If what you want is what we call raking - matching multidimensional control totals, there is a module called rake.py on SPSS Developer Central, www.spss.com/devcentral, that does this.
It requires SPSS 15, programmability, and the Advanced Statistics module, the latter because it fits a log-linear model using GENLOG as part of the process.
Usage is pretty simple even if you are not proficient in Python. Here is a simple example using the employee data.sav file.
begin program.
import spss, spssaux, rake
rake.rake(['jobcat','gendern'],[{1:.333, 2:.333,3:.334}, {1:.50, 2:.50}], finalweight='wt', poptotal=474)
end program.
This forces the dataset to have equal percentages for the jobcat variable and then equal numbers of males and females.
HTH,
Jon Peck
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of Eugenio Grant
Sent: Wednesday, February 28, 2007 10:41 AM
To:
[hidden email]
Subject: [SPSSX-L] Rim weighting
Hi Guys:
I don´t think this has been addressed before here in the forum, does anyone
have some syntax or maybe a paper, article or link with explanations on how
rim weighting works.
Regards,
Locked
