search

xuyiqing / fect

fixed effect counterfactual estimators
Other
57 stars 20 forks source link

Will the result still be valid if some units are untreated, treated, and then untreated again? #2

Closed jluo41 closed 4 years ago

jluo41 commented 4 years ago

The ordinary policy pattern is being untreated, and then treated (that is D = [0,0,0, ..., 1,1,1...].

What if the policy pattern is being untreated, treated, and then untreated? That is the D = [0,0,0,0, ..., 1,1,1, ..., 0,0,0 ...]. Will the result still be valid? Can the result still be interpreted in the previous way?

Thanks,

Junjie

xuyiqing commented 4 years ago

Yes, it will be valid, as long as you are willing to accept the assumption that the treatment only has contemporaneous effects (as in two-way fixed effects).

On Fri, Jun 12, 2020 at 2:23 AM floydluo notifications@github.com wrote:

The ordinary policy pattern is being untreated, and then treated (that is D = [0,0,0, ..., 1,1,1...].

What if the policy pattern is being untreated, treated, and then untreated? That is the D = [0,0,0,0, ..., 1,1,1, ..., 0,0,0 ...]. Will the result still be valid? Can the result still be interpreted in the previous way?

Thanks,

Junjie

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/xuyiqing/fect/issues/2, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2PKGG4N6FHRBR7STQBBFTRWHXYXANCNFSM4N4FBL6A .

-- Yiqing Xu

Assistant Professor Department of Political Science Stanford University http://yiqingxu.org/

jluo41 commented 4 years ago

Great! Thanks for your reply.