Gabriel Ristow Cidral
Gabriel Ristow Cidral
I am also curious about this implementation. It would be great to use both
that only happens in jupyter lab, jupyter nb works fine
I will start working on this :) Should we use a library like SparseSC or develop internally the algorithm? Also, the p-value here is calculated using permutation between control and...
Yes I think we can use our own implementation. We can create a new class SyntheticControlAnalysis in experiment_analysis.py, but I think part of the logic should be in a new...
Also, just to confirm we're in the same page: In a case of synthetic control, normally the data it's observational, so we know the treatment and control groups. However, in...
Our use case is to perturbate effect on profit margin, where it can be either positive or negative. You can expand this other financial metrics, such as profit in monetary...
@david-jankoski can you close this issue as it`s fixed please? Thanks!!
exactly! We can also set as an input how "aggressive" this increase of alpha can be.So it can follow a function like this (@matheusbuniotto's idea): 