np.graph {ssym}

Tool to plot natural cubic splines or P-splines.

Description

np.graph displays a graph of a fitted nonparametric effect, either natural cubic spline or P-spline, from an object of class ssym.

Usage

np.graph(object, which, var, exp, simul, obs, xlab, ylab, xlim, ylim, main)

Arguments

object

an object of the class ssym. This object is returned from the call to ssym.l(), ssym.nl() or ssym.l2().

which

an integer indicating the interest submodel. For example, 1 indicates location submodel, and 2 indicates skewness (or relative dispersion) submodel.

var

character. It allows to choosing the nonparametric effect using the name of the associated explanatory variable.

exp

logical. If TRUE, the fitted nonparametric effect is plotted in exponential scale. Default is FALSE.

simul

logical. If TRUE, the fitted nonparametric effect is plotted jointly with their 95\% simultaneous confidence intervals. If TRUE, the fitted nonparametric effect is plotted jointly with their 95\% pointwise confidence intervals. Default is TRUE.

obs

logical. If TRUE, the fitted nonparametric effect is plotted jointly with the observed data. Default is FALSE.

xlab

character. An optional label for the x axis.

ylab

character. An optional label for the y axis.

xlim

numeric. An optional range of values for the x axis.

ylim

numeric. An optional range of values for the y axis.

main

character. An optional overall title for the plot.

Author(s)

Luis Hernando Vanegas <[e-mail]> and Gilberto A. Paula

References

Lancaster, P. and Salkauskas, K. (1986) Curve and Surface Fitting: an introduction. Academic Press, London. Green, P.J. and Silverman, B.W. (1994) Nonparametric Regression and Generalized Linear Models, Boca Raton: Chapman and Hall. Eilers P.H.C. and Marx B.D. (1996). Flexible smoothing with B-splines and penalties. Statistical Science. 11, 89-121.

Examples

#data("Ovocytes", package="ssym")
#fit <- ssym.l(fraction ~ type + psp(time) | type + psp(time), data=Ovocytes,
#              family='Powerexp', xi=-0.55)
#
#par(mfrow = c(1,2))
#np.graph(fit, which=1, xlab="Time", main="Location")
#np.graph(fit, which=2, exp=TRUE, xlab="Time", main="Dispersion")