Confused about dimensionality of nuisance model predictions #342
-
I am running simulations with 200 samples, 2 covariates to orthogonalize with respect to (Z), 50 treatment variables I want to orthogonalize (T), and 1 binary outcome I want to orthogonalize. I am running When I fit the model with the default Any help is appreciated!
|
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
Hello @RandallJEllis thanks for your interesting question. Since you use If you'd like to set
Hope this helps! |
Beta Was this translation helpful? Give feedback.
Hello @RandallJEllis
thanks for your interesting question.
By design and for consistency,
DoubleML
iterates over all treatments and fits all nuisance models for each treatment. This happens even if a nuisance target is independent of the individual treatments. This explains the dimensionality.Since you use
data = DoubleMLData.from_arrays(x=Z, y=Y, d=T)
the default valueuse_other_treat_as_covariate=True
is set and thus, for each treatment, all other 49 treatments join the set of covariates when estimating ml_l and ml_m.If you'd like to set
use_other_treat_as_covariate=False
and avoid recalculatingml_l
, you can use the doubleml samples to create one set of predictions, broadcast them on…