nlr (version 0.1-3)

nl.lmsNM: Fitt a nonlinear regression model by least median of squares. The Optimization is done by golden section method.

Description

Least Median of square estimate is robust fitt by minimizing the median of squared residuals. This function use the "optim" function which minimize using Golden section method.

Usage

nl.lmsNM(formula, data, start)

Arguments

formula

nl.form object of the nonlinear function model.

data

list of data include responce and predictor.

start

list of parameter values of nonlinear model function (\(\theta\). in \(f(x,\theta)\)).

Value

list of parameter estimates.

Details

Note that due to using classic optimization method, and due to non uniqueness of minimum of objective function this estimate is not efficient, but is high breakdown estimate.

References

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

See Also

nl.lmsGA, nlr.control, nlr

Examples

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