Longitudinal API Overview

This page lists public estimator APIs for sequential and simultaneous nested NPIV estimation. Use the domain pages for mathematical development and this page for direct class/function lookup.

RKHS Estimators

nnpiv.rkhs.RKHSIV([kernel, gamma, degree, ...])

RKHS IV estimator.

nnpiv.rkhs.RKHSIVCV([kernel, gamma, degree, ...])

RKHS IV estimator with cross-validation.

nnpiv.rkhs.ApproxRKHSIV([kernel_approx, ...])

Approximate RKHS IV estimator using kernel approximations.

nnpiv.rkhs.ApproxRKHSIVCV([kernel_approx, ...])

Approximate RKHS IV estimator with cross-validation using kernel approximations.

nnpiv.rkhs.RKHSIVL2([kernel, gamma, degree, ...])

RKHS IV estimator with L2 regularization.

nnpiv.rkhs.RKHSIVL2CV([kernel, gamma, ...])

RKHS IV estimator with L2 regularization and cross-validation.

nnpiv.rkhs.ApproxRKHSIVL2([kernel_approx, ...])

Approximate RKHS IV estimator with L2 regularization.

nnpiv.rkhs.ApproxRKHSIVL2CV([kernel_approx, ...])

Approximate RKHS IV L2 estimator with cross-validation.

nnpiv.rkhs.RKHS2IV([kernel, gamma, degree, ...])

Nested RKHS IV estimator.

nnpiv.rkhs.RKHS2IVCV([kernel, gamma, ...])

Cross-validated RKHS2IV estimator.

nnpiv.rkhs.RKHS2IVL2([kernel, gamma, ...])

Nested RKHS IV estimator with L2 regularization.

nnpiv.rkhs.RKHS2IVL2CV([kernel, gamma, ...])

Cross-validated RKHS2IVL2 estimator.

nnpiv.rkhs.ApproxRKHS2IV([kernel_approx, ...])

Approximate alternate simultaneous RKHS estimator using finite kernel features.

nnpiv.rkhs.ApproxRKHS2IVCV([kernel_approx, ...])

Cross-validated approximate alternate simultaneous RKHS estimator.

nnpiv.rkhs.ApproxRKHS2IVL2([kernel_approx, ...])

Approximate Appendix J / Algorithm 2 RKHS estimator using finite kernel features.

nnpiv.rkhs.ApproxRKHS2IVL2CV([...])

Cross-validated approximate Appendix J / Algorithm 2 RKHS estimator.

Ensemble and Random Forest Estimators

nnpiv.ensemble.EnsembleIV([adversary, ...])

Implements an ensemble learning IV method with adversarial and learner components.

nnpiv.ensemble.EnsembleIVStar([adversary, ...])

Similar to EnsembleIV but with a different method for updating the test predictions using a linear combination approach.

nnpiv.ensemble.EnsembleIVL2([adversary, ...])

An extension of EnsembleIV with L2 regularization and optional cross-validation to select the best regularization parameter.

nnpiv.ensemble.Ensemble2IV([adversary, ...])

Implements a nested ensemble learning IV method with two adversaries and two learners.

nnpiv.ensemble.Ensemble2IVL2([adversary, ...])

An extension of Ensemble2IV with L2 regularization and optional cross-validation to select the best regularization parameter.

Neural Network Estimators

nnpiv.neuralnet.AGMM(learner, adversary)

Adversarial Generalized Method of Moments estimator.

nnpiv.neuralnet.KernelLayerMMDGMM(learner, ...)

AGMM with kernel layer using Maximum Mean Discrepancy.

nnpiv.neuralnet.CentroidMMDGMM(learner, ...)

AGMM with centroid-based Maximum Mean Discrepancy.

nnpiv.neuralnet.KernelLossAGMM(learner, ...)

AGMM with kernel loss.

nnpiv.neuralnet.MMDGMM(learner, adversary_g, ...)

AGMM with Maximum Mean Discrepancy.

nnpiv.neuralnet.AGMM2L2(learnerh, learnerg, ...)

Adversarial Generalized Method of Moments estimator for nested NPIV with L2 regularization.

Sparse and Regularized Linear Estimators

nnpiv.linear.sparse_l1vsl1([lambda_theta, ...])

Sparse Linear NPIV estimator using \(\ell_1-\ell_1\) optimization.

nnpiv.linear.sparse_ridge_l1vsl1([...])

Sparse Ridge NPIV estimator using \(\ell_1-\ell_1\) optimization.

nnpiv.linear.sparse2_l1vsl1([mu, V1, V2, ...])

Sparse Linear NPIV estimator using \(\ell_1-\ell_1\) optimization for nested NPIV.

nnpiv.linear.sparse2_ridge_l1vsl1([mu, V1, ...])

Sparse Ridge NPIV estimator using \(\ell_1-\ell_1\) optimization for nested NPIV.

nnpiv.linear.sparse_l2vsl2([lambda_theta, ...])

Sparse Linear NPIV estimator using \(\ell_2-\ell_2\) optimization.

nnpiv.linear.sparse_ridge_l2vsl2([...])

Sparse Ridge NPIV estimator using \(\ell_2-\ell_2\) optimization.

nnpiv.linear.sparse2_l2vsl2([mu, V1, V2, ...])

Sparse Linear NPIV estimator using \(\ell_2-\ell_2\) optimization for nested NPIV.

nnpiv.linear.sparse2_ridge_l2vsl2([mu, V1, ...])

Sparse Ridge NPIV estimator using \(\ell_2-\ell_2\) optimization for nested NPIV.

TSLS Baselines

nnpiv.tsls.tsls()

Two-stage least squares estimator.

nnpiv.tsls.regtsls([cv, n_alphas])

Regularized two-stage least squares estimator using Elastic Net.