spa_pls

SwPA-PLS provides the influence of each variable without considering the 
influence of the rest of the variables through sub-sampling of samples and variables.

Interfaces and methods for variable selection in Partial Least
Squares. The methods include filter methods, wrapper methods and embedded
methods. Both regression and classification is supported.

Kristian Hovde Liland

plsVarSel

Variable Selection in Partial Least Squares

Tahir Mehmood

Solve Sæbø

spa_pls function

<dl><dt>y</dt>
<dd>vector of response values (<code>numeric</code> or <code>factor</code>).</dd>
<dt>X</dt>
<dd>numeric predictor <code>matrix</code>.</dd>
<dt>ncomp</dt>
<dd>integer number of components (default = 10).</dd>
<dt>N</dt>
<dd>number of Monte Carlo simulations (default = 3).</dd>
<dt>ratio</dt>
<dd>the proportion of the samples to use for calibration (default = 0.8).</dd>
<dt>Qv</dt>
<dd>integer number of variables to be sampled in each iteration (default = 10).</dd>
<dt>SPA.threshold</dt>
<dd>thresholding to remove non-important variables (default = 0.05).</dd></dl>

Arguments

Tahir Mehmood, Kristian Hovde Liland, Solve Sæbø.

Author

Sub-window permutation analysis coupled with PLS (SwPA-PLS) — spa_pls

<dl>

<dt>y</dt>
<dd>vector of response values (<code>numeric</code> or <code>factor</code>).</dd>


<dt>X</dt>
<dd>numeric predictor <code>matrix</code>.</dd>


<dt>ncomp</dt>
<dd>integer number of components (default = 10).</dd>


<dt>N</dt>
<dd>number of Monte Carlo simulations (default = 3).</dd>


<dt>ratio</dt>
<dd>the proportion of the samples to use for calibration (default = 0.8).</dd>


<dt>Qv</dt>
<dd>integer number of variables to be sampled in each iteration (default = 10).</dd>


<dt>SPA.threshold</dt>
<dd>thresholding to remove non-important variables (default = 0.05).</dd>

</dl>

spa_pls: Sub-window permutation analysis coupled with PLS (SwPA-PLS)

Description

Usage

Value

Arguments

Author

References

See Also

Examples