predict.fregre.gls: Predictions from a functional gls object

In fda.usc: Functional Data Analysis and Utilities for Statistical Computing

Predictions from a functional gls object

Description

The predictions for the functional generalized least squares fitted linear model represented by object are obtained at the covariate values defined in newx.

Usage

## S3 method for class 'fregre.gls'
predict(
  object,
  newx = NULL,
  type = "response",
  se.fit = FALSE,
  scale = NULL,
  df,
  interval = "none",
  ...
)

## S3 method for class 'fregre.igls'
predict(
  object,
  newx = NULL,
  data,
  df = df,
  weights = 1,
  pred.var,
  n.ahead = 1L,
  ...
)

Arguments

object	fregre.gls object.
newx	An optional data list in which to look for variables with which to predict. If omitted, the fitted values are used. List of new explanatory data.
type	Type of prediction (response or model term).
se.fit	=TRUE (not default) standard error estimates are returned for each prediction.
scale	Scale parameter for std.err. calculation.
df	Degrees of freedom for scale.
interval	Type of interval calculation.
...	Further arguments passed to or from other methods.
data	Data frame with the time or spatinal index
weights	variance weights for prediction. This can be a numeric vector or a one-sided model formula. In the latter case, it is interpreted as an expression evaluated in newdata
pred.var	the variance(s) for future observations to be assumed for prediction intervals. See link{predict.lm} for more details.
n.ahead	number of steps ahead at which to predict.

Value

a vector with the predicted values.

Author(s)

Manuel Febrero-Bande, Manuel Oviedo de la Fuente [e-mail]

References

Oviedo de la Fuente, M., Febrero-Bande, M., Pilar Munoz, and Dominguez, A. Predicting seasonal influenza transmission using Functional Regression Models with Temporal Dependence. arXiv:1610.08718. https://arxiv.org/abs/1610.08718

See Also

fregre.gls

Examples

## Not run: 
data(tecator)
ind<-1:190
x <-fdata.deriv(tecator$absorp.fdata,nderiv=1)
dataf=as.data.frame(tecator$y)
dataf$itime <- 1:nrow(x)
ldat=list("df"=dataf[ind,],"x"=x[ind])
newldat=list("df"=dataf[-ind,],"x"=x[-ind])
newy <- tecator$y$Fat[-ind]
ff <- Fat ~ x
res.lm <- fregre.lm(ff,data=ldat)
summary(res.lm)
res.gls <- fregre.gls(ff,data=ldat, correlation=corAR1())
summary(res.gls)
par.cor <- list("cor.ARMA"=list("p"=1))
par.cor <- list("cor.ARMA"=list("index"=c("itime"),"p"=1))
res.igls <- fregre.igls(ff,data=ldat,correlation=par.cor) 
pred.lm <- predict(res.lm,newldat)
pred.gls <- predict(res.gls,newldat)
pred.igls <- predict(res.igls,newldat)
mean((pred.lm-newldat$df$Fat)^2)
mean((pred.gls-newldat$df$Fat)^2)
mean((pred.igls-newldat$df$Fat)^2)

## End(Not run)

fda.usc documentation built on Oct. 17, 2022, 9:06 a.m.