StateSpaceTimeSeries.sample_posterior

StateSpaceTimeSeries.sample_posterior(**kwargs)

Sample the posterior phase and attach Kalman-smoothed predictions.

Parameters:

**kwargs (Any) – Keyword arguments override sample_kwargs.

Return type:

DataTree

Notes

After NUTS and posterior predictive sampling, the conditional (smoothed) posterior replaces the posterior_predictive group with y_hat / mu on CausalPy’s canonical dimensions.