Hi folks, I’m trying to track CPS response rates by counting PERNUM=1 (in IPUMS extracts) and PULINENO=1 in CPS microdata files downloaded directly from Census. According to the IPUMS extract, there were 40,092 responses in March 2025. But according to the CSV file downloaded from Census, there were 39,568.
Am I doing something wrong, or is this a real discrepancy that has an explanation?