LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (March 2004, week 3)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Wed, 17 Mar 2004 09:22:02 EST
Reply-To:   PGall9898@AOL.COM
Sender:   "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:   Philip Gallagher <PGall9898@AOL.COM>
Subject:   Re: Bivariate Logit/Probit
Comments:   To: kahlenberg@WISO.UNI-KOELN.DE
Content-Type:   text/plain; charset="US-ASCII"

Jens Kahlenberg <kahlenberg@WISO.UNI-KOELN.DE> wrote, in part,

Hello everyone, I am new in these lists.

I am concerned with bivariate generalized linear models. In particular, my focus is on bivariate logit or probit models, i.e. models with two dependent 0-1-variables.

Here my questions: ... 2. In that context: Does anybody know any good literature about these models? Often "bivariate" is being confused with "multiple" (with two regression covariates), so I suffer some problems of finding the right literature.

Jens, it may help your searches to know that most of the statisticians that I know use the term multivariate to describe the general case of what you mean when you say bivariate, although I have discovered to my embarrassment that this convention is not universally honored. In this usage, however, when my friends speak of a Multivariate General Linear Model they mean multiple (two or more) dependent variables, for example. If you were to repeat your searches substituting multivariate for bivariate you might find find more articles.

Good luck.

Phil Gallagher Nantucket


Back to: Top of message | Previous page | Main SAS-L page