Hi,
the predict-function is not very good in guessing names from a given new
dataset. So if you want to predict x1 from some new x2 values, your
newdata argument should contain some x2 - values.
predict(model, newdata=data.frame(x2=seq(0,4)), interval =
c("confidence"), level = 0.90,type="re
It is not an error but rather a warning. As you should have seen, R
went ahead and returned estimates for 24 predicted values for x1 for
arguments to the formula of x2. In R errors and warnings are very
different. You are expected to post full console messages to prevent
this sort of confus
How about
library(ggplot2)
qplot(wt, mpg, data = mtcars, geom=c("point", "smooth"),method = "lm").
On Sat, Mar 7, 2009 at 6:19 PM, Martin Batholdy wrote:
> hi,
>
>
> is there an easy way to plot the "confidence lines" or "confidence area" of
> the beta weight in a scatterplot?
>
>
> like in this
3 matches
Mail list logo
