fit_lasso_poly

Compute regression function and derivative estimates based
on polynomial basis lasso with penalty parameter chosen by
cross validation (CV).

Doubly robust average partial effect estimation. This implementation contains methods for adding additional smoothness to plug-in regression procedures and for estimating score functions using smoothing splines. Details of the method can be found in Harvey Klyne and Rajen D. Shah (2023) <doi:10.48550/arXiv.2308.09207>.

Harvey Klyne

drape

Doubly Robust Average Partial Effects

fit_lasso_poly function

<dl><dt>X</dt>
<dd>matrix of covariates.</dd>
<dt>y</dt>
<dd>vector of responses.</dd>
<dt>degree</dt>
<dd>maximum degree of polynomial terms.</dd>
<dt>lambda</dt>
<dd>optional scalar tuning parameter, if "NULL" chosen via
cross-validation.</dd></dl>

Arguments

Fit a lasso regression using quadratic polynomial basis, with interactions. — fit_lasso_poly

<dl>

<dt>X</dt>
<dd>matrix of covariates.</dd>


<dt>y</dt>
<dd>vector of responses.</dd>


<dt>degree</dt>
<dd>maximum degree of polynomial terms.</dd>


<dt>lambda</dt>
<dd>optional scalar tuning parameter, if "NULL" chosen via
cross-validation.</dd>

</dl>

fit_lasso_poly: Fit a lasso regression using quadratic polynomial basis, with interactions.

Description

Usage

Value

Arguments