Trend Tests

code

analysis

A topic that has been bothering me for years

Author

Zhenglei Gao

Published

February 4, 2025

Materials and Resources

Example of Trend Tests

CA

Jonckheere-Terpstra

Tukey trend tests

library(tukeytrend)

Warning: package 'tukeytrend' was built under R version 4.4.2

Loading required package: multcomp

Warning: package 'multcomp' was built under R version 4.4.2

Loading required package: mvtnorm

Loading required package: survival

Loading required package: TH.data

Warning: package 'TH.data' was built under R version 4.4.2

Loading required package: MASS


Attaching package: 'TH.data'

The following object is masked from 'package:MASS':

    geyser

data(litter, package="multcomp") 
dl <- litter 
dl$dosen <- as.numeric(as.character(dl$dose)) 
fitw <- lm(weight ~ dosen, data=dl) 
ttw <- tukeytrendfit(fitw, dose="dosen", scaling=c("ari", "ord", "arilog")) 
exa1<-summary(glht(model=ttw$mmm, linfct=ttw$mlf))

exa1


     Simultaneous Tests for General Linear Hypotheses

Linear Hypotheses:
                               Estimate Std. Error z value Pr(>|z|)
dosenari: dosenari == 0       -0.002063   0.002522  -0.818    0.537
dosenord: dosenord == 0       -0.773009   0.453985  -1.703    0.130
dosenarilog: dosenarilog == 0 -0.297261   0.263454  -1.128    0.352
(Adjusted p values reported -- single-step method)