0
$\begingroup$

I am currently using the CausalImpact package for some research and in this context I need to know and be able to explain, how the posterior tail-area probability is calculated in order to reproduce that value for validation purposes. Does anyone know, how that value can be reproduced given the data and the estimation series provided by the model?

Improve this question
$\endgroup$
1
  • $\begingroup$ Sometimes this issue trips folks up. $\endgroup$
    – dimitriy
    Commented Nov 7, 2020 at 5:41

1 Answer 1

Reset to default
1
$\begingroup$

The CausalImpact paper describes the calculation of the tail-area probability in detail (see section 2.3). There is probably no "easier" way to reproduce it than the actual implementation in the package...

Improve this answer
$\endgroup$

Your Answer

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

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