Status:Closed    Asked:Nov 28, 2017 - 11:54 AM

Vast Overestimation of Population

I am analyzing the specific household and individual characteristics of a limited number of counties in New Jersey. I downloaded the 2016 household and individual variables I wanted and tried to check my population counts to verify everything. However, when I apply the HHWT or PERWT to the PUMA counts I get a population of 8.9 million. According to the FactFinder the population should be closer to 3.1 million. I double checked my PUMAs and made sure the sample was limited to the geography in question, but it still seems way too big.

What am I doing wrong?

Do you have the same question? Follow this Question

Staff Answer


Jeff Bloem


I just looked into your most recent data extract and I've noticed that you haven't included a state identifier variable (STATEFIP). This is important because PUMA codes are state-dependent and must be read in combination with one of the state identifier variables. I suspect this is the main source of the descrepency. If you continue to not find population counts that are close to American Fact Finder, send me your code and I can take a closer look.


Nov 28, 2017 - 12:38 PM

Report it


Does using the INCLUGH variable over time requires correcting for the VERIFY=...
Does CLASSWKR in ASEC regarding self-employment (code 10) include incorporate...
I am trying to cross age, urban, and race. Which weight am I supposed to use?
Regarding Top-Coded and Replacement Values for 1990 HHINCOME
What happened to the tobacco use questions? They seem to have disappeared.
Do you have a plan to release earlier Contingent worker supplement data (1995...
Login   |   Register

Recently Active Members

View More »

Share |