get_sigma_yx

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>.

Xinyu DAI

rbbnp

A Bias Bound Approach to Non-Parametric Inference

Susanne M Schennach

get_sigma_yx function

<dl><dt>Y</dt>
<dd>A numerical vector representing the sample data of variable Y.</dd>
<dt>X</dt>
<dd>A numerical vector representing the sample data of variable X.</dd>
<dt>x</dt>
<dd>The specific point at which sigma_yx is to be estimated.</dd>
<dt>h</dt>
<dd>A bandwidth parameter used in the kernel function for smoothing.</dd>
<dt>inf_k</dt>
<dd>A kernel function used to weigh observations in the neighborhood of point x.</dd></dl>

Arguments

Estimation of sigma_yx — get_sigma_yx

<dl>

<dt>Y</dt>
<dd>A numerical vector representing the sample data of variable Y.</dd>


<dt>X</dt>
<dd>A numerical vector representing the sample data of variable X.</dd>


<dt>x</dt>
<dd>The specific point at which sigma_yx is to be estimated.</dd>


<dt>h</dt>
<dd>A bandwidth parameter used in the kernel function for smoothing.</dd>


<dt>inf_k</dt>
<dd>A kernel function used to weigh observations in the neighborhood of point x.</dd>

</dl>

get_sigma_yx: Estimation of sigma_yx

Description

Usage

Value

Arguments