Calculates the design matrix, Z, of the random effects for a natural cubic smoothing spline as described by Verbyla et al., (1999). An initial design matrix, \(\bold{\Delta} \bold{\Delta}^{-1} \bold{\Delta}\), based on the knot points is computed. It can then be post multiplied by the power of the tri-diagonal matrix \(\bold{G}_s\) that is proportional to the variance matrix of the random spline effects. If the power is set to 0.5 then the random spline effects based on the resulting Z matrix will be independent with variance \(\sigma_s^2\).
Zncsspline(knot.points, Gpower = 0, print = FALSE)
A numeric
giving the values of the knot points
to be used in fitting the spline. These must be orderd in increasing order.
A numeric
giving the power of the tri-diagonal matrix
\(\bold{G}_s\) from which the variance matrix of the random spline
effects is caluclated. that the initial design matrix is to be
the value of the variance component for the random spline effects.
The smoothing parameter is then the inverse of the ratio of this
component to the residual variance.
A logical
indicating whether to print the
\(\bold{\Delta}\) and \(\bold{G}_s\) matrices.
A matrix
containing the design matrix.
Verbyla, A. P., Cullis, B. R., Kenward, M. G., and Welham, S. J. (1999). The analysis of designed experiments and longitudinal data by using smoothing splines (with discussion). Journal of the Royal Statistical Society, Series C (Applied Statistics), 48, 269-311.
# NOT RUN {
Z <- Zncsspline(knot.points = 1:10, Gpower = 0.5)
# }
Run the code above in your browser using DataLab