Article View: bit.listserv.stat-l
Article #1024partial shrinkage in logistic regression
From: Frank Harrell
Date: Sat, 03 Jul 1993 01:31
Date: Sat, 03 Jul 1993 01:31
17 lines
1408 bytes
1408 bytes
Does anyone know of a reference to a shrinkage method that allows the analyst to shrink a subset of the coefficients? The applicatioin I have in mind is one in which a multi-level polytomous factor has some low-frequency levels that I would like to impose James-Stein-type shrinkage on to shrink them to the mean logit. For continuous covariables I want to get ordinary betas. I am familiar to work by Copas and Van Houwelingen and Le Cessie which allow overall shrinkage in logistic regression. Thanks. Please reply to the newgroup or to feh@biostat.mc.duke.edu : -- ---------------------------------------------------------------------------- Frank E Harrell Jr feh@biostat.mc.duke.edu Associate Professor of Biostatistics Division of Biometry Duke University Medical Center
Technical Details
Message-ID:
<17235@news.duke.edu>Path:
arc1-ca.pugleaf.net!gmd.de!newsserver.jvnc.net!howland.reston.ans.net!gatech!news-feed-1.peachnet.edu!concert!duke!news.duke.edu!duke.edu!fehShow Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: f5efb,a963997cbc8b7fc7,start X-Google-Attributes: gidf5efb,public X-Google-ArrivalTime: 1993-07-02 18:35:18 PST Path: arc1-ca.pugleaf.net!gmd.de!newsserver.jvnc.net!howland.reston.ans.net!gatech!news-feed-1.peachnet.edu!concert!duke!news.duke.edu!duke.edu!feh From: feh@duke.edu (Frank Harrell) Newsgroups: bit.listserv.stat-l Subject: partial shrinkage in logistic regression Keywords: shrinkage Message-ID: <17235@news.duke.edu> Date: 3 Jul 93 01:31:32 GMT Sender: news@news.duke.edu Lines: 17 Nntp-Posting-Host: biostat.mc.duke.edu