neighbayes.dgp.simulate_sem_logit

neighbayes.dgp.simulate_sem_logit(W=None, gdf=None, n_side=None, lam=0.35, beta=None, err_hetero=False, rng=None, seed=None, contiguity='queen', create_gdf=False, geometry_type='polygon', *, unit_effects=None)[source]

Simulate the latent SEM logit that SEMLogit fits.

DGP

y* = X beta + (I - lam W)^{-1} eps, eps iid standard logistic, y = 1(y* > 0).

param W:

Spatial unit structure, as for simulate_sar_logit().

param gdf:

Spatial unit structure, as for simulate_sar_logit().

param n_side:

Spatial unit structure, as for simulate_sar_logit().

param contiguity:

Spatial unit structure, as for simulate_sar_logit().

param lam:

Spatial error parameter.

type lam:

float, default=0.35

param beta:

Coefficients including intercept. Defaults to [0.3, 1.0].

type beta:

np.ndarray, optional

param err_hetero:

Scale each logistic disturbance by sqrt(1 + ||x_i||^2), a heteroskedastic departure from the model.

type err_hetero:

bool, default False

param rng:

Random state controls.

param seed:

Random state controls.

param create_gdf:

As for simulate_sar_logit().

param geometry_type:

As for simulate_sar_logit().

returns:

Dict with keys y, X, W_sparse, W_graph, eta_true (the latent utility y*) and params_true.

rtype:

dict or geopandas.GeoDataFrame