I am working in the context of opt-in, web-based surveys. Often the desire is for accurate population estimates, and often at a country-wide level. The standard approach at this organization is to define demographic strata and determine quotas for each stratum according to high-quality reference data such as that from the U.S. Census Bureau, so that strata proportions equal population proportions. Most often these strata are defined by gender and age.

I've come to understand that some of the surveys run here are pre-stratified at one combination of gender and age groups, and then after the survey timeline has ended, post-stratified and weighted along more discretized groupings of the same variables. As an example, assume that pre-collection strata are divided along 3 age groups (18-24, 25-54, 55+), and then post-collection strata are divided into 6 age groups (18-24, 25-34, 35-44, 45-54, 55-64, 65+). Quotas are set for the initial strata according to census data, and then the results obtained from this quota sample are weighted according to the same census dataset, but divided into narrower age groups.

Something about this feels wrong to me, but I don't have the expertise to identify what exactly that is. Reading about survey methods, I see plenty of material about pre-stratification and post-stratification, but nothing on using them both together. Maybe my attempts to find reading on this particular approach are inadequate. Either way, I would very much appreciate some guidance here.

Thank you in advance.

  • $\begingroup$ If you (pre-)stratified at the state level, and then post-stratified at the congressional district level because you wanted estimates at that level, would that also feel wrong? $\endgroup$
    – num_39
    Feb 7 at 21:49
  • $\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$
    – Community Bot
    Feb 7 at 21:52


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.