nlr (version 0.1-3)

nl.lts: Compute (LTS) Least Trimmed Square Estimate.

Description

LTS is minimizing trimmed sum of squares.

Usage

nl.lts(formula, data, start, h = NULL, control = nlr.control())

Arguments

formula

nl.form object of the nonlinear model function.

data

List of data used in predictor and response.

start

List of parameter starting value.

h

Percentage of trimming the residuals, if omited the default 25% will be used.

control

nlr.control options, will be submited to least square nlsqr function.

Value

nl.fitt object of fitted model parameter.

Details

LTS trimme h percent of residuals first then compute the least square estimate, and final parameter estimate is the one minimize the sum of squares of errors.

References

Riazoshams H, Midi H, and Ghilagaber G, 2018,. Robust Nonlinear Regression, with Application using R, Joh Wiley and Sons.

See Also

nl.form, nl.fitt

Examples

# NOT RUN {
data=list(xr=Weights$Date,yr=Weights$Weight)
fit<- nl.lts(nlrobj1[[14]],data=data,start=list(p1=1000,p2=42,p3=.11))
fit$parameters
# }