Omitted Variables in Logistic Regression

Article View: bit.listserv.stat-l

Article #992

Back to bit.listserv.stat-l Previous Next

#992

From: Julia Lane
Date: Tue, 27 Jul 1993 16:09

14 lines
1237 bytes

When you omit a variable in a linear regression, the consequence is
to bias the coefficient on included variables which are correlated
with the omitted variable.  It's pretty straightforward to show
the magnitude of this bias.

Does anyone know how to show this in logistic regression?  Any help
would be much appreciated.

************************************************
JULIA LANE
JILANE@AUVM.AMERICAN.EDU
202-885-3781 (W)
202-885-3790 (FAX)
************************************************

Technical Details

Message-ID: <STAT-L%93072712152918@VM1.MCGILL.CA>

Path:

arc1-ca.pugleaf.net!gmd.de!xlink.net!howland.reston.ans.net!europa.eng.gtefsd.com!paladin.american.edu!auvm!AMERICAN.EDU!JILANE

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: f5efb,4ca7498180ddee80,start
X-Google-Attributes: gidf5efb,public
X-Google-ArrivalTime: 1993-07-27 12:38:11 PST
Path: arc1-ca.pugleaf.net!gmd.de!xlink.net!howland.reston.ans.net!europa.eng.gtefsd.com!paladin.american.edu!auvm!AMERICAN.EDU!JILANE
Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
Newsgroups: bit.listserv.stat-l
Return-Path: <@AUVM.AMERICAN.EDU,@VTBIT.BITNET:owner-stat-l@VM1.MCGILL.CA>
Message-ID: <STAT-L%93072712152918@VM1.MCGILL.CA>
Date: Tue, 27 Jul 1993 12:09:51 EDT
Sender: Stat-l Discussion List <STAT-L@MCGILL1.BITNET>
From: Julia Lane <JILANE@AMERICAN.EDU>
Organization: The American University
Subject: Omitted Variables in Logistic Regression
Lines: 13