) data are common in political science, and political methodologists have given much good advice on dealing with them. We review some methods for LDV “change point problems” and demonstrate the use of Bayesian approaches for count, binary, and duration-type data. Our applications are drawn from American politics, Comparative politics, and International Political Economy. We discuss the tradeoffs both philosophically and computationally. We conclude with possibilities for multiple change point work.

Publisher

Cambridge University Press (CUP)

Subject

Political Science and International Relations,Sociology and Political Science

Reference47 articles.

1. The change point posterior density is degenerate for period 49; hence, the posterior odds ratio for no change is zero.

2. The posterior odds ratio for no change is zero: there is no mass at k = T.

3. In general, the chains showed good mixing, and posteriors were (relatively) smooth and unimodal. Convergence assessed using Geweke (1992) and Raftery and Lewis (1995) diagnostics.

4. If the researcher has a sufficiently sharp theory and the requisite data to hand, there is no theoretical bar to utilizing covariates. In the King et al. (1990) data itself, the record for France does not include the Fifth Republic.

5. All posteriors were (relatively) smooth and unimodal. Convergence of the change point parameter assessed using Geweke (1992) and Raftery and Lewis (1995) diagnostics. Convergence for the coefficient estimates was less easily obtained, but varying the priors somewhat resulted in very similar posterior findings.

Cited by 29 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3