Hi all I am analyzing several DMA's for campaign effectiveness using the CausalImpact package by Kay Brodersen. I have data for participants and non-participants INCLUDING their contemporaneous regressors (e.g. Spend dollars, Economic attributes, Google search trend data e.t.c) My question is HOW can I use the Control time series "together with their regressors" to evaluate the Participants campaign effectiveness. The documentation does not include such an example

  • $\begingroup$ This is hard to follow. What are "DMA's"? What "documentation" are you referring to? Are you just asking for help w/ your software / code? $\endgroup$ – gung May 11 '16 at 21:44
  • $\begingroup$ Hi gung. A DMA is a designated market area in which several of them are test markets and the majority are controls without a marketing intervention. The documentation I am referring to is the package research paper research.google.com/pubs/pub41854.html. The question is more about the application of the package and if I can utilize it for multiple control series but also with additional regressors. $\endgroup$ – Elderkm2012 May 12 '16 at 1:29
  • $\begingroup$ I feel like this message should probably be a comment but I can't seem to post one now :( I'm working on a similar problem and I'm planning to throw in a few control series AND a few key covariates (macro economics, marketing spending etc.). What method did you end up using for your problem? Would you mind sharing your experience with CausalImpact for similar problem? Thanks! $\endgroup$ – Yue Feb 27 at 5:05

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.