IPUMS FAQs: Why don’t my calculations perfectly match official statistics?

At IPUMS we try to address every user’s questions and suggestions about our data. It is just one feature that adds value to IPUMS data. Over time, many questions are often repeated. In this blog series, we will be sharing some of these frequently asked questions. Maybe you’ll learn something, or perhaps you’ll just find these interesting. Regardless, we hope you enjoy.

Here’s one of those questions:

Why don’t my calculations perfectly match official statistics?

The US Census publishes official summary statistics from the decennial census and the American Community Survey (ACS), which is the source data behind the IPUMS USA project. This being the case, many users try to see if they are able to exactly replicate the official statistics with IPUMS USA data. Sometimes this leads to a user asking why their calculation does not perfectly match the official US Census statistics.

Many times the discrepancy is due to a technicality in the calculation itself. For example, the official statistics may restrict the population to adults (or those who are older than 16 years old), and this detail may not be clear in the documentation. Other times the calculation is exactly the same, but the final numbers still do not perfectly match. In this situation, we tell users that we do not generally expect to exactly replicate official US Census statistics with public use data. We do expect to be within the margin of error around statistical estimates, but exact matches are rare.

Discrepancies between user-calculated estimates and official statistics are largely due to the fact that official statistics are calculated from restricted-access data, which is only available for internal government or specially approved purposes. This restricted-access data has a little more detail than public use data, which is limited to maintain the confidentiality of those included in the sample. Therefore, while replications of official statistics should be close, and within a specific margin of error, we generally don’t expect to perfectly match official statistics every time.

Story by Jeff R. Bloem
PhD Student, Department of Applied Economics
Graduate Research Assistant, Minnesota Population Center