bayespecon.dgp.generate_panel_sem_flow_data¶

bayespecon.dgp.generate_panel_sem_flow_data(n=None, T=5, G=None, lam_d=0.3, lam_o=0.2, lam_w=0.1, beta_d=None, beta_o=None, sigma=1.0, sigma_alpha=0.5, gamma_dist=-0.5, seed=None, k=None, err_hetero=False, gdf=None, knn_k=4, distribution='lognormal')[source]¶

Simulate panel SEM flow data with O-D-pair random effects.

Per-period DGP:

\[\eta_t = X_t\beta + \alpha + B^{-1}\varepsilon_t, \quad \varepsilon_t \sim \mathcal{N}(0, \sigma^2 I_N).\]

Panel analogue of generate_panel_flow_data() for SEM. Use to generate training data for SEMFlowPanel.