default.knots

Computes default knots for a given x vector.

Fits semiparametric additive regression models with spatially adaptive penalized splines and computes simultaneous confidence bands and associated specification (lack-of-fit) tests. Simultaneous confidence bands cover the entire curve with a prescribed level of confidence and allow us to assess the estimation uncertainty for the whole curve. In contrast to pointwise confidence bands, they permit statements about the statistical significance of certain features (e.g. bumps) in the underlying curve.The method allows for handling of spatially heterogeneous functions and their derivatives as well as heteroscedasticity in the data. See Wiesenfarth et al. (2012) <doi:10.1080/01621459.2012.682809>.

Manuel Wiesenfarth

AdaptFitOS

Adaptive Semiparametric Additive Regression with Simultaneous
Confidence Bands and Specification Tests

Tatyana Krivobokova

Matt Wand

Catherine Loader

Jiayang Sun

Lucent Technologies 

default.knots function

<dl> <dt>x</dt>
<dd>The covariate. Note that for B-splines, only the range of <code>x</code> is considered.</dd> <dt>num.knots</dt>
<dd>The number of knots. Defaults to <code>floor(n/max(4, floor(n/35)) - 1)</code>.</dd> <dt>knotchoice</dt>
<dd>Either "equidistant" or "quantiles" for equidistant and quantile based knots, respectively. Note that in case of B-splines, knots are always equidistant.</dd></dl>

Arguments

Compute default knots for a given x vector — default.knots

<dl>

 <dt>x</dt>
<dd>The covariate. Note that for B-splines, only the range of <code>x</code> is considered.</dd>

 <dt>num.knots</dt>
<dd>The number of knots. Defaults to <code>floor(n/max(4, floor(n/35)) - 1)</code>.</dd>

 <dt>knotchoice</dt>
<dd>Either "equidistant" or "quantiles" for equidistant and quantile based knots, respectively. Note that in case of B-splines, knots are always equidistant.</dd>

</dl>

default.knots: Compute default knots for a given x vector

Description

Usage

Arguments