# [R] Test on mu with multivariate normal distribution

Peter Dalgaard p.dalgaard at biostat.ku.dk
Sun May 8 09:25:04 CEST 2005

```"Telse Henschel" <telsehenschel at web.de> writes:

> Dear WizaRds,
>
> I am sorry to bother you with a newbie question, but although I tried to solve my problem using the various .pdf files (Introduction, help pages etc.), I have come to a complete stop. Please be so kind as to guide me a little bit along my way of exploring multivariate analysis in R.
>
> I want to test wether the means-vector mu1 of  X, consisting of the means per column of that matrix , and mu2, i.e. the means per column of Y,  are distributed equally  under the assumption of a multivariate normal distribution. I thought “simtest” could be the right function to get the p-value, but I fail to use R correctly. Here is what I tried to do:
>
> f1		<- factor(c("8", "10", "12", "14"))
>
> X		<- matrix(1:16, ncol=4)
> colnames(X)	<- c("Obj1","Obj2","Obj3","Obj4")
> X.frame	<- data.frame(f1,X)
>
> Y		<- matrix(1:12, ncol=4)
> colnames(Y)	<- c("Obj1","Obj2","Obj3","Obj4")
> Y.frame	<- data.frame(f1,Y)
> XY		<- data.frame(X.frame, Y.frame) # won’t work, because of different nr of rows
>
> test.stat	<- lm(XY ~ f1)	# ???

Try this:

X <- matrix(rnorm(16), ncol=4)
Y <- matrix(rnorm(12), ncol=4)
XY <- rbind(X,Y)
g <- factor(rep(1:2,c(4,3)))
fit1 <- lm(XY ~ g)
fit0 <- lm(XY ~ 1)
anova(fit0,fit1)

(using 1:16 and 1:12 for X and Y gives

Error in anova.mlmlist(object = fit0, fit1) :
residuals have rank 1 < 4

)

> # simtest(test.stat, XY, type="Tukey")
>
> creates errors already by just staring at it. I apologize.
>
>
> Thank you so much for your support,
> Telse
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help