I am working with duration data. My analysis uses as dependent variable a binary variable indicating whether the individual has divorced yet in time t (Y=1) or not (Y=0).

However, the literature on divorce uses mostly the duration (Y=1,2,3,...J) as the dependent variable, and follows on using a Fixed Effects estimator.

I acknowledge that the two approaches estimate different things, but I also see that the are slightly different perspectives over the same thing, aka how a policy affects duration. Does anyone have insight over which approach is better or what are the limitations of each?

Thank you.



Doksum and Gasko (1990) gives an answer to this question. It is that "a one-to-one correspondence between models in binary data analysis and continuous time survival analysis exists", which they spell out. The only difference is that they developed in different fields, each remaining suspicious of the other's approach to the same question.

Doksum, K. A., & Gasko, M. (1990). On a correspondence between models in binary regression analysis and in survival analysis. International Statistical Review/Revue Internationale de Statistique, 243-252.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.