Function for computing the basis matrix for restricted cubic splines which are constant beyond the last knot

Contains functions for estimating generalized parametric mixture and non-mixture cure models <doi:10.1016/j.cmpb.2022.107125>, loss of lifetime, mean residual lifetime, and crude event probabilities.

Lasse Hjort Jakobsen 

cuRe

Parametric Cure Model Estimation

Mark Clements 

Rasmus Kuhr Jensen 

Lars Klingen Gjærde 

cbc function

<dl><dt>x</dt>
<dd>Values to evaluate the basis functions in.</dd>
<dt>df</dt>
<dd>Degrees of freedom. One can supply <code>df</code> rather than knots; <code>cbc</code> then chooses <code>df + 1</code> knots
at suitably chosen quantiles of <code>x</code> (which will ignore missing values) and adds an additional knot at the 95th
quantile of <code>x</code>.</dd>
<dt>knots</dt>
<dd>Chosen knots for the spline.</dd>
<dt>ortho</dt>
<dd>Logical. If <code>TRUE</code> orthogonalization of the basis matrix is carried out.</dd>
<dt>R.inv</dt>
<dd>Matrix or vector containing the values of the R matrix from the QR decomposition of the basis matrix.
This is used for making new predictions based on the initial orthogonalization.
Therefore the default is <code>NULL</code>.</dd>
<dt>intercept</dt>
<dd>Logical. If <code>FALSE</code>, the intercept of the restricted cubic spline is removed.</dd></dl>

Arguments

Restricted cubic splines with cure — cbc

<dl>

<dt>x</dt>
<dd>Values to evaluate the basis functions in.</dd>


<dt>df</dt>
<dd>Degrees of freedom. One can supply <code>df</code> rather than knots; <code>cbc</code> then chooses <code>df + 1</code> knots
at suitably chosen quantiles of <code>x</code> (which will ignore missing values) and adds an additional knot at the 95th
quantile of <code>x</code>.</dd>


<dt>knots</dt>
<dd>Chosen knots for the spline.</dd>


<dt>ortho</dt>
<dd>Logical. If <code>TRUE</code> orthogonalization of the basis matrix is carried out.</dd>


<dt>R.inv</dt>
<dd>Matrix or vector containing the values of the R matrix from the QR decomposition of the basis matrix.
This is used for making new predictions based on the initial orthogonalization.
Therefore the default is <code>NULL</code>.</dd>


<dt>intercept</dt>
<dd>Logical. If <code>FALSE</code>, the intercept of the restricted cubic spline is removed.</dd>

</dl>

cbc: Restricted cubic splines with cure

Description

Usage

Value

Arguments

References