SieveMinimumDistance

Guide & worked example · Source

SieveMinimumDistance(
    model,
    moment_function,
    degree=3,
    include_interactions=True,
    include_intercept=True,
    ridge=1e-06,
    **kwargs,
)

Polynomial-sieve minimum distance estimator for conditional moments.

The criterion is the quadratic norm of sample moments interacted with a polynomial instrument basis:

trace(M(theta)' W M(theta)), where M = F(z)' psi(theta) / n.

Attributes

Name	Description
`basis_`
`degree`
`device`
`dtype`
`history`
`include_interactions`
`include_intercept`
`lr`
`maxiter`
`model`
`moment_function`
`optimizer_class`
`optimizer_kwargs`
`params`
`ridge`
`weighting_matrix_`
`z_mean_`
`z_scale_`

Methods

Name	Description
fit
moments	Evaluate sample moments at the current model parameters.
predict	Predict with the fitted structural model.
summary	Print a summary of the model results.
to

fit

SieveMinimumDistance.fit(t, y, z, verbose=False)

moments

SieveMinimumDistance.moments(t, y)

Evaluate sample moments at the current model parameters.

predict

SieveMinimumDistance.predict(t)

Predict with the fitted structural model.

summary

SieveMinimumDistance.summary()

Print a summary of the model results.

to

SieveMinimumDistance.to(device)