Skip to content
Prev 246523 / 398502 Next

Assumptions for ANOVA: the right way to check the normality

Try the following:
# using your scrd data and your proposed models
fit1<- lm(response ~ stimulus + condition + stimulus:condition, data=scrd)
fit2<- lm(response ~ stimulus + condition, data=scrd)
fit3<- lm(response ~ condition, data=scrd)

# Set up for 6 plots on 1 panel
op = par(mfrow=c(2,3))

# residuals function extracts residuals
# Visual inspection is a good start for checking normality
# You get a much better feel than from some "magic number" statistic
hist(residuals(fit1))
hist(residuals(fit2))
hist(residuals(fit3))

# especially qqnorm() plots which are linear for normal data
qqnorm(residuals(fit1))
qqnorm(residuals(fit2))
qqnorm(residuals(fit3))

# Restore plot parameters
par(op)
Indeed - Kruskal-Wallis is a good test to use for one factor data that is 
ordinal so it is a good alternative to your fit3.
Your "response" seems to be a discrete variable rather than a continuous 
variable.
You must decide if it is reasonable to approximate it with a normal 
distribution which is by definition continuous.