get_Q

Estimates the spectral transformation Q for spectral deconfounding by 
shrinking the leading singular values of the covariates.

Screen for and analyze non-linear sparse direct effects in the presence of unobserved confounding using the spectral deconfounding techniques (Ćevid, Bühlmann, and Meinshausen (2020)<jmlr.org/papers/v21/19-545.html>, Guo, Ćevid, and Bühlmann (2022) <doi:10.1214/21-AOS2152>). These methods have been shown to be a good estimate for the true direct effect if we observe many covariates, e.g., high-dimensional settings, and we have fairly dense confounding. Even if the assumptions are violated, it seems like there is not much to lose, and the deconfounded models will, in general, estimate a function closer to the true one than classical least squares optimization. 'SDModels' provides functions SDAM() for Spectrally Deconfounded Additive Models (Scheidegger, Guo, and Bühlmann (2025) <doi:10.1145/3711116>) and SDForest() for Spectrally Deconfounded Random Forests (Ulmer, Scheidegger, and Bühlmann (2025) <doi:10.48550/arXiv.2502.03969>).

Markus Ulmer

SDModels

Spectrally Deconfounded Models

Cyrill Scheidegger

get_Q function

<dl><dt>X</dt>
<dd>Numerical covariates of class <code>matrix</code>.</dd>
<dt>type</dt>
<dd>Type of deconfounding, one of 'trim', 'pca', 'no_deconfounding'. 
'trim' corresponds to the Trim transform Cevid2020SpectralModelsSDModels 
as implemented in the Doubly debiased lasso Guo2022DoublyConfoundingSDModels, 
'pca' to the PCA transformationPaul2008PreconditioningProblemsSDModels 
and 'no_deconfounding' to the Identity.</dd>
<dt>trim_quantile</dt>
<dd>Quantile for Trim transform, only needed for trim.</dd>
<dt>q_hat</dt>
<dd>Assumed confounding dimension, only needed for pca.</dd>
<dt>gpu</dt>
<dd>If <code>TRUE</code>, the calculations are performed on the GPU. 
If it is properly set up.</dd>
<dt>scaling</dt>
<dd>Whether X should be scaled before calculating the spectral transformation.</dd></dl>

Arguments

Author

Estimation of spectral transformation — get_Q

<dl>

<dt>X</dt>
<dd>Numerical covariates of class <code>matrix</code>.</dd>


<dt>type</dt>
<dd>Type of deconfounding, one of 'trim', 'pca', 'no_deconfounding'. 
'trim' corresponds to the Trim transform Cevid2020SpectralModelsSDModels 
as implemented in the Doubly debiased lasso Guo2022DoublyConfoundingSDModels, 
'pca' to the PCA transformationPaul2008PreconditioningProblemsSDModels 
and 'no_deconfounding' to the Identity.</dd>


<dt>trim_quantile</dt>
<dd>Quantile for Trim transform, only needed for trim.</dd>


<dt>q_hat</dt>
<dd>Assumed confounding dimension, only needed for pca.</dd>


<dt>gpu</dt>
<dd>If <code>TRUE</code>, the calculations are performed on the GPU. 
If it is properly set up.</dd>


<dt>scaling</dt>
<dd>Whether X should be scaled before calculating the spectral transformation.</dd>

</dl>

get_Q: Estimation of spectral transformation

Description

Usage

Value

Arguments

Author

References

Examples