Status:Closed    Asked:Jan 13, 2014 - 11:58 PM

What proceedures would you reccomend for computing standard errors for CPS ASEC data for years prior to 2005?

In regards to the CPS ASEC, for years from 2005 on we have replicate weights. For years prior to 2005, which variables in the IPUMS dataset, if any, represent survey design elements such as strata or clusters, or are indicators of or proxies for such elements, for purposes of doing variance estimates?

I have read this paper:

But the discussion is so general that I can not tell which of these methods are actually available given the information which is present in the IPUMS ASEC sample.

For years prior to 2005, is there a standard or preferred method for calculating variance or standard errors for means? For regression coefficients? I am interested in approaches that would generally be considered good professional practice, without being esoteric or merely fussy.

Do you have the same question? Follow this Question

Staff Answer




There are no strata/cluster variables in the CPS public use files because they are censored from the data by the Census Bureau. IPUMS-CPS does not endorse any specific method for generating variance estimates as the "Best Practice," but recommends that user's explore current literature on estimating variance in the Current Population Survey. For example, this article describes a procedure for generating synthetic design variables to use in place of the censored variables.
I hope this helps.


Feb 13, 2014 - 08:21 AM

Report it


Why are not all the "not in the labour force" categories filled for the EMPST...
I am getting strange numbers for NIU persons in the sixties, especially 1962-...
Login   |   Register

Recently Active Members

View More »

Share |