R Graphical Manual

Browse All

Last data update: 2014.03.03

R: M- and MM-estimators for location.

M-estimators

R Documentation

M- and MM-estimators for location.

Description

Functions for calculating M- and MM-estimators for location given values and associated standard errors or standard uncertainties.

Usage

MM.estimate(x, ...)

## Default S3 method:
MM.estimate(x, u, c = 4.685, ...)

huber.estimate(x, ...)

## Default S3 method:
huber.estimate(x, u, k= 1.345, ...)

Arguments

`x`	numeric vector of mean values for groups
`u`	numeric vector of standard deviations or standard uncertainties associated with the values `x`
`c, k`	Tuning parameters passed to other functions (see `rlm`)
`...`	Parameters passed to other functions.

Details

These functions are wrappers for robust estimation using rlm. All simply call rlm with the formula x~1 and weights 1/u^2.

Value

An object of class ‘loc.est’.

Author(s)

S. L. R. Ellison s.ellison@lgc.co.uk

References

None, yet.

Examples



## Cd heat of vapourisation example from the paper cited above
x2<-c(27.044, 26.022, 26.340, 26.787, 26.796)
v<-c(3, 76, 464, 3, 14)*1e-3

MM.estimate(x2, sqrt(v))

huber.estimate(x2, sqrt(v))