Erik Sverdrup

Hi @kmaloneyUSGS, unfortunately grf does not estimate a dose-response. If you supply a continuous treatment to causal_forest the statistical quantity tau(X) you are getting is an [average partial effect](https://grf-labs.github.io/grf/reference/causal_forest.html): >...

Hi @ninetale, the effective number of samples used for estimation in both 1 and 2 is n=1000, but in 1 you set aside honest.fraction*sample.fraction=400 for "honest" splitting. 3: yes, but...

Very nice Apoorva, maybe you could convert this to a "Draft PR" then just use this as a playground for learning and fighting with C++/bindings using grf's build system at...

Is this still something you want to devote large chunk of time to? If not let's close this for now? (for users who don't want to leave python, stitching together...

That sounds like a great and practical idea! If you find it engaging, perhaps you could create an example gallery on your page to gather user feedback and refine the...

Closing in favor of #257 which discusses R/Python interop.

Hi @Lee-xli, the [following vignette](https://grf-labs.github.io/grf/articles/rate_cv.html) shows how to aggregate RATE metrics. The RATE is the area under the TOC curve, so if you just want a t-value for a point...

Hi @shafayetShafee, >After going through [this paper](https://arxiv.org/abs/2409.01578), I can think of some approaches. But I am a bit confused, since these resources discussed about binary treatment only, whereas my usecase...

Hi @MCKnaus, thank you very much for the suggestion (and also for the interesting reference). For cases with custom outcome/propensity models, the intended design was to construct those models outside....