Article View: sci.math.stat
Article #988Projection Pursuit with logistic link
From: Charles Roosen
Date: Thu, 15 Apr 1993 18:05
Date: Thu, 15 Apr 1993 18:05
11 lines
1324 bytes
1324 bytes
Has anyone out there worked on implementing Projection Pursuit Regression with a 0-1 response using a logistic link function? This can be thought of as using logistic additive models with derived predictors which are linear combinations of the original predictors. I'm familiar with Friedman's method for classification using Projection Pursuit, but was wondering if anyone has worked on using a logistic response approach instead. Thanks, Charles Roosen charles@playfair.stanford.edu
Technical Details
Message-ID:
<1993Apr15.180522.17272@EE.Stanford.EDU>Path:
arc1-ca.pugleaf.net!gmd.de!newsserver.jvnc.net!howland.reston.ans.net!agate!headwall.Stanford.EDU!EE.Stanford.EDU!playfair.Stanford.EDU!charlesShow Full Headers
Complete Article Headers
X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: f5efb,756d19e6af6cb5be,start X-Google-Attributes: gidf5efb,public X-Google-Thread: 10d04f,756d19e6af6cb5be,start X-Google-Attributes: gid10d04f,public X-Google-Thread: f8fde,756d19e6af6cb5be,start X-Google-Attributes: gidf8fde,public X-Google-ArrivalTime: 1993-04-15 11:21:59 PST Newsgroups: sci.math.stat,comp.ai.neural-nets,bit.listserv.stat-l Path: arc1-ca.pugleaf.net!gmd.de!newsserver.jvnc.net!howland.reston.ans.net!agate!headwall.Stanford.EDU!EE.Stanford.EDU!playfair.Stanford.EDU!charles From: charles@playfair.Stanford.EDU (Charles Roosen) Subject: Projection Pursuit with logistic link Message-ID: <1993Apr15.180522.17272@EE.Stanford.EDU> Sender: usenet@EE.Stanford.EDU (Usenet) Organization: Stanford University Date: Thu, 15 Apr 93 18:05:22 GMT Lines: 14