On Thu, 22 Jun 2006, Simon Blomberg wrote:
Hi all,
I noticed an undocumented feature for split. It sorts the resulting list
according to the grouping factor. An example:
test - data.frame(x=rnorm(48), f=letters[sample(1:8)])
split(test, test$f)
I wasn't expecting this behaviour, although
Hi Greg,
Since you haven't yet had a response, you could distill this. It uses the
pixel dataset from nlme() as an example.
## To get separate files, do this
postscript(c:\MyGraph%03.ps, onefile=F)
plot(Pixel, display = Dog, inner = ~Side, layout=c(4,1))
dev.off()
## To get your layout into
Hi All,
I need your help in NA handling.
I've following data series.
x-c(1,4,5,8,NA,4,NA,5,5,1,2,7,8,9,NA,NA,NA,15,6,8)
Now i want to interpolate where NA value persists. Like, between 9 and 5 there
are three NA's. So, that should be interpolated like,
1st NA- (15-9)/4
2nd NA- 1st NA value +
Try this:
help.search(interpolate)
Then find this:
library(zoo)
na.approx(x)
[1] 1.0 4.0 5.0 8.0 6.0 4.0 4.5 5.0 5.0 1.0 2.0 7.0 8.0 9.0 10.5
[16] 12.0 13.5 15.0 6.0 8.0
Hth,
JeeBee.
On Thu, 22 Jun 2006 06:54:53 +0100, Sumanta Basak wrote:
Hi All,
I need your help in
On Wed, 21 Jun 2006, Cleber N.Borges wrote:
Hello All!
How to plot a image ( image function )
with restrictions, like a polygon??
The suggestions given in:
http://finzi.psych.upenn.edu/R/Rhelp02a.new/archive/15030.html
by Denis White let you overplot the image with a masking polygon
BertG == Berton Gunter [EMAIL PROTECTED]
on Tue, 13 Jun 2006 14:34:48 -0700 writes:
BertG RSiteSearch('Rosner') ?RSiteSearch or search directly
BertG from CRAN.
BertG Incidentally, I'll repeat what I've said
BertG before. Don't do outlier tests. They're
BertG
Thanks to everyone for the replies to my question.
There are several good algorithms to make decision trees with
multivariate splits (sometimes called oblique trees), some are even
freeware (QUEST, CRUISE...), but most are not open-sourced.
Unfortunately there seems to be no good choice for
Albert
Is this what you want?:
a[,order(colSums(a))]
John S
---
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Albert Vilella
Sent: 21 June 2006 11:38
To: r help
Subject: [R] sort matrix by sum of columns
Hi all,
I would like to know how can
Dear list,
Is it possible to have lattice provide two different ordinate axis,
one on the right side and one of the left side of the plot?
I would like to make a xyplot with x both in a linear scale and in a
log-approximate scale.
Thank you in advance.
/Fredrik
Sorry
should read:
ip - function(x) 1240 * x^(-0.88)
Rainer M Krug wrote:
Hi
System:
Linux, SuSE 10
R 2.3.0
I try to do the following
ip - function(x) 1240*dip(x, 0.88)
iip - function(x) integrate(ip, x - 0.045, x + 0.045)$value
f - integrate(iip, 10, 100)
Error in
Well why not do it symbolically, e.g.
int(a*x^b,x) = \frac{a}{b+1}x^{b+1}
and integrating this again gives
\frac{a}{(b+1)(b+2)}x^{b+2},
of course for resonable values of a and b such that things are well defined.
But if you follow the link
Thanks a lot - the symbolic solution will work and I understand what is
wrong with my function
Rainer
Frede Aakmann Tøgersen wrote:
Well why not do it symbolically, e.g.
int(a*x^b,x) = \frac{a}{b+1}x^{b+1}
and integrating this again gives
\frac{a}{(b+1)(b+2)}x^{b+2},
of course for
On 6/22/06, Fredrik Karlsson [EMAIL PROTECTED] wrote:
Dear list,
Is it possible to have lattice provide two different ordinate axis,
one on the right side and one of the left side of the plot?
Not easily. I hope to add some support for this sort of thing in the
future, but I'm not sure when.
