NSSDNResult.observed#

property NSSDNResult.observed: NDArray[float64][source]#

(r,) the slice of endog the path rows align with.

The whole series under the filtered alignment, endog[1:] under the predicted one, so that observed[i] is the observation row i of every path refers to.

Example

>>> import numpy as np
>>> y = np.sin(0.2 * np.arange(100.0))
>>> res = NSSDN(y, k=2, state_dim=8, schedule=(Stage(1e-2, 10),), seed=0).fit()
>>> res.observed.shape == res.emission.shape
True