Your question is not clear. Confidence intervals apply to parameters.
What you set out below is a simulation strategy. x is a simulated
sample and y is a statistic based on it. There is no 'model' in any
statistical sense.
What is the parameter for which you want a confidence interval?
What
UseR,
I am on the conference committee for CMG'08 (Computer Measurement
Group - www.cmg.org). At the last several conferences I have
presented papers, and workshops, on the use of R in computer
performance analysis and visualization. I am sending this out to see
if anyone would be interested in
I have a model as follows:
x <- replicate(100, sum(rlnorm(rpois(1,5), 0,1)))
y <- quantile(x, 0.99))
How would one go about estimating the boundaries of a 95% confidence
interval for y?
Any pointers would be greatly appreciated.
> version
_
platform i386-pc-mingw32
arch i386
os mingw32
system i
Two small points for this discussion.
Emacs + ESS is brilliant, but it does require some investment of time for
people to become comfortable with it. You really need to grok Emacs first. It
is protable across platforms, as pointed out below, but if you are trying to
get a neophyte class on si
David Winsemius <[EMAIL PROTECTED]> wrote in
news:[EMAIL PROTECTED]:
> "Jacques Wagnor" <[EMAIL PROTECTED]> wrote in
> news:[EMAIL PROTECTED]:
>
>> I have a model as follows:
>>
>> x <- replicate(100, sum(rlnorm(rpois(1,5), 0,1)))
>> y <- quantile(x, 0.99))
>>
>> How would one go about estima
Stefan Grosse wrote:
> On Saturday 02 February 2008 07:51:00 pm you wrote:
> FE> I'm using the standard Ubuntu debian repositories.
> FE> Frank
> FE>
>
> Try the 0.4.9 etch package from the project:
> http://sourceforge.net/project/showfiles.php?group_id=50231&package_id=43758&release_id=568604
T
On 2 February 2008 at 20:15, Stefan Grosse wrote:
| On Saturday 02 February 2008 07:51:00 pm you wrote:
| FE> I'm using the standard Ubuntu debian repositories.
| FE> Frank
| FE>
|
| Try the 0.4.9 etch package from the project:
|
http://sourceforge.net/project/showfiles.php?group_id=50231&packag
This does not answer your question directly but note that
strapply in the gsubfn package can be used to select strings
by content:
> library(gsubfn)
> (x <- strapply(txt, "Variation_", simplify = c))
[1] "Variation_0001" "Variation_5452" "Variation_4192" "Variation_4193"
[5] "Variation_8246" "
On Saturday 02 February 2008 07:51:00 pm you wrote:
FE> I'm using the standard Ubuntu debian repositories.
FE> Frank
FE>
Try the 0.4.9 etch package from the project:
http://sourceforge.net/project/showfiles.php?group_id=50231&package_id=43758&release_id=568604
for gutsy the latest package is 0.4.
Atte Tenkanen a écrit :
> Dear R-users,
> How do you save a big table or matrix
I use
write.table() to save and
read.table() to read
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http:
That actually reminds me of a problem I had to tackle a while ago.
Say I have the following:
txt <- c("Variation_0001 // chr1:1083805-1283805 // Array CGH //
15286789 // Iafrate et al. (2004) // CopyNumber /// Variation_5452 //
chr1:1142956-1147823 // Computational mapping of resequencing
hits=-2.5 tests�YES_00,FORGED_RCVD_HELO
X-USF-Spam-Flag: NO
try this:
dat <- data.frame(Col = c("chr1:71310034", "chr14:23354088",
"chr15:37759058", "chr22:18262638", "chrUn:31337214",
"chr10_random:4369261", "chrUn:3545097"))
vals <- strsplit(as.character(dat$Col), ":")
dat$"Col_a" <-
Benilton Carvalho wrote:
> help("strsplit")
> b
>
Yes, but...
The postprocessing gets a bit awkward. It might be easier to use sub()
to get rid of the first/last bit of the string i.e.
C2 <- sub("^.*:", "", Col)
C1 <- sub(":.*$", "", Col)
An orthogonal idea is
con <- textConnection("Col")
re
Please note the request for a reproucible example at the foot of this (and
every) message. Your 'x' looks like a data frame, double-spaced by your
mailer (and your sent HTML when asked not to, probably the cause).
