Separation and Rare Events

Cite This

Files in this item

Checksum: MD5:a1d1159a1cf8b7b6f2f386a05ed59349

BEISER-MCGRATH, Liam F., 2022. Separation and Rare Events. In: Political Science Research and Methods. Cambridge University Press. 10(2), pp. 428-437. ISSN 2049-8470. eISSN 2049-8489. Available under: doi: 10.1017/psrm.2020.46

@article{BeiserMcGrath2022Separ-57342, title={Separation and Rare Events}, year={2022}, doi={10.1017/psrm.2020.46}, number={2}, volume={10}, issn={2049-8470}, journal={Political Science Research and Methods}, pages={428--437}, author={Beiser-McGrath, Liam F.} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dc:date rdf:datatype="">2022-04-22T10:30:17Z</dc:date> <dcterms:abstract xml:lang="eng">When separation is a problem in binary dependent variable models, many researchers use Firth's penalized maximum likelihood in order to obtain finite estimates (Firth, 1993; Zorn, 2005; Rainey, 2016). In this paper, I show that this approach can lead to inferences in the opposite direction of the separation when the number of observations are sufficiently large and both the dependent and independent variables are rare events. As large datasets with rare events are frequently used in political science, such as dyadic data measuring interstate relations, a lack of awareness of this problem may lead to inferential issues. Simulations and an empirical illustration show that the use of independent “weakly-informative” prior distributions centered at zero, for example, the Cauchy prior suggested by Gelman et al. (2008), can avoid this issue. More generally, the results caution researchers to be aware of how the choice of prior interacts with the structure of their data, when estimating models in the presence of separation.</dcterms:abstract> <dcterms:hasPart rdf:resource=""/> <dc:contributor>Beiser-McGrath, Liam F.</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:issued>2022</dcterms:issued> <bibo:uri rdf:resource=""/> <dcterms:rights rdf:resource=""/> <dc:rights>Attribution-NonCommercial-ShareAlike 4.0 International</dc:rights> <dcterms:title>Separation and Rare Events</dcterms:title> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dspace:isPartOfCollection rdf:resource=""/> <dc:language>eng</dc:language> <dcterms:available rdf:datatype="">2022-04-22T10:30:17Z</dcterms:available> <dc:creator>Beiser-McGrath, Liam F.</dc:creator> <dcterms:isPartOf rdf:resource=""/> <dspace:hasBitstream rdf:resource=""/> </rdf:Description> </rdf:RDF>

Downloads since Apr 22, 2022 (Information about access statistics)

Beiser-McGrath_2-xoos3thk4kg10.pdf 20

This item appears in the following Collection(s)

Attribution-NonCommercial-ShareAlike 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International

Search KOPS


My Account