Sampling Variance estimates

Sampling variance or error variance estimates for regression estimates.

Usage

Var.y(y, S, Var.e = NULL)

Arguments

y

fdata class object.

S

Smoothing matrix calculated by S.basis or S.NW functions.

Var.e

Error Variance Estimates. If Var.e=NULL, Var.e is calculated.

Value

Var.y: returns the sampling variance of the functional data. Var.e: returns the sampling error variance of the functional data.

References

Ramsay, James O., and Silverman, Bernard W. (2006), Functional Data Analysis, 2nd ed., Springer, New York.

See also

See Also as Var.e

Author

Manuel Febrero-Bande, Manuel Oviedo de la Fuente manuel.oviedo@udc.es

Examples

a1<-seq(0,1,by=.01)
a2=rnorm(length(a1),sd=0.2)
f1<-(sin(2*pi*a1))+rnorm(length(a1),sd=0.2)
nc<-50
np<-length(f1)
tt=1:101
mdata<-matrix(NA,ncol=np,nrow=nc)
for (i in 1:nc) mdata[i,]<- (sin(2*pi*a1))+rnorm(length(a1),sd=0.2)
mdata<-fdata(mdata,tt)
S=S.NW(tt,h=0.15)
var.e<-Var.e(mdata,S)
var.y<-Var.y(mdata,S)
var.y2<-Var.y(mdata,S,var.e) #the same