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 1999)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Tue, 30 Mar 1999 19:56:22 -0600
Reply-To:     "Matheson, David" <davidm@SPSS.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         "Matheson, David" <davidm@SPSS.COM>
Subject:      Re: Combining Variables
Comments: To: Sheril Smith <iresrs@LANGATE.GSU.EDU>

Sheril, To be of much help, we would need to know how you want multiracial responses to be coded. Suppose codes 1-8 correspond to yes responses to only 1 of the 8 variables. There are 28 possible biracial responses. Would you want these to occupy codes 9-36 on the new ethnicity variable? Perhaps with a code 37 for 3 or more ethnic groups checked? This set of codes is only 1 possible scenario. Another scenario would be forced choice of 1 of the ethnic groups chosen, but then you'd have to provide a basis for that choice. Also, note that if the variable is to be used for descriptive purposes, such as cross-tabulation without inferential statistics, you may be able to get the information you want from the MULT RESPONSE procedure. The original 8 variables could be declared as a multiple dichotomy set. You would likely want to use cases, rather than responses, as the percentage base.

David Matheson SPSS Technical Support

-----Original Message----- From: Sheril Smith [mailto:iresrs@LANGATE.GSU.EDU] Sent: Tuesday, March 30, 1999 11:02 AM To: SPSSX-L@UGA.CC.UGA.EDU Subject: Combining Variables

Hi All,

I'm new to this list, so forgive me if this question has been previously asked.

I have a data set from a questionnaire that we recently sent out. One question asked about race/ethnicity of respondents. Respondents were able to check more than one category as they saw fit, thus each racial category became it's own separate variable. I'm now trying to combine all eight racial categories into one variable, so that I'll end up with one variable, 'ethicity', rather than 'white', 'black', 'asian', 'hispanic', etc. Does anyone know how I might accomplish this task?

**************************************************************************** **************************************************************************** **** Sheril R. Smith Doctoral Student Research Analyst I Office of Institutional Research Georgia State University (404) 651-1075


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