More Flexible API for Multiple Testing Corrections

[s3alfisc]

Context

Currently, it is only possible to control for multiple testing for hypothesis of the same parameter, against the same null.

from pyfixest.estimation import feols
from pyfixest.utils import get_data
from pyfixest.multcomp import rwolf

data = get_data().dropna()
fit = feols("Y ~ Y2 + X1 + X2", data=data)
rwolf(fit.to_list(), "X1", reps=9999, seed=123)

E.g. for a set of regression models $s = 1, ..., S$, we can only test that $\beta_{ks} = 0$ for a parameter k. In the example above, the parameter to be tested, "X1", needs to be fixed across models. It is not possible to e.g. test more complex hypotheses, as e.g. $\beta_{1,1} = 0$, $\beta_{1,2} = 0$, etc.

To Do

• Define an API that allows users to test more complex hypotheses via bonferroni() and rwolf(). We can draw some inspiration from the rwolf2 Stata module.
• Then, implement it =)