smooth.ADAM.persistence_vector

property ADAM.persistence_vector: Dict[str, Any]

$persistence).

Returns a dictionary containing the smoothing/persistence parameters that control how quickly the model adapts to new observations. Higher values mean faster adaptation (more weight on recent observations).

Returns:

Dictionary with keys persistence_level (alpha, 0-1), persistence_trend (beta, 0-alpha, only if model has trend), and persistence_seasonal (gamma, 0 to 1-alpha, only if model has seasonality).

Return type:

Dict[str, Any]

Raises:

ValueError – If the model has not been fitted yet.

See also

phi_

Damping parameter for trend

Examples

>>> model = ADAM(model="AAA", lags=12)
>>> model.fit(y)
>>> alpha = model.persistence_vector['persistence_level']
>>> gamma = model.persistence_vector['persistence_seasonal']

Type:

Estimated smoothing parameters (R