I am trying to replicate the median age for BLS Table 18b. Employed persons by detailed industry and age (https://www.bls.gov/cps/cpsaat18b.htm).
I get the exact same number of employed persons, but the median age is different. I belive this is a result of differences between the microdata and published tables, but could not find any documentation of this.
Any assistance would be appreciated.
The estimates published by the BLS are calculated using the CPS composite weight PWCMPWGT (COMPWT in IPUMS CPS). The Census Bureau states that even using the composite weight, “not all estimates made from a public use file will match such weighted published estimates. This is because of various steps taken in the creation of CPS public use files to protect the confidentiality of CPS respondents. Top side estimates for most major demographic and economic categories such as age, race, gender and major labor force status will agree with the published totals; however, estimates for small groups/combinations of these characteristics will differ. The same is true for any estimates for any demographic or labor force characteristic not listed above. Such estimates will be similar but not identical.”