Status:Closed    Asked:Feb 21, 2017 - 12:27 PM

How can I transform the incwt variable into a percentage to calculate weighted averages?

I need to calculate averages conditioned on year and occuupation using the weight variable incwt so that they are representative. How do I use this weight in calculating averages? Can it be transformed into a percentage?

Do you have the same question? Follow this Question

Staff Answer


Jeff Bloem


I think you are referring to EARNWT. If not, feel free to clarify. If your aim is to calculate income by year and occupation, it may be better to use the INCTOT variable within the ASEC samples and use the PERWT weighting variable. You can learn more about sampling weights by reviewing this IPUMS-CPS FAQ page. For some occupations, due to the relatively small sample in the CPS and the large number of occupation categories, it may be difficult to calculate meaningful summary statistics using public use data. One option around this difficulty would be to aggregate some occupations together so you have a smaller number of occupation categories. Finally, the BLS puts out a table every year with national occupational employment and wage estimates. Here is a link to the table for 2015.

I hope this helps.


Feb 22, 2017 - 07:42 AM

Report it


When did IPUMS-CPS start like the way (easily downloadable way) like now?
Replicate weights for use with CPS-TUS
Longitudinal cohort in TUS 2014/2015?
When can we expect NFHS 4 data to included in IPUMS-DHS database?
trying again need more characters
DOINGLW2 variable
Login   |   Register

Recently Active Members

View More »

Share |