pmlogreg: Piecewise monotone logistic regression with taut strings

In ftnonpar: Features and Strings for Nonparametric Regression

Description

Applies the taut string method to binary data.

Usage

pmlogreg(y, thr.const=2.5, verbose=FALSE, extrema.nr=-1, bandwidth=-1, 
localsqueezing=TRUE, squeezing.factor=0.5, tolerance=0.001,extrema.mean=TRUE)

Arguments

y	observed values (ordered by value of independent variable)
thr.const	smoothing parameter for the multiresolution criterion (should be approximately 2.5)
verbose	logical, if T progress (for each iteration) is illustrated grahically
extrema.nr	if set to a positive integer an approximation with the specified number of local extreme values is calculated
bandwidth	if set to a positive value the specified bandwidth is used instead of the multiresolution criterion.
localsqueezing	logical, if T (default) the bandwidth is changed locally.
squeezing.factor	The amount of decrement applied to the bandwidthes
tolerance	Accuracy used for the determination of the bandwidth when extrema.nr is greater than 0.
extrema.mean	logical, if T (default) the value of the taut string approximation at local extreme values is set to the mean of the observations on the interval where the extremum is taken.

Value

A list with components

y	The approximation of the given data
widthes	Bandwidth used
nmax	Number of local extreme values
knotsind	Indices of knot points
knotsy	y-koordinates of knots of the taut string

Author(s)

Arne Kovac [e-mail]

See Also

l1pmreg,pmden,pmspec

Examples

aaa<-rbinom(1024,1,0.5+0.5*sin(seq(0,10*pi,len=1024)))
pmlogreg(aaa,verbose=TRUE)$n

ftnonpar documentation built on May 2, 2019, 3:04 a.m.