Individuelle Diskussion im Kurs über die Probleme, die eigenen Files in R zu laden.
load(url("http://andreasmock.github.io/data/hnscc.RData"))
summary(aov(age ~ grade, hnscc))
## Df Sum Sq Mean Sq F value Pr(>F)
## grade 4 1059 264.8 1.778 0.133
## Residuals 274 40795 148.9
cor.test(~ age + days_to_death, data=hnscc)
##
## Pearson's product-moment correlation
##
## data: age and days_to_death
## t = -0.9266, df = 276, p-value = 0.3549
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.17220287 0.06236354
## sample estimates:
## cor
## -0.05568803
Besserer Approach: Survival analysis
Nicht-parametrische Alternative zum T-Test: Wilcoxon-Mann-Whitney-Test.
R Funktion: wilcox.test()