Status:Closed    Asked:Apr 23, 2014 - 02:06 PM

Can you use PERWT in combination with MULYEAR to obtain weighted data for a single year from a multiyear file?


I'm working on estimating economic security indicators for Northern Virginia. I'm using the 2010-2012 3-year file because I want to make sure I have a big enough sample size for racial breakdowns. However, for basic breakdowns I would like to use 1-year data to have the most recent information. In order to be more efficient I decided to download the 3-year file, and use MULTYEAR == 2012 to separate 2012 data.

Is it posible to use MULTYEAR to restrict the sample to a single year and still have accurate weighting? Or do I need to dowload the 1-year file to have accurate weights.

Thanks so much in advance for your response.

I look forward to hearing back from you


Do you have the same question? Follow this Question

Staff Answer




It is not possible to weight a single year in a multi-year file to be nationally representative because the PERWT variable is adjusted in the multi-year file. If you multiply PERWT by 3 in a 3-year file you will get close to the Nationally Representative figures for that year (which you can check using the 1-year file), but it is safest to use the 1-year files for doing analyses on single years.

I hope this helps.


Apr 23, 2014 - 03:37 PM

Report it


Stacking 3 Individual Years of Data vs. Waiting for the 3-year Sample
alternative to a 3-year file
Comparing single year to multiyear
I am getting strange numbers for NIU persons in the sixties, especially 1962-...
Login   |   Register

Recently Active Members

View More »

Share |