alpha2h: Test Equality of Curves with Homoscedastic or Heteroscedastic...

In curvetest: The package will formally test two curves represented by discrete data sets to be statistically equal or not when the errors of the two curves were assumed either equal or not using the tube formula to calculate the tail probabilities.

Description

For each value $at$ in the defining interval, find a bandwidth $h$ so that alpha*100 percent of data points specified in $xseq$ should be within the $(x-h, x+h)$ window. This is a utility function.

Usage

alpha2h(alpha, at, xseq)

Arguments

alpha	Smoothing parameter that for each point in the domain, use a windown width that should have alpha*100 percent of data points falling in the window.
at	a point in the x domain.
xseq	Sequence of the data points.

Value

A numeric value h that will be used as bandwidth in the next curve fitting process.

Author(s)

Zhongfa Zhang, Jiayang Sun

References

Zhongfa Zhang, et al: Test Equality of Curves with Homoscedastic or Heteroscedastic Errors. To appear.

See Also

curvetest, curvefit, print.curvetest, plot.curvetest

Examples

    x= runif(100)
    (h=alpha2h(0.3, at=0.5, xseq=x))  ##get the window width h around x=.5 so that 30% data points of xseq fall in the area.  
  

curvetest documentation built on May 29, 2017, 8:46 p.m.