Hi everyone,
i want to use PUMAs (smallest geographical unit) for my analysis of educational inequality in the US from 2005-2015.
1)How can i deal with the change in PUMA definition from 2005-2011 versus 2012-2020?
2)I want to match the PUMAs to local education agencies from the CCD data. From the CCD Data, i know the adress (street,zip code …) of the education agencies but how can i match this to the IPUMS PUMAs ?
Thank you!
Dear Franz,
As far as I know, the Local Education Agencies (LEAs) in the CCD are the same as school districts. Thus, I think the first think you’ll need to do is match school districts to the 2010 PUMAs and school districts to 2000 PUMAs. I recommend using the Geocorr product from the University of Missouri. The 2014 Geocorr will allow you to match school districts to 2010 PUMAs, and the 2000 Geocorr will allows you to match school districts to 2000 PUMAs.
PUMAs (in many cases) will be comprised of multiple local education agencies, so I assume you want to aggregate LEA statistics in the CCD up to the PUMA level. This is especially true in suburban and rural areas because of the way PUMAs are constructed (minimum of 100,000 persons). Is that a correct assumption? Regardless of the unit of analysis you want to use (PUMA or school district), the matching will be quite challenging.
As for handling PUMA boundary changes, I don’t have a great suggestion for you, but my colleagues at IPUMS may chime in on that part of your question.
Sincerely,
Dave Van Riper
IPUMS USA offers the variable CPUMA0010, which bridges the 2000 and 2010 PUMA boundary vintages. By aggregating 2010 PUMAs together until their combination aligns (within 1% population margin) with one or more 2000 PUMAs, changes in boundaries are absorbed into this new CPUMA0010 geographic unit. Once you’ve matched school districts to their corresponding vintage PUMA, you can use the summary file on the CPUMA0010 definitions page to match them to the corresponding consistent PUMA.