I am modeling the probability of player succeeding in the NFL with a
binomial logistic regression with 1 signifying success and 0
signifying no success. I performed the regression of the binomial
variable against overall draft position using the college conference
for which each player played as
Thanks for the insight on the debugger. It has taken me a day or so to
get use to it, but it is very helpful.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Ben Bolker
Sent: Tuesday, June 20, 2006 12:56 PM
To: r-help@stat.math.ethz.ch
Subject: Re: [R]
Justin Rapp wrote:
I am modeling the probability of player succeeding in the NFL with a
binomial logistic regression with 1 signifying success and 0
signifying no success. I performed the regression of the binomial
variable against overall draft position using the college conference
for
I have recently fit a binomial link = logit model and I want to visually
see the estimated response across a specific covariate.
I can accomplish this by creating a function that extracts the betas
from the model then forms a linear combination with the classes I'm
interested in next pass the
Dear R users
I want to compute Kendall's Tau between two vectors x and y.
But x and y may have zeros in the same position(s) and I wrote the
following function to be sure to drop out those double zeros
cor.kendall - function(x,y) {
nox - c()
noy - c()
#
for (i in 1:length(x)) if (x[i]!=
At the encouragement of many at UseR, I'm trying to build my first real
package. I have no C/Fortran code, just plain old R code, so it should be
rocket science. On a Linux box, I used package.skeleton() to create a basic
package containing just one hello world type of function. I edited the
Hi, All:
I used optim() to minimise likelihood function for fitting the data to a
partiuclar distribution. The function is converged and the value of
log-likelihood is different when I change the intial value.
Whether it means the program does not work well?
Thanks!
Xin
Since I haven't seen a reply to this, I will offer a couple of
comments. I've never used deal, but it sounded interesting, so I
thought I'd look at it.
Have you looked at Susanne G. Bøttcher and Claus Dethlefsen. deal: A
Package for Learning Bayesian Networks. Journal of
Dear colleagues,
With the help of a colleague of mine here in Helsinki (Seppo Nyrkkö)
who looked at innards of the R source code for Mac it turned out that
this was indeed an issue concerning the Mac locale and its settings
and not R.
Though we had tried this earlier by changing the LANG
Thanks to Jeff Laake for giving me a starting point.
It appears my zipping should have been:
zip -r hello.zip hello
essentially creating an outer folder having the package
name inside the zip file. It still didn't quite work,
with an error as follows:
utils:::menuInstallLocal()
It is difficult to say much since you haven't described your likelihood
function. However, there are some general things that you can do: (1) make
sure that you are maximizing, by defining your objective function as the
negative of likelihood, (2) use log-likelihood rather than the likelihood
Dear All,
I would like to totally echo Frank Harrell's appreciation of both UseR! and
Vienna. I had a wonderful time despite being jet-lagged for the whole time!
I was also wondering whether the minutes of the final session on getting
credit for contributions to computational statistics
I am writing on the behalf of a colleague.
She needs to evaluate the correlation between two time series.
How can this be performed through R? (how many types of correlations can be
performed and which are the commands to do it?)
thank you for your help and attention
Stefano
What would be nice is to have something like a robust task view...
Andy
From: Berton Gunter
Many thanks for this Martin. There now are several packages
with what appear to be overlapping functions (or at least
algorithms). Besides those you mentioned, robust and
roblm are at least two
Achim Zeileis wrote:
[...]
The plan is to provide the original presentation slides of the
panelists and a video of the whole panel disc, and probably some minutes
and/or further information.
Did you happen to video Ivan Mizera's talk as well? I'd really like to
see that again!
--
Jeffrey
On Thu, 2006-06-22 at 15:40 -0500, Jeffrey Horner wrote:
Achim Zeileis wrote:
[...]
The plan is to provide the original presentation slides of the
panelists and a video of the whole panel disc, and probably some minutes
and/or further information.
Did you happen to video Ivan Mizera's
Stefano Sofia stefano.sofia at regione.marche.it writes:
I am writing on the behalf of a colleague.
She needs to evaluate the correlation between two time series.
How can this be performed through R? (how many types of correlations can be
performed and which are the
commands to do it?)
For those who are interested, here is a solution using grid. This
preserves some of the original spirit of do_plot_xy, but is more
satisfactory when x and y are on different scales:
my.panel - function(x, y, cex=1, ...){
require(grid)
panel.xyplot(x, y, cex = cex, ...)
a - 0.5 * cex *
I just learned that my earlier suggestion was wrong. It's better to
compute the variance of the predicted or fitted values and compare those
with the estimated variance components.
