Keith Battocchi

Could you please provide some more information about your environment? What version of python are you running, and on what operating system? Can you also please provide the output of...

Could you elaborate on what you think the problem is? If your model correctly assigns a very low probability to an outcome, then either it is correct and the 1{T_i=t}...

I agree with this: > @kbattocchi Here is my understanding: For each record, in order to calculate treatment effect \theta_t(X) for all treatments (say 1,2,3..N, N treatments) compared to treatment...

This is where the indicator 1{T_i=t} comes in: if treatment t was not assigned to that unit, then the indicator will be zero and so it doesn't matter what the...

@justforsoy If it affects the relationship between T and Y, then I think it must inherently affect Y as a result of this relationship (i.e. most of our estimators assume...

Closing in favor of #746

At one point, we were considering an alternate approach to refitting where we kept track of which attributes were modified and prevented refitting if they would invalidate the results; however,...

Could you provide more context for where you're getting that error? If you can provide a complete reproduction it would be easier to understand what's going on.

Could you expand on exactly what data you'd like us to output? In particular, how does what you want differ from what the [`treat`](https://econml.azurewebsites.net/_autosummary/econml.cate_interpreter.SingleTreePolicyInterpreter.html#econml.cate_interpreter.SingleTreePolicyInterpreter.treat) method on the class provides? That...

Thanks for the suggestion - for the case of a binary outcome this does seem like a potentially valuable addition to the library and it's something we'll consider.