[R-sig-eco] Marrying Tukey's HSD and ANOVA results
I've done a standard two way ANOVA using glm on the dependent variable "clutchsize" with the two factors "treatment" (which has 3 levels called 1, 2, and 3) and "species" (which has two levels called 1 and 2). Apparently there is no significant interaction term. Then I did Tukey's HSD and found that there were significant differences between species at only one of the three treatment levels, treatment level 1. Are these in fact conflicting results? ##ANOVA RESULTS summary(aov((clutchsize~treatment*species))) Df Sum Sq Mean Sq F value Pr(>F) treatment 1 29.26 29.264 7.0230 0.00884 ** species 1 138.14 138.143 33.1526 4.13e-08 *** treatment:species 1 8.11 8.110 1.9464 0.16487 Residuals 163 679.20 4.167 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 ##TUKEY HSD RESULTS TukeyHSD(aov(clutchsize~treatment*species)) Tukey multiple comparisons of means 95% family-wise confidence level Fit: aov(formula = clutchsize ~ treatment * species) $treatment difflwr upr p adj 2-1 1.3245614 0.4184292 2.2306936 0.0020030 3-1 1.0416667 0.1316071 1.9517262 0.0204117 3-2 -0.2828947 -1.1806793 0.6148899 0.7368331 $species diff lwr upr p adj 2-1 -1.89988 -2.544747 -1.255013 0 $`treatment:species` diff lwrupr p adj 2:1-1:1 1.1791506 -0.19269072 2.5509919 0.1364846 3:1-1:1 0.6476190 -0.73345324 2.0286913 0.7550479 1:2-1:1 -2.4225564 -4.08045729 -0.7646555 0.0005858 2:2-1:1 -0.8357143 -2.46652980 0.7951012 0.6787094 3:2-1:1 -0.6357143 -2.26652980 0.9951012 0.8706501 3:1-2:1 -0.5315315 -1.89354633 0.8304833 0.8701101 1:2-2:1 -3.6017070 -5.24376636 -1.9596476 0.000 2:2-2:1 -2.0148649 -3.62957317 -0.4001566 0.0055886 3:2-2:1 -1.8148649 -3.42957317 -0.2001566 0.0177862 1:2-3:1 -3.0701754 -4.71995456 -1.4203963 0.041 2:2-3:1 -1.483 -3.10589150 0.1392248 0.0944158 3:2-3:1 -1.283 -2.90589150 0.3392248 0.2077935 2:2-1:2 1.5868421 -0.27701672 3.4507009 0.1438444 3:2-1:2 1.7868421 -0.07701672 3.6507009 0.0684872 3:2-2:2 0.200 -1.63980803 2.0398080 0.9995894 ___ R-sig-ecology mailing list R-sig-ecology@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
Re: [R-sig-eco] Marrying Tukey's HSD and ANOVA results
Lara R. Appleby 04 writes: > I've done a standard two way ANOVA using glm on the dependent > variable "clutchsize" with the two factors "treatment" (which has 3 > levels called 1, 2, and 3) and "species" (which has two levels > called 1 and 2). Apparently there is no significant interaction > term. Then I did Tukey's HSD and found that there were significant > differences between species at only one of the three treatment > levels, treatment level 1. > > ##ANOVA RESULTS > > summary(aov((clutchsize~treatment*species))) > Df Sum Sq Mean Sq F value Pr(>F) > treatment 1 29.26 29.264 7.0230 0.00884 ** > species 1 138.14 138.143 33.1526 4.13e-08 *** > treatment:species 1 8.11 8.110 1.9464 0.16487 > Residuals 163 679.20 4.167 I think you failed to tell R that `treatment' was a factor (i.e. a categorical variable). The Df in the output above suggests that you are actually (accidentally) running a linear regression on treatment number, rather than an ANOVA on treatment. The Df should be 2,1,2 for the design you described above. That doesn't answer your other question, but it would be better to sort out the more fundamental issue first. ___ R-sig-ecology mailing list R-sig-ecology@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
