Smoothed covariances: C[i][j][time]
Initial state covariance
Filtered covariances: Cf[i][j][time]
Class identifier
Innovation covariances
Observation matrix. p=1: [m] row vector (backward compat). p>1: [p, m].
State transition matrix
-2 · log-likelihood
State dimension
Mean absolute percentage error
Mean squared error
Number of observations
Number of non-NaN observations
Observation dimension
Scaled residuals
Raw residuals
Standardized residuals
Residual variance
Sum of squared residuals
Innovations
Observation noise std devs
State noise covariance
Smoothed states: x[state][time]
Initial state mean
Filtered states: xf[state][time]
Smoothed state std devs: xstd[time][state]
Covariates matrix
Observations
Fitted values
Prediction standard deviations
MATLAB DLM-compatible result layout and names. Produced by toMatlab. State arrays use the MATLAB convention:
x[stateIdx][timeIdx],C[i][j][timeIdx],xstd[timeIdx][stateIdx].