Is there a way to generate equally balanced subsample quotas when working with randomization? | Experience Community
Skip to main content
Question

Is there a way to generate equally balanced subsample quotas when working with randomization?

  • October 15, 2021
  • 1 reply
  • 172 views
L

Hello!
I want to include a randomization in my survey that randomly shows one of four blocks to participants. In doing so, I aim to generate evenly distributed quotas for the resulting 4 subgroups. Randomization only won't lead to a rather equal distribution for quotas (age, gender, education), will it?
Or is there a way to run the survey and to create a solution with e.g., 4 quota checks in one survey? Something like: qualtrics checks quotas for subgroup A, and quotas are already met and then it checks if there is a person with these traits needed to fill the quotas in subgroup B to D.
Thank you!

1 reply

E
Forum|alt.badge.img

There is stratified random sampling where you identify specific groups and then randomly sample within each group.
There is purposeful sampling. Depending on the project goals you might need to worry about bias, but you should worry about this anyway.
You could increase sample size until minor groups have a sufficient sample size. You have more analysis options with this approach. There is no requirement that you use all of the data collected, though how you selectively analyze the data can also lead to bias. One solution is to be open about how you did the analysis and make the raw data available. If someone disagrees with you they can take your raw data and do the analysis in the way they think is right. If they get a different conclusion then you have lively debate.

Terms & ConditionsAccessibility statement