I was curious if it was possible to join two rounds of the CPS march supplement (or any monthly supplement) using the IPUMS data. The NBER has some papers that say you can join portions of the survey from year to year: http://www.nber.org/cps/
Has anyone tried this with the IPUMS data and would you be willing to share how you did this?
IPUMS-CPS does not currently offer variables that facilitate linking respondents across samples. Such variables are currently being worked on but there is no planned release date for the new variables at this time. However, it is possible to use the linking variables and methods you referenced by merging the NBER files with the IPUMS-CPS files. As long as you have not select cases based on a variable or changed the sort order of your IPUMS-CPS March download, the sort order of the NBER March supplement files and the IPUMS-CPS March files should be the same. This means you can perform a sequential merge. That is, match the first NBER records to the first IPUMS record, the second to the second, etc for each March sample. This will effectively add the NBER identifiers onto the IPUMS records. Once this is done, you can use the NBER identifiers to link the IPUMS respondents across March samples. I believe the linking procedure varies a bit from year to year, so please refer to the NBER documentation for more details.
I hope this helps.