Randomization Does Not Justify Logistic Regression

dc.creatorFreedman, David A.
dc.date2008-08-28
dc.date.accessioned2026-07-07T09:59:07Z
dc.date.available2026-07-07T09:59:07Z
dc.descriptionThe logit model is often used to analyze experimental data. However, randomization does not justify the model, so the usual estimators can be inconsistent. A consistent estimator is proposed. Neyman's non-parametric setup is used as a benchmark. In this setup, each subject has two potential responses, one if treated and the other if untreated; only one of the two responses can be observed. Beside the mathematics, there are simulation results, a brief review of the literature, and some recommendations for practice.
dc.descriptionPublished in at http://dx.doi.org/10.1214/08-STS262 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)
dc.identifierhttps://arxiv.org/abs/0808.3914
dc.identifierhttp://arxiv.org/abs/0808.3914
dc.identifierStatistical Science 2008, Vol. 23, No. 2, 237-249
dc.identifierdoi:10.1214/08-STS262
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/167916
dc.subjectMethodology
dc.titleRandomization Does Not Justify Logistic Regression
dc.typetext

Files

Collections