nhejazi / txshift

:package: :game_die: R/txshift: Efficient Estimation of the Causal Effects of Stochastic Interventions, with Corrections for Outcome-Dependent Sampling
https://codex.nimahejazi.org/txshift
Other
13 stars 4 forks source link

Estimate Q on original scale #71

Open Lauren-EylerDang opened 1 year ago

Lauren-EylerDang commented 1 year ago

Hi Nima,

I am working on a project with a count outcome, and some of the algorithms my collaborators want to consider in the SL library only handle non-negative integers. For this reason, I modified the est_Q function to estimate Q on the original outcome scale (instead of scaling Y before estimating Q). If you find this modification helpful, please consider my pull request.

Thanks, Lauren