The data consists of weights of fresh harvested plants with four different treatments. The data is normally distributed and homogeneity of variances is given too.
Anova shows significiant differences:
anova_Ernte <- aov(Gewicht ~ Variante, data=Daten_Ernte)
Anova(anova_Ernte)
Anova Table (Type II tests)
Response: Gewicht
Sum Sq Df F value Pr(>F)
Variante 57213 3 2.9778 0.03226 *
Residuals 1511436 236
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
However post-hoc test HSD.Test() doesnt show any significiant differences:
HSD.test(anova_Ernte, "Variante", group = TRUE, console = TRUE, main = "")
4 434.70 a
1 426.90 a
3 400.95 a
2 398.20 a
Gewicht std r Min Max
1 426.90 80.08929 80 234 596
2 398.20 79.90095 80 216 561
3 400.95 74.87869 40 228 568
4 434.70 84.98754 40 264 647
Tuckey-HSD shows the following
TukeyHSD(anova_Ernte)
Tukey multiple comparisons of means
95% family-wise confidence level
Fit: aov(formula = Gewicht ~ Variante, data = Daten_Ernte)
$Variante
diff lwr upr p adj
2-1 -28.70 -61.439904 4.039904 0.1085058
3-1 -25.95 -66.048029 14.148029 0.3394912
4-1 7.80 -32.298029 47.898029 0.9582293
3-2 2.75 -37.348029 42.848029 0.9980106
4-2 36.50 -3.598029 76.598029 0.0887876
4-3 33.75 -12.551216 80.051216 0.2368136
And finally kurskal wallis does not show significiant differences between the groups:
kruskal(y=Daten_Ernte$Gewicht, trt=Daten_Ernte$Variante, p.adj = "bonferroni", console = TRUE)
kruskal.test(Daten_Ernte$Gewicht ~ Daten_Ernte$Variante)
4 133.9000 a
1 131.2063 a
3 109.8875 a
2 108.4000 a
Am i now safe to say that there are no significiant differences between the groups or do i have options to find out which groups differ according to anova?
