kernelSx

The function evaluates the matrix of design weights to
 predict the response at arbitrary locations x.
 This function is not intended to be used directly.

smooth

Multivariate smoothing using iterative bias reduction with kernel, thin plate splines, Duchon splines or low rank splines.

Pierre-Andre Cornillon

Iterative Bias Reduction

kernelSx function

<dl> <dt>kernelx</dt>
<dd>Character string which allows to choose between gaussian kernel
 (<code>"g"</code>), Epanechnikov (<code>"e"</code>), uniform (<code>"u"</code>),
 quartic (<code>"q"</code>).</dd> <dt>X</dt>
<dd>Matrix of explanatory variables, size n, p.</dd> <dt>Xetoile</dt>
<dd>Matrix of new design points x* at which to predict the
 response variable, size n*, p.</dd> <dt>bx</dt>
<dd>The vector of different bandwidths, length \(p\).</dd></dl>

Arguments

Pierre-Andre Cornillon, Nicolas Hengartner and Eric Matzner-Lober.

Author

Evaluates the smoothing matrix at x* — kernelSx

<dl>

 <dt>kernelx</dt>
<dd>Character string which allows to choose between gaussian kernel
 (<code>"g"</code>), Epanechnikov (<code>"e"</code>), uniform (<code>"u"</code>),
 quartic (<code>"q"</code>).</dd>

 <dt>X</dt>
<dd>Matrix of explanatory variables, size n, p.</dd>

 <dt>Xetoile</dt>
<dd>Matrix of new design points x* at which to predict the
 response variable, size n*, p.</dd>

 <dt>bx</dt>
<dd>The vector of different bandwidths, length \(p\).</dd>

</dl>

kernelSx: Evaluates the smoothing matrix at x*

Description

Usage

Value

Arguments

Author

See Also