To see how to do this, consider the following minor modification of
an example in the lme
Gabor Grothendieck wrote:
On 6/21/06, Duncan Murdoch [EMAIL PROTECTED] wrote:
Peter Dalgaard wrote:
Duncan Murdoch [EMAIL PROTECTED] writes:
Suppose I have two columns, x,y. I can use order(x,y) to calculate a
permutation that puts them into increasing order of x,
with
This is more of a stats question, but since I'm using R.
Can someone tell me if the standard errors produced by hurdle(), zicounts(),
poisson, and the negative binomial formulations of three are directly
comparable? Why or why not?
Thank you,
Jeff
[[alternative HTML
On 6/22/06, Duncan Murdoch [EMAIL PROTECTED] wrote:
Jay Emerson wrote:
At the encouragement of many at UseR, I'm trying to build my first real
package. I have no C/Fortran code, just plain old R code, so it should be
rocket science. On a Linux box, I used package.skeleton() to create a
RSiteSearch(EACF) led me to
http://finzi.psych.upenn.edu/R/Rhelp02a.new/archive/43927.html;. In
this note from Oct. 2004, Brian Ripley said the EACF did not exist but
'acf' and 'pacf' did. Moreover, he said that model selection using acf
and pacf is a rather old-fashioned idea. Just
Hi
Benjamin Tyner wrote:
For those who are interested, here is a solution using grid. This
preserves some of the original spirit of do_plot_xy, but is more
satisfactory when x and y are on different scales:
my.panel - function(x, y, cex=1, ...){
require(grid)
panel.xyplot(x, y, cex =
Most clever! I'd completely forgotten about panel.segments.
Paul Murrell wrote:
Here's one way to vectorize the lines ...
my.panel2 - function(x, y, cex=1, ...){
panel.xyplot(x, y, cex = cex, ...)
a - 0.5 * cex *
convertWidth(unit(1, char), native, valueOnly=TRUE)
b - 0.5 *
Hi
Benjamin Tyner wrote:
I like the functionality provided by outer=TRUE, but when it comes time
to place separate xlabs or ylabs, I always end up 'eyeballing' it on a
case-by-case basis. For example,
##begin example
require(lattice)
cars.lo - loess(dist ~ speed, cars)
RSiteSearch(Frechet distance) returned only one hit for me just
now, and that was for a Frechet distribution, as you mentioned. Google
found www.cs.concordia.ca/cccg/papers/39.pdf, which suggests that
computing it may not be easy.
If you'd like more help from this
What's your error message? I see a syntax error in
random=list(Probe=pdBlocked(list(~1,pdCompSymm(~1
),End=~1,ProbeNo=pdCompSymm(~1))
I count 5 open parens and 3 close parens. I know that might have
been part of what you copied into this email and not what you gave R.
Hi,
I'm using zoo because it can automatically label the months of a time
series composed of daily observations.
This works well for certain time series lengths, but not for others, e.g.:
While:
library(zoo)
plot(zoo(runif(10), as.Date(2005-06-01) + 0:50))
Shows up the months and day of
On Thu, 2006-06-22 at 19:52 -0700, Spencer Graves wrote:
RSiteSearch(Frechet distance) returned only one hit for me just
now, and that was for a Frechet distribution, as you mentioned. Google
found www.cs.concordia.ca/cccg/papers/39.pdf, which suggests that
computing it may not be
see inline
Rajarshi Guha wrote:
On Thu, 2006-06-22 at 19:52 -0700, Spencer Graves wrote:
RSiteSearch(Frechet distance) returned only one hit for me just
now, and that was for a Frechet distribution, as you mentioned. Google
found www.cs.concordia.ca/cccg/papers/39.pdf, which
AndyL == Liaw, Andy [EMAIL PROTECTED]
on Thu, 22 Jun 2006 14:21:17 -0400 writes:
AndyL What would be nice is to have something like a
AndyL robust task view... Andy
Indeed. I have volunteered to do this a while ago.
First wanted to get robustbase to a reasonable state.
A
When the axis labelling does not work well you will have to do it yourself
like this. The plot statement is instructed not to plot the axis and then
we extract into tt all the dates which are day of the month 1. Then
we manually draw the axis using those.
library(zoo)
set.seed(1)
z -
46 matches
Mail list logo