I am working on a problem where I am trying to estimate the effect of whether event C will occur given the time to B. The following scenarios illustrate the possible paths my system may take.

A -> B -> C

A -> C - > B

A -> B

Easy enough; a logistic model: $Logit(C) = b_0 + b_1time_{A->B}$ could explain probability of an event C given the time to B.

However in my system if event C occurs before event B it causes B to take longer to occur. How can I account for this effect? (There are likely other confounding effects that contribute to C occurring)

  • $\begingroup$ Try using a one period lag of C as a predictor. $\endgroup$ Nov 21, 2020 at 15:39


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.