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 (December 1997, week 3)Back to main SAS-L pageJoin or leave SAS-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Sun, 21 Dec 1997 22:14:24 -0500
Reply-To:     dsachs@netcarrier.com
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         Don Sachs <dsachs@NETCARRIER.COM>
Organization: All USENET -- http://www.Supernews.com
Subject:      Re: hotelling's t
Content-Type: text/plain; charset=us-ascii

The Hotelling T statistic is the multivariate extension of a univariate Student t. It is used whenever there is more than one dependent variable in the model, and tests the null hypothesis that a vector of all the variables equals zero. Note that it is posible for one the dependent variables to be significant with rejecting the multivariate null, and vice versa. The Hotelling T can be computed using PROC REG or PROC GLM, by adding MTEST and listing the multivarite nulls.


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