For those unfamiliar with census geography, census tracts are made up of multiple block groups.

Suppose I have three data tables (all categorical):

  • Block Group Geography x Home Value
  • Block Group Geography x Household Income
  • Census Tract Geography x Home Value x Household Income

Would I be able to use Bayes' Theorem and the information I know about the census tract and block group to calculate the probability of a home's value being in a particular category (i.e. 100k-200k) given that the person owning the home has a certain household income and lives within a particular block group?

If so, is this the correct way to do it:

  • p = P(Home Value [T] | Household Income [T]) where [T] indicates census tract
  • q = Total owner-occupied housing units with a particular home value [BG]/Total owner-occupied housing units [BG] where [BG] indicates block group

P(Home Value [BG] | Household Income [BG]) = $\frac{pq}{\sum_{p,q} pq}$

Thanks for any help!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.