Skip to content

predict problem

6 messages · Troels Ring, Uwe Ligges, Brian Ripley +1 more

#
Windows 98
R : Copyright 2001, The R Development Core Team
Version 1.2.1 (2001-01-15)
Dear friends.
How comes this works and produce a single prediction:
x <- rnorm(15)
y <- x + rnorm(15)
predict(lm(y ~ x))
new <- data.frame(x = seq(-3, 3, 0.5))
predict(lm(y ~ x), new, se.fit = TRUE)
pred.w.plim <- predict(lm(y ~ x), new, interval="confidence")
new1 <- data.frame(x=3)
predict(lm(y ~ x), new1, interval="confidence")

while this refuses to take the "new" and predict ?
lot <- c(30,20,60,80,40,50,60,30,70,60)
hours <- c(73,50,128,170,87,108,135,69,148,132)
z1 <- lm(hours~lot)
new <- data.frame(x=80)
predict(z1,new,interval="confidence",level=90)
best wishes
Troels 

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
Troels Ring wrote:
What you want is level=0.9 ???

Uwe Ligges
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
On Mon, 9 Apr 2001, Troels Ring wrote:

            
There's no variable called `lot' in your new data frame.

new <- data.frame(lot=80)

And you want a 90% not a 90 confidence interval:

predict(z1,new,interval="confidence",level=0.9)
     fit      lwr      upr
[1,] 170 166.9245 173.0755

Now, did you really want a confidence and not prediction interval?
#
You need to change "new <- data.frame(x=80)" to read
"new <- data.frame(lot=80)"

Alan



On Mon, 09 Apr 2001 15:43:13 +0200 Troels Ring
<tring at gvdnet.dk> wrote:

            
----------------------
Alan T. Arnholt
arnholt at math.appstate.edu

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
On Mon, 09 Apr 2001 15:43:13 +0200 Troels Ring
<tring at gvdnet.dk> wrote:

            
you will also need to change your level to read .90 versus 
90
fit      lwr      upr
[1,] 170 166.9245 173.0755

Alan
----------------------
Alan T. Arnholt
arnholt at math.appstate.edu

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
Faster than the wind several people spotted the errors
new <- data.frame(lot=80)
and
predict(z1,new,interval="confidence",level=.90)
Thank you for your efforts and kindness !

Troels
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://stat.ethz.ch/pipermail/r-help/attachments/20010409/73b61a36/attachment.html