I have a dependent variables with a significant amount of zeros (and the share of zeros is different between the control and treatment groups, and changes between the pre- and post-treatment periods). I do observe a pre-treatment parallel trend of the dependent variable (when including the zeros).

My problem is simple: is a standard diff-in-diff biased in this case (and why)? If yes, what can be done?


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.