American Community Survey Data Users Group
ACS Data Products & Resources
ACS Public Use Microdata Samples (PUMS)
ACS Summary Files
Application Programming Interface (API)
ACS Data Issues
ACS Data for Small Geographic Areas & Population Subgroups
Mapping ACS Data/GIS Applications
Measuring Trends Over Time with ACS Data
ACS Public Use Microdata…
ACS Public Use Microdata Samples…
Complex Analysis Plan for…
This group requires membership for participation - click to join
John J. Green
Mar 21, 2016 3:00 PM
Complex Analysis Plan for PUMS using SPSS?
Does anyone have recommendations for setting up a complex analysis plan in SPSS for analyzing ACS PUMS data? I am trying to help a group of master-level graduate students analyze 2014 5-year ACS PUMS data, and they need to use SPSS, given that is what is available for our lab. They want to be able to calculate the appropriate standard errors for their hypothesis tests. I have been combing the web to find recommendations, but I just keep finding posts for STATA, etc. with the note that SPSS cannot be used. Surely, there are folks using SPSS. Does anyone have recommendations?
Mar 22, 2016 8:05 AM
I think your challenge is not so much one with ACS as of what's included in the base package of the software. It is my understanding that SPSS treats weights as frequency weights unless you have an extension package (e.g. Complex Samples package) installed. (See:
That said, the Census Bureau wrote code for an older version of SAS that does the replicate weight processing step by step (rather than the newer jackknife command). Read:
There's a link toward the bottom, "Estimating ASEC Variances with Replicate Weights" that contains the code (
You may be able to re-work that code for SPSS.
(Note: When I opened the document, the SAS code was gibberish, but changing the text format to Arial fixed the problem.)
Let me know if that helps!
John J. Green
Mar 22, 2016 9:28 AM
Thanks for these ideas, Beth. I will check them out and let you know how things progress. JG
Mar 22, 2016 10:06 AM
To the best of my knowledge, SPSS Complex Samples still does not support replicate weights which are required for the analysis of PUMS data (successive difference replication). May be you can write your own macro to do this, but it will be still be confusing to the students.
Any of Stata, R, SAS or even WesVar can be used for the task (or at least tricked with specification of BRR or jackknife weights). Unfortunately, SPSS is out of the league... as the web was pointing out to you.