However,
> x <- ts(c(36,44,45,106,38,46,47,112,42,49,48,118,42,50,51,118),
+
help("strsplit")
b
On Feb 2, 2008, at 12:43 PM, joseph wrote:
Hello
I have a data frame and one of its columns is as follows:
Col
chr1:71310034
chr14:23354088
chr15:37759058
chr22:18262638
chrUn:31337214
chr10_random:4369261
chrUn:3545097
I would like to get rid of col
Hello
I have a data frame and one of its columns is as follows:
Col
chr1:71310034
chr14:23354088
chr15:37759058
chr22:18262638
chrUn:31337214
chr10_random:4369261
chrUn:3545097
I would like to get rid of colon (:) and replace this column
with two new columns containing th
tom soyer wrote:
> Spencer,
>
> The warning message is sent from VAR, it basically lets you know that the
> data it used had no column names and it had to supply them using y1, y2, y3,
> etc. It can be suppressed by including options(warn=-1) in the function.
>
> Anyway, it seems that the p
"Jacques Wagnor" <[EMAIL PROTECTED]> wrote in
news:[EMAIL PROTECTED]:
> I have a model as follows:
>
> x <- replicate(100, sum(rlnorm(rpois(1,5), 0,1)))
> y <- quantile(x, 0.99))
>
> How would one go about estimating the boundaries of a 95% confidence
> interval for y?
>
> Any pointers would b
Spencer,
The warning message is sent from VAR, it basically lets you know that the
data it used had no column names and it had to supply them using y1, y2, y3,
etc. It can be suppressed by including options(warn=-1) in the function.
Anyway, it seems that the p value from my function does not matc
Dear Tom:
Your revised function eliminates the discrepancy in the degrees of
freedom but is still very different from the numbers reports on Tsay, p.
102:
archTest(log(1+as.numeric(m.intc7303)), lag=12)
ARCH test (univariate)
data: Residual of y1 equation
Chi-squared = 13.1483,
OK, it's no good. Here is the result:
> data(m.intc7303)
> archTest(log(1+as.numeric(m.intc7303)), lags=12)
ARCH test (univariate)
data: Residual of y1 equation
Chi-squared = 13.1483, df = 12, p-value = 0.3584
On 2/2/08, tom soyer <[EMAIL PROTECTED]> wrote:
>
> Spencer,
>
> Sorry, I
Dear list,
This is off-topic, but perhaps there is an expert out there who can help
me in
a bootstrapping test.
I have two samples A, B from, say, a normal distribution. A third sample R
is the vector of pairwise minima of the same random variables:
A = rnorm(100)
B = rnorm(100)
A2 = rnorm(10
Spencer,
Sorry, I forgot that the default lag in arch is 16. Here is the fix. Can you
try it again and see if it gives the correct (or at least similar compared
to a true LM test) result?
archTest=function(x, lags=12){
#x is a vector
require(vars)
s=embed(x,lags)
y=VAR(s,p=1,type="const")
re
Dear Tom, Bernhard, Ruey:
I can't get that to match Tsay's example, but I have other
questions about that.
1. I got the following using Tom's 'archTest' function (below):
> archTest(log(1+as.numeric(m.intc7303)), lags=12)
ARCH test (univariate)
data: Residual of y1 equat
Perhaps the 'page' function?
Patrick Burns
[EMAIL PROTECTED]
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of S Poetry and "A Guide for the Unwilling S User")
Oliver Herbst wrote:
>HI,
>
>
>
>can anybody help me how to observe or read the output of an r command
>pagewise? (E.g. to make a
On Saturday 02 February 2008 03:21:24 pm Frank E Harrell Jr wrote:
FE> I have tried installing rkward on three different ubuntu systems and
FE> have never gotten past this error:
FE>
FE> rkward
FE> /usr/bin/rkward.bin: symbol lookup error: /usr/bin/rkward.bin: undefined
FE> symbol: R_LastvalueSymbo
Hi,
have a look at ?try which leads to using a construct of the following
form:
myTtest <- try(t.test(...))
if (inherits(myTtest, "try-error"))
{
cat(myTtest)
myTtest <- NA
}
Christian
__
R-help@r-project.org mailing list
https://stat.ethz
As mentioned three days ago, the R-help mailing list is now
only accepting postings from subscribers (more or less)
unconditionally.
Non-subscriber postings are currently held for moderation
which we would like to "out source".
To this end, we look for volunteers who are willing to share
the load
NO
Dear Oliver,
I'm not sure why you'd want to do this rather than just scrolling the
console after the output is completed (assuming, of course, that you
can scroll your console), but here's a function (not extensively
tested) that might do what you want:
more <- function(command, lines=20){
Stefan Grosse wrote:
> On Saturday 02 February 2008 04:06:38 am Wade Wall wrote:
> WW> I know this question has been asked in the past, but I am wondering if
> WW> anyone running R on Linux has any guidance as to a text editor that works
> WW> well with R.
