• LeninWeave [none/use name]@hexbear.net
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    9 months ago

    The purpose is to measure the effect of a single variable, so you make sure to correct for all other variables. For example, to measure the effect of height you might compare white men only against white men, black women only against black women, etc.

    In a study measuring the gender pay gap, they would be correcting for variables other than gender.

    • Juice [none/use name]@hexbear.net
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      9 months ago

      Is that what “this estimation assumes other factors associated with earning potential — for instance, gender, age, years of schooling, and location — are held equal,” means? Cuz that’s not what it sounds like. Assuming things are equal isn’t this statistical matching thing you are talking about

      Edit: I found the study so I’m trying to figure out how these other factors are controlled for.