If you use the now default UNIQUE or REGRESSION method, this specification is ignored, as WITH is always used. If you use EXPERIMENTAL or HIERARCHICAL methods, the order in which effects are entered into the model depends on this specification. There is an extensive table in the ANOVA chapter of the Syntax Reference Guides (page 108 of the Release 8.0 version) that lays out all of the possibilities.

David Nichols Principal Support Statistician and Manager of Statistical Support SPSS Inc.

> -----Original Message----- > From: Diniz Lopes [SMTP:dmfl.etal@MAIL.TELEPAC.PT] > Sent: Thursday, February 11, 1999 4:08 PM > To: SPSSX-L@UGA.CC.UGA.EDU > Subject: > > Dear All > > Can someone help me with this one: I am trying to perform a Simple > Factorial Anova with covariates. SPSS gives me three hypothesis for > entering covariates - before effects, with effects and after effects. Can > someone please explain me the difference between methods. We can see > differences on the outputs... > > Thanks in advance! > > Diniz