Author:
Altman Micah,McDonald Michael P.
Abstract
Numerical issues matter in statistical analysis. Small errors occur when numbers are translated from paper and pencil into the binary world of computers. Surprisingly, these errors may be propagated and magnified through binary calculations, eventually producing statistical estimates far from the truth. In this replication and extension article, we look at one method of verifying the accuracy of statistical estimates by running these same data and models on multiple statistical packages. We find that for two published articles, Nagler (1994, American Journal of Political Science 38:230-255) and Alvarez and Brehm (1995, American Journal of Political Science 39:1055-1089), results are dependent on the statistical package used. In the course of our replications, we uncover other pitfalls that may prevent accurate replication, and make recommendations to ensure the ability for future researchers to replicate results.
Publisher
Cambridge University Press (CUP)
Subject
Political Science and International Relations,Sociology and Political Science
Reference12 articles.
1. American Ambivalence Towards Abortion Policy: Development of a Heteroskedastic Probit Model of Competing Values
2. Choosing Reliable Statistical Software;Altman;PS: Political Science and Politics,2001
3. Replication information and data for this article are available at the ICPSR publication archive as study #1113.
4. Nagler generously supplied the original Shazam code and data used in his analysis, as well as the original output.
Cited by
14 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
1. Odyssey: An Interactive Workbench for Expert-Driven Floating-Point Expression Rewriting;Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology;2023-10-29
2. Testing a constant mean function using functional regression;Neural Computing and Applications;2023-08-23
3. A Method to Audit the Assignment of Registered Voters to Districts and Precincts;Political Analysis;2020-01-17
4. Finding root causes of floating point error;ACM SIGPLAN Notices;2018-12-02
5. Finding root causes of floating point error;Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation;2018-06-11