Date:         Tue, 10 Mar 2009 10:38:28 -0500
Reply-To:     "Swank, Paul R" <Paul.R.Swank@uth.tmc.edu>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Swank, Paul R" <Paul.R.Swank@uth.tmc.edu>
Subject:      Re: Reference for factor loading cut-off
Comments: To: Eins Bernardo <einsbernardo@yahoo.com.ph>
In-Reply-To:  <132353.31185.qm@web76102.mail.sg1.yahoo.com>
Content-Type: multipart/alternative;

Two questions: why principal components and why a varimax rotation? As far as cut-offs go, why not test them. Some people use 1/sqrt(N-3) as an estimate of the standard error. There are programs that do significance tests of loadings for EFAs, like Mplus.

Dr. Paul R. Swank,
Professor and Director of Research
Children's Learning Institute
University of Texas Health Science Center-Houston

From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Eins Bernardo
Sent: Tuesday, March 10, 2009 10:01 AM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Reference for factor loading cut-off

I am working PCA using varimax rotation.  The editor of a journal suggested a cut-off  of 0.5 on the rotated factor loadings.  Using that cut-off is the same as throwing my paper into the garbage can since only few variables would qualify such criterion.  I am looking for a reference about the cut-offs.  I appreciate your help.

Eins


________________________________
How can I tell if my jewelry is real silver?<http://ph.answers.yahoo.com/question/index?qid=20080420083550AAtOSbk>
Find Out on Yahoo! Answers

[text/html]