Hi Thomas,
Perhaps:
test = read.table("test.dat", header=T, dec=',')
x <- test[,1:21]
y <- test[, "Y"]
mymodel <- lm(y ~ x)
# Coefficients and more information
summary(mymodel)
# Plots for the residuals
plotspar(mfrow=c(2,2))
plot(mymodel)
See also ?lm
HTH,
Jorge
On Tue, May 13, 2008 at 6:54 PM, Anja und Th. Sponsel <[EMAIL PROTECTED]>
wrote:
> I just have read the guide and I can do some small steps with cran but
> I still have no clue...
>
> I have data like this:
> X1 X2 X3 ... X21 Y
> 1 0 0 0 ... 18 -0,07254
> 2 1 0 0 ... 6 -0,14921
> 3 0 1 0 ... 12 -0,04165
> 4 0 0 0 ... 8 0,08359
> 5 ... ... ... ... ... ...
> 120 0 0 1 1 8 0,07928
>
> My script is:
> > require(stats); require(graphics)
> > test = read.table("test.dat", header=T)
> > x <- test[, 1:21]
> > y <- test[, "Y"]
> > lm(y ~ x)
>
> The error may be an invalid type (list) for variable x (see below):
> Fehler in model.frame.default(formula = y ~ x, drop.unused.levels =
> TRUE) :
> ungültiger Typ (list) für die Variable 'x'
>
> Then I tried:
> ...
> > lm(data=test)
> Then I get a lot of coefficients, but I'm not sure. That cant be the
> result.
>
> Then I tried:
> > summary(lm(data = wetter))
>
> Call:
> lm(data = wetter)
>
> Residuals:
> ALL 120 residuals are 0: no residual degrees of freedom!
>
> Coefficients: (139 not defined because of singularities)
> Estimate Std. Error t value Pr(>|t|)
> (Intercept) 0.044747 NA NA NA
> X2 0.660275 NA NA NA
> X3 -0.097629 NA NA NA
> X4 0.647851 NA NA NA
> X5 -3.305631 NA NA NA
> ... 0.249788 NA NA NA
>
> I am confused...
>
> Best regards,
> Thomas
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
