Re: [R] Normality in split-plot design

Silvano, To test normality of the erros you can use m0 <- aov(...) shapiro.test(residuals(m0)) or another test like Kolmogorov-Smirnov (ks.test), Jarque-Bera (jarque.test{moments}, jarque.bera.test{tseries}) among others. Fell free to join our R brazilian group on yahoo groups named R_STAT. You

[R] Normality in split-plot design

Hi, I would like to test the normality of errors in an split-plot design using R. I used the following program: anava = aov(ganhos ~ Blocos + Trat*Supl + Error(Blocos/Trat)) summary(anava) bartlett.test(ganhos, Trat) bartlett.test(ganhos, Supl) How can I test the normality of the errors?