Bind data to the statespace representation


Endogenous data to bind to the model. Must be column-ordered ndarray with shape (k_endog, nobs) or row-ordered ndarray with shape (nobs, k_endog).


The strict requirements arise because the underlying statespace and Kalman filtering classes require Fortran-ordered arrays in the wide format (shaped (k_endog, nobs)), and this structure is setup to prevent copying arrays in memory.

By default, numpy arrays are row (C)-ordered and most time series are represented in the long format (with time on the 0-th axis). In this case, no copying or re-ordering needs to be performed, instead the array can simply be transposed to get it in the right order and shape.

Although this class (Representation) has stringent bind requirements, it is assumed that it will rarely be used directly.

Last update: Dec 14, 2023