WeightedSumFitter.priors_from_data#

WeightedSumFitter.priors_from_data(X, y)[source]#

Set Dirichlet prior for weights based on number of control units.

For synthetic control models, this method sets the shape parameter of the Dirichlet prior on the control unit weights (beta) to be uniform across all available control units. This ensures that all control units have equal prior probability of contributing to the synthetic control.

Parameters:

X (xarray.DataArray) – Control unit data with shape (n_obs, n_control_units).
y (xarray.DataArray) – Treated unit outcome data.

Returns:

Dictionary containing: - “beta”: Dirichlet prior with shape=(1,…,1) for n_control_units

Return type:

Dict[str, Prior]