Nested Nonparametric Instrumental Variable Regression
Home
Installation & Replication
1. Installation
1.1. Create and activate an environment
1.2. Install dependencies
1.3. Install the package
2. What’s in the box?
3. Quick start (library)
4. Reproducing the simulations
4.1. Folder layout
4.2. Nonparametric simulations (Table 1)
4.3. Semiparametric coverage simulations (Table 2)
4.4. Unified Slurm options
4.5. Notes on parallelism & threads
5. Empirical replications (notebooks)
Longitudinal Nested NPIV: Sequential (AGMM) vs Simultaneous (AGMM2L2)
Semiparametrics: DML (Mediated) with Neural Nets - AGMM (Sequential) and AGMM2L2 (Simultaneous)
6. Repository structure
7. Citing
8. License
Estimators for Sequential and Simultaneous Nested NPIV
Overview
Assumptions
Notation
Estimator Objectives
Progressive Recipe
Estimator Families
Regularized Kernel Hilbert Space
Closed form - Estimator 1
Closed form - Estimator 2
Closed form - Estimator 3
Closed form - Estimator 3 (RKHS norm)
Random Forest
Estimator 1
Estimator 2
Estimator 3
Estimator 3 - (Function class bounded)
Neural Networks
oadam.OAdam
Subsetted Estimator
Sparse Linear Function Spaces (
\(\ell_1-\ell_1\)
)
Estimator 1
Estimator 2
Estimator 3 - (Ridge)
Estimator 3 - (
\(\ell_1\)
-norm)
Regularized Linear Function Spaces (
\(\ell_2-\ell_2\)
)
Estimator 1
Estimator 2
Estimator 3 - (Ridge)
Estimator 3 - (
\(\ell_2\)
-norm)
Linear Class
tsls.tsls
tsls.regtsls
Related Pages
Estimation Diagnostics
Overview
Assumptions
Notation
Progressive Recipe
Canonical Diagnostics Reference
Universal Diagnostics API
Assumptions
Notation
Diagnostic A: Relative Well-posedness
Growing-sieve diagnostic (J and eta paths)
Post-estimation error-direction diagnostic (kappa_eff)
Post-estimation sieve path (kappa_eff by J and eta)
Availability and workflow
Plug-and-play usage with dataset blocks
Canonical nested NPIV shortcut
Related Pages
Semiparametric Estimation
Overview
Assumptions
Notation
Debiased Machine Learning Meta-Algorithm
Progressive Recipe
Model-Specific Semiparametric APIs
NPIV
dml_npiv.DML_npiv
Mediation Analysis
Different Estimands
Long-term Effect Analysis
Surrogacy Model
Latent Unconfounded Model
Related Pages
API Documentation
Overview
Longitudinal Estimator APIs
Longitudinal API Overview
RKHS Estimators
Ensemble and Random Forest Estimators
Neural Network Estimators
Sparse and Regularized Linear Estimators
TSLS Baselines
Diagnostics APIs
Semiparametric APIs
Semiparametric API Overview
NPIV Functional Inference
Mediation Analysis
Long-Term Effect Estimation
Related Pages
Nested Nonparametric Instrumental Variable Regression
»
API Documentation
»
Longitudinal API Overview
»
nnpiv.rkhs.ApproxRKHSIVL2CV
View page source
nnpiv.rkhs.ApproxRKHSIVL2CV
class
nnpiv.rkhs.
ApproxRKHSIVL2CV
(
kernel_approx
=
'nystrom'
,
n_components
=
10
,
kernel
=
'rbf'
,
gamma
=
2
,
degree
=
3
,
coef0
=
1
,
kernel_params
=
None
,
delta_scale
=
'auto'
,
delta_exp
=
'auto'
,
alpha_scales
=
'auto'
,
n_alphas
=
30
,
cv
=
6
)
[source]
Approximate RKHS IV L2 estimator with cross-validation.