PermTest {pgirmess}R Documentation

Permutation test for lm, lme and glm (binomial and Poisson) objects

Description

Permutation test for lm, lme and glm (binomial and Poisson) objects

Usage

    PermTest(obj, B=1000,...)

    ## S3 method for class 'lm':
    PermTest(obj, B=1000,...)
    ## S3 method for class 'lme':
    PermTest(obj, B=1000,...)
    ## S3 method for class 'glm':
    PermTest(obj, B=1000,...)

Arguments

obj an object of class lm, lme, or glm
B number of permutations, default = 1000
... used to pass other arguments

Details

For glm, when the response is a two-column matrix with the columns giving the numbers of successes and failures, PermTest.glm uses permcont(); PermTest.lme requires the library nlme.

Value

A list object of class PermTest including:

p.value the p value obtained
B the number of permutations
call the call

Warning

This generic function is implemented in R language, thus can be quite slow.

Author(s)

Patrick Giraudoux <patrick.giraudoux@univ-fcomte.fr>. The implementation of PermTest.lme has been helped by Renaud Lancelot

Examples

library(MASS)
mylm<-lm(Postwt~Prewt,data=anorexia)
PermTest(mylm,B=250)

## Dobson (1990) Page 93: Randomized Controlled Trial :
    counts <- c(18,17,15,20,10,20,25,13,12)
    outcome <- gl(3,1,9)
    treatment <- gl(3,3)
    glm.D93 <- glm(counts ~ outcome + treatment, family=poisson)
    PermTest(glm.D93,B=250)

library(nlme)
fm2 <- lme(distance ~ age + Sex, data = Orthodont, random = ~ 1)
PermTest(fm2,B=250)

  

[Package pgirmess version 1.3.7 Index]