bayespecon.dgp.generate_panel_flow_data_separable¶
-
bayespecon.dgp.generate_panel_flow_data_separable(n=
None, T=5, G=None, rho_d=0.3, rho_o=0.2, beta_d=None, beta_o=None, **kwargs)[source]¶ Simulate panel flow data from a separable SAR flow model.
Identical to
generate_panel_flow_data()except the network parameter is derived as \(\rho_w = -\rho_d \rho_o\). Use this function to generate training data forSARFlowSeparablePanel.- Parameters:¶
- n : int¶
Number of spatial units.
- T : int¶
Number of time periods.
- G : libpysal.graph.Graph¶
Row-standardised spatial graph on n units.
- rho_d : float¶
Destination spatial autoregressive parameter.
- rho_o : float¶
Origin spatial autoregressive parameter.
- beta_d : array-like, shape (k,)¶
Destination-side regression coefficients.
- beta_o : array-like, shape (k,)¶
Origin-side regression coefficients.
- **kwargs¶
Forwarded to
generate_panel_flow_data()(e.g.sigma,sigma_alpha,seed).
- Returns:¶
Same as
generate_panel_flow_data(). The"rho_w"entry will equal-rho_d * rho_o.- Return type:¶