Malte S. Kurz
Malte S. Kurz
We do have unit tests for model defaults, see https://github.com/DoubleML/doubleml-for-py/blob/master/doubleml/tests/test_doubleml_model_defaults.py. The intention behind such "default setting unit tests" is twofold: 1) It should assert that the defaults are valid /...
### Describe the bug Bug reported by @ShreyDixit: Assume that one successfully initializes an object of class `DoubleMLData`. Then alters a property like `y_col` in a way that violates some...
Currently we only check that predictions are finite in https://github.com/DoubleML/doubleml-for-py/blob/b3cbdb572fce435c18ec67ca323645900fc901b5/doubleml/_utils.py#L204-L208 We may additionally want to check that estimated probabilities are strictly in `(0,1)` (maybe with some eps threshold). Otherwise, the...
See https://twitter.com/natfriedman/status/1420122675813441540 & https://github.com/citation-file-format/citation-file-format.
### Trimming as part of the ML estimation and prediction step - At the moment the trimming of propensity scores is part of the "score evaluation step", see https://github.com/DoubleML/doubleml-for-py/blob/6ea72e4491bb219fade53b569a199823162fe8d4/doubleml/double_ml_irm.py#L199-L201 -...
See also https://github.com/DoubleML/doubleml-for-r/issues/83
Indended behavior (and execption handling / warning) of repetitive calls to `set_ml_nuisance_params`
* If the function `set_ml_nuisance_params('ml_g', 'd', params)` is being called multiple times it results in the last `params` dict being used. * I think this behavior is fine, but I...
The dimensions in the docu at the moment reflect the single treatment variable case only, see 
In the python package `DoubleML`, we do have unit tests for model defaults, see https://github.com/DoubleML/doubleml-for-py/blob/master/doubleml/tests/test_doubleml_model_defaults.py. The intention behind such "default setting unit tests" is twofold: 1. It should assert that...