Why can't I match the American Factfinder numbers?


#1

I downloaded an IPUMS data set about commute type for various metro regions, however, for some reason I can’t seem to match the data on the American Factfinder website, which I was doing just to confirm I understand things correctly. When I look at total workers over 16 years of age, for the Raleigh metro (39580) I get either 656,611 from the ACS 1 year or 616,341 from the ACS 5-year. The American Factfinder site says that it is using the ACS 5-year. Since I’m looking at commute type breakdown, I also checked percentages and still couldn’t match the American Factfinder data perfectly. When I look at driving alone, I get 80.2% (in Raleigh metro) from the ACS 1-year, 80.7% from the ACS 5-year, and using the numbers on the American Factfinder site, I get 80.3%, so the ACS 5-year is a larger difference even though it is what the Factfinder says it is using.

So where does the difference here come from? Which data set should I be using?

Thanks. - Josh


Query to match ACS data
#2

Estimates derived from the ACS public use microdata are expected to differ from the summary tables available through American FactFinder. This is because the summary tables use the full ACS samples while the public use microdata files include a subset of the sample (about two thirds). The microdata sample is then re-weighted to match the total population figures. While we do expect estimates to differ, they should generally still fall within the published margins of error.

I hope this helps!