@kbattocchi
Hi Keith,
How would you recommend handling a case where we know the true treatment probabilities? I'd prefer to use them to avoid having to fit the model_propensity (in a doubly robust model, say ForestDRLearner).
A few options:
- Pass the (inverse) probabilities as
sample_weight to fit. But then we need to choose something for model_propensity, perhaps just a dummy classifier?
- Create a trivial
model_propensity that takes the probability as a feature and returns the same probability. But then we need some workaround to prevent the model_regression from using the probability as a feature (by DRLearner will always pass X, W to both model_propensity and model_regression). Maybe we can use a sklearn pipeline with transformer for this.
Thanks!
Kyle
@kbattocchi
Hi Keith,
How would you recommend handling a case where we know the true treatment probabilities? I'd prefer to use them to avoid having to fit the model_propensity (in a doubly robust model, say ForestDRLearner).
A few options:
sample_weighttofit. But then we need to choose something formodel_propensity, perhaps just a dummy classifier?model_propensitythat takes the probability as a feature and returns the same probability. But then we need some workaround to prevent themodel_regressionfrom using the probability as a feature (by DRLearner will always pass X, W to both model_propensity and model_regression). Maybe we can use a sklearn pipeline with transformer for this.Thanks!
Kyle