rbbnp0.3.0 package

A Bias Bound Approach to Non-Parametric Inference

biasBound_condExpectation

Bias bound approach for conditional expectation estimation

biasBound_density

Bias bound approach for density estimation

create_biasBound_config

Create a configuration object for bias bound estimations

create_kernel_functions

Create kernel functions based on configuration

cv_bandwidth

Cross-Validation for Bandwidth Selection

DATA_PATH

The Path to the Data Folder

epanechnikov_kernel_ft

Fourier Transform Epanechnikov Kernel

epanechnikov_kernel

Epanechnikov Kernel

EXT_DATA_PATH

The Path to the External Data Folder for Non-R Data Files

fun_approx

Approximation Function for Intensive Calculations

gen_sample_data

Generate Sample Data

get_avg_f1x

Kernel point estimation

get_avg_fyx

Kernel point estimation

get_avg_phi_log

Compute log sample average of fourier transform and get mod

get_avg_phi

Compute Sample Average of Fourier Transform Magnitude

get_conditional_var

get the conditional variance of Y on X for given x

get_est_Ar

get the estimation of A and r

get_est_B

get the estimation of B

get_est_b1x

Estimation of bias b1x

get_est_byx

Estimation of bias byx

get_est_vy

get the estimation of Vy

get_sigma_yx

Estimation of sigma_yx

get_sigma

Estimation of sigma

get_xi_interval

get xi interval

kernel_reg

Kernel Regression function

normal_kernel_ft

Fourier Transform of Normal Kernel

normal_kernel

Normal Kernel Function

plot_ft

Plot the Fourier Transform

rpoly01

Generate n samples from the distribution

select_bandwidth

Select Optimal Bandwidth

silverman_bandwidth

Silverman's Rule of Thumb for Bandwidth Selection

sinc_ft

Define the closed form FT of the infinite order kernel sin(x)/(pi*x)

sinc

Infinite Kernel Function

true_density_2fold

True density of 2-fold uniform distribution

W_kernel_ft

Define the Fourier transform of a infinite kernel proposed in Schennac...

W_kernel

Define the inverse Fourier transform function of W

A novel bias-bound approach for non-parametric inference is introduced, focusing on both density and conditional expectation estimation. It constructs valid confidence intervals that account for the presence of a non-negligible bias and thus make it possible to perform inference with optimal mean squared error minimizing bandwidths. This package is based on Schennach (2020) <doi:10.1093/restud/rdz065>.