estfun.gam

This extracts the score of the log-likelihood for each observation for a
model estimated using <code>gam</code> or <code>bam</code>. It is necessary to allow
<code>mgcv</code> to work correctly with functions from <code>sandwich</code> to product
cluster or robust standard errors.

internal

Kernel regularized least squares, also known as kernel ridge regression,
is a flexible machine learning method. This package implements this method by
providing a smooth term for use with 'mgcv' and uses random sketching to
facilitate scalable estimation on large datasets. It provides additional
functions for calculating marginal effects after estimation and for use with
ensembles ('SuperLearning'), double/debiased machine learning ('DoubleML'),
and robust/clustered standard errors ('sandwich'). Chang and Goplerud (2024)
<doi:10.1017/pan.2023.27> provide further details.

Max Goplerud

gKRLS

Generalized Kernel Regularized Least Squares

Qing Chang

estfun.gam function

<dl><dt>x</dt>
<dd>A model estimated using <code>gam</code> or <code>bam</code>.</dd>
<dt>correct_df</dt>
<dd>The default, <code>TRUE</code>, adjusts <code>sandwich</code> to use the
effective degrees of freedom for <code>k</code> instead of the number of columns
of the design. <code>FALSE</code> uses <code>k</code>.</dd>
<dt>override_check</dt>
<dd>The default, <code>FALSE</code>, allows this function to be
used inside of <code>sandwich</code>. If only the matrix of scores is required,
set to <code>TRUE</code>.</dd>
<dt>...</dt>
<dd>Not used for <code>estfun.gam</code>.</dd></dl>

Arguments

Estimating Robust/Clustered Standard Errors with mgcv — estfun.gam

<dl>

<dt>x</dt>
<dd>A model estimated using <code>gam</code> or <code>bam</code>.</dd>


<dt>correct_df</dt>
<dd>The default, <code>TRUE</code>, adjusts <code>sandwich</code> to use the
effective degrees of freedom for <code>k</code> instead of the number of columns
of the design. <code>FALSE</code> uses <code>k</code>.</dd>


<dt>override_check</dt>
<dd>The default, <code>FALSE</code>, allows this function to be
used inside of <code>sandwich</code>. If only the matrix of scores is required,
set to <code>TRUE</code>.</dd>


<dt>...</dt>
<dd>Not used for <code>estfun.gam</code>.</dd>

</dl>

estfun.gam: Estimating Robust/Clustered Standard Errors with `mgcv`

Description

Usage

Value

Arguments