cband {mixreg}R Documentation

Calculate confidence and prediction bands for mixtures of one-variable regressions.

Description

Produces confidence and prediction bands, two-sided or upper or lower, for the lines fitted in a model consisting of a mixture of one-variable regressions.

Usage

cband(object, cov.mat, x, y, alpha=0.05, xlen=100, plotit=FALSE,
      type=NULL)

Arguments

object Object describing the fitted mixture of regressions, as returned by mixreg.
cov.mat The estimated covariance matrix of the parameter estimates of the fit, as returned by covmix.
x The vector of predictors for each of the regression models in the mixture. Only one-dimensional predictors are permitted here.
y The vector of responses for the regression models.
alpha One minus the confidence level for the confidence and prediction bands; e.g. alpha = 0.05 for 95% confidence.
xlen The number of points to be plotted in the band envelopes. The x-values of the points will be equi-spaced from min(x) to max(x).
plotit Logical argument indicating whether to plot the fitted model and confidence bands.
type Character argument specifying the type of band. Must have one of the values "both", "upper", or "lower". Defaults to "both".

Details

The prediction bands are conditional in that the associated probability is condtional upon the associated observation being generated by the relevant component of the mixture.

Value

A list (of class "cband") with components

theta The parameter list from object (as returned by mixreg).
intercept The logical value from object indicating whether intercepts were fitted.
x The argument x of the call to cband.
y The argument y of the call to cband.
xf The equispaced sequence of values from min(x) to max(x) at which the values of the band envelopes were calculated.
bnds A list with one entry for each component of the mixture. Each entry is a matrix with 4 columns (lower and upper confidence, lower and upper prediction bounds) if type is "both", or with 2 columns (confidence bounds, prediction bounds) if type is "upper" or "lower".

Side Effects

If plotit is TRUE a plot of the fit and the confidence and prediction bands is produced in whatever device is currently open.

References

Turner, T. R. (2000) Estimating the rate of spread of a viral infection of potato plants via mixtures of regressions. Appl. Statist. vol. 49, Part 3, pp. 371 – 384.

See Also

bootcomp, covmix, mixreg, plot.cband, plot.mresid, qq.mix, resid.mix

Examples

#See mixreg for examples.

[Package mixreg version 0.0-2 Index]