[R] Tukey tests in two-way ANOVA

Lucy McMahon lucymcmahon004 at hotmail.co.uk
Mon May 15 19:40:29 CEST 2017


R-help:

I'm looking into the abundance of an algal species over site and years using a two-way ANOVA:

> summary (aov (fserratus ~ site+year))
            Df     Sum Sq   Mean Sq   F value      Pr(>F)
site       1      1487       1486.6      6.094       0.0155 *
year      1      1173      1172.8      4.808       0.0309 *

But I'm receiving the following warning messages when I run the Tukey test.
> TukeyHSD(aov(fserratus ~ site+year))

$site
                    diff              lwr                      upr                 p adj
1-0         -8.039565     -14.51045     -1.568685    0.0154723

Warning messages:
1: In replications(paste("~", xx), data = mf) : non-factors ignored: year
2: In TukeyHSD.aov(aov(fserratus ~ site + year)) :
  'which' specified some non-factors which will be dropped


Any advice would be appreciated, thanks.




	[[alternative HTML version deleted]]



More information about the R-help mailing list