>
> Beside the aforementioned emacs+ESS
Greetings,
For the following quarterly data I did a classical decomposition by hand in
a spreadsheet and got reasonably similar results using Minitab 15.
x
1 36
2 44
3 45
4 106
5 38
6 46
7 47
8 112
HI,
can anybody help me how to observe or read the output of an r command
pagewise? (E.g. to make a break after the first page of output data and then
continue by putting a key on the console)
Thanks a lot.
Oliver
[[alternative HTML version deleted]]
__
I am in a similar situation and found that Kate combined with Konsole
operates very much like Tinn-R. I actually use Kate for all interpreters
like Python, R, and Octave under linux.
Tom
Wade Wall wrote:
>
> Hi all,
>
> I know this question has been asked in the past, but I am wondering if
Is this what you want?
> x <- read.table(textConnection("Index A
+ 1 1
+ 1 2
+ 1 3
+ 2 4
+ 2 3
+ 3 7
+ 3 9
+ 3 3
+ 3 1"), header=TRUE)
> data.frame(x, value=ave(x$A, x$Index, FUN=function(z) z / sum(z)))
Index A value
1 1 1 0.167
2 1 2 0.333
3 1 3 0.500
4 2 4 0.57
Le sam. 02 févr. à 05:49, 宋时歌 a écrit :
> On Linux platform, nothing beats Emacs + ESS.
To me, an added bonus of Emacs + ESS is that you can remove the "On
Linux platform", above. Emacs is one of the very few (only?)
programmer's text editor with a good R mode that runs on all platforms
whe
?try
e.g.,
for(i in x) try(t.test(...))
On Feb 2, 2008 7:43 AM, My Coyne <[EMAIL PROTECTED]> wrote:
> Hi,
>
> I place a t.test in a loop and would like to continue to process the loop
> even when t.test encounter error. How do I do that?For example, in one
> iteration, the data is complet
What you want to do is to use 'plot' for the initial vector and then
"lines" to add the other two. You will have to set the range of the
y-axis in the initial call to "plot". The sequence would probably
look like this:
plot(a, ylim=range(a, b, c), col='black')
lines(b, col='red')
lines(c, col='g
Hi,
I place a t.test in a loop and would like to continue to process the loop
even when t.test encounter error. How do I do that?For example, in one
iteration, the data is completely constant and t.test gives error, the
entire program terminates. I would like to write the information out to
After to much windows contamination, my brain does not do the cryptic part of
Emacs+ESS C-x M-c M-headache. Eclipse is is currently my choice.
(But the installation instructions could be better)
Kees
On Saturday 02 February 2008 05:49:10 am 宋时歌 wrote:
> On Linux platform, nothing beats Emacs +
On Saturday 02 February 2008 04:06:38 am Wade Wall wrote:
WW> I know this question has been asked in the past, but I am wondering if
WW> anyone running R on Linux has any guidance as to a text editor that works
WW> well with R.
Beside the aforementioned emacs+ESS there exists another good editor
On 01/02/2008 11:49 PM, 宋时歌 wrote:
> On Linux platform, nothing beats Emacs + ESS.
This discussion may be relevant:
http://xkcd.com/378/
Duncan Murdoch
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read th
I have a model as follows:
x <- replicate(100, sum(rlnorm(rpois(1,5), 0,1)))
y <- quantile(x, 0.99))
How would one go about estimating the boundaries of a 95% confidence
interval for y?
Any pointers would be greatly appreciated.
> version
_
platform i386-pc-mingw32
arch i386
os mingw32
system i
I'm an R newbie and am trying to plot 3 vectors, say a,b,c. I have
downloaded 3 R manuals and searched your forum. There are plenty of X vs Y
examples, but cannot find how to plot 3, or more vectors one one graph. I'm
sure I overlooked something.
Thanks for any help.
CHV
--
View this message i
Dear R users
I wonder if there is a quick way to calculate the ratio/fraction of a
list/data frame. For example, if I have a data frame with two fields:
"Index" and "A". I would like to know the fractions of A's within the same
"Index". That is, for Index =1, three fractions will be "1/(1+2+3)
On 2/2/08, 宋时歌 <[EMAIL PROTECTED]> wrote:
> On Linux platform, nothing beats Emacs + ESS.
Another text editor would be Bluefish. I believe it would lack
functionality compared to the Emacs + ESS.
Liviu
__
R-help@r-project.org mailing list
https://stat.e
45 matches
Mail list logo
