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 (October 2005)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Sun, 9 Oct 2005 22:29:08 -0700
Reply-To:     Michael Healy <healym@earthlink.net>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Michael Healy <healym@earthlink.net>
Subject:      Missing data in regression query
In-Reply-To:  <026501c5cca8$346fee90$3280a8c0@res.tbzmed.ac.ir>
Content-type: text/plain; charset="US-ASCII"

Hi, This is a stats question. I have a data set with 2,000 cases and many of the variables which are going to be used as predictors in multiple regression modeling are missing up to 50% of their values. I probably have about 30% listwise complete data, so I don't want to model just the complete cases. I also don't want to impute scores because of the vast amount of missingingness. Does anyone have any hints/suggestions/resources/etc. For dummy coding missing values or other creative ways of dealing with data like this? Thanks, Mike Healy


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