Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Fixed effects in cross-sectional data

    Dear all,

    I have a theoretical question regarding fixed effects in cross-sectional data.

    Omitting region fixed effects will only bias the results of a linear regression if some unobserved, region-specific characteristics are correlated with both x and y, and will not bias the results, if only correlated with y, right?

    Best,
    Marco

  • #2
    That is correct. How useful it is, is another question, in that one is usually unable to know whether there are such unobserved characteristics or not.

    Comment

    Working...
    X