Announcement

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

  • DID regression COLLINEARITY problem

    Hello to everyone,
    I want to run a difference-in-differences regression with a control variable.

    My variables are:
    dependent (number of children, continuous)
    time (survey wave, dichotomous)
    treatment (dichotomous)
    ttreated (interaction term between time and treatment)
    control variable (employment, coded as 1=employed and 0=not employed)

    I use the command:
    reg dependent time treated ttreated i.employment, but what comes out is that time and ttreated are omitted because of collinearity.
    I have other dichotomous covariates that does not give any problem.

    Can someone help me?

    Thank you!

  • #2
    Virginia:
    as per FAQ, without an excerpt/example of yuor dataset, that you can share via -dataex- it is difficult to reply positively.
    As an aside, please see -fvvarlist- notation to create categorical variables and interactions.
    Kind regards,
    Carlo
    (Stata 19.0)

    Comment


    • #3
      Good evening,
      thank you very much for your answer. Fortunately, I solved the problem!

      Comment

      Working...
      X