SNK is derived from Tukey, but it is less conservative (finds more differences). Tukey controls the error for all comparisons, where SNK only controls for comparisons under consideration. The level by alpha default is 0.05.
SNK.test( y, trt, DFerror, MSerror, alpha = 0.05, group = TRUE, main = NULL, console = FALSE )
| y | model(aov or lm) or answer of the experimental unit |
|---|---|
| trt | Constant( only y=model) or vector treatment applied to each experimental unit |
| DFerror | Degree free |
| MSerror | Mean Square Error |
| alpha | Significant level |
| group | TRUE or FALSE |
| main | Title |
| console | logical, print output |
Statistics of the model
Design parameters
Critical Range Table
Statistical summary of the study variable
Comparison between treatments
Formation of treatment groups
It is necessary first makes a analysis of variance.
if y = model, then to apply the instruction:
SNK.test (model, "trt",
alpha = 0.05, group = TRUE, main = NULL, console = FALSE)
where the model
class is aov or lm.
1. Principles and procedures of statistics a biometrical
approach Steel & Torry & Dickey. Third Edition 1997
2. Multiple
comparisons theory and methods. Departament of statistics the Ohio State
University. USA, 1996. Jason C. Hsu. Chapman Hall/CRC.
BIB.test, DAU.test,
duncan.test, durbin.test,
friedman, HSD.test, kruskal,
LSD.test, Median.test, PBIB.test,
REGW.test, scheffe.test,
waerden.test, waller.test,
plot.group
library(agricolae) data(sweetpotato) model<-aov(yield~virus,data=sweetpotato) out <- SNK.test(model,"virus", console=TRUE, main="Yield of sweetpotato. Dealt with different virus")#> #> Study: Yield of sweetpotato. Dealt with different virus #> #> Student Newman Keuls Test #> for yield #> #> Mean Square Error: 22.48917 #> #> virus, means #> #> yield std r Min Max #> cc 24.40000 3.609709 3 21.7 28.5 #> fc 12.86667 2.159475 3 10.6 14.9 #> ff 36.33333 7.333030 3 28.0 41.8 #> oo 36.90000 4.300000 3 32.1 40.4 #> #> Alpha: 0.05 ; DF Error: 8 #> #> Critical Range #> 2 3 4 #> 8.928965 11.064170 12.399670 #> #> Means with the same letter are not significantly different. #> #> yield groups #> oo 36.90000 a #> ff 36.33333 a #> cc 24.40000 b #> fc 12.86667 c#> $statistics #> MSerror Df Mean CV #> 22.48917 8 27.625 17.1666 #> #> $parameters #> test name.t ntr alpha #> SNK virus 4 0.05 #> #> $snk #> Table CriticalRange #> 2 3.261182 8.928965 #> 3 4.041036 11.064170 #> 4 4.528810 12.399670 #> #> $means #> yield std r Min Max Q25 Q50 Q75 #> cc 24.40000 3.609709 3 21.7 28.5 22.35 23.0 25.75 #> fc 12.86667 2.159475 3 10.6 14.9 11.85 13.1 14.00 #> ff 36.33333 7.333030 3 28.0 41.8 33.60 39.2 40.50 #> oo 36.90000 4.300000 3 32.1 40.4 35.15 38.2 39.30 #> #> $comparison #> difference pvalue signif. LCL UCL #> cc - fc 11.5333333 0.0176 * 2.604368 20.462299 #> cc - ff -11.9333333 0.0151 * -20.862299 -3.004368 #> cc - oo -12.5000000 0.0291 * -23.564170 -1.435830 #> fc - ff -23.4666667 0.0008 *** -34.530836 -12.402497 #> fc - oo -24.0333333 0.0012 ** -36.433003 -11.633664 #> ff - oo -0.5666667 0.8873 -9.495632 8.362299 #> #> $groups #> NULL #> #> attr(,"class") #> [1] "group"# version old SNK.test() df<-df.residual(model) MSerror<-deviance(model)/df out <- with(sweetpotato,SNK.test(yield,virus,df,MSerror, group=TRUE)) print(out$groups)#> yield groups #> oo 36.90000 a #> ff 36.33333 a #> cc 24.40000 b #> fc 12.86667 c