I'm running samr (Two class unpaired), but keep getting the following error:
perm= 1
Error in if (logged2) { : argument is of length zero
library (impute)
library (samr)
data = list (x=dat, y=y, geneid = matrix(twoUnpaired.data[,1],ncol=1),
genenames = matrix(twoUnpaired.data[,2], ncol=1))
My Coyne a écrit :
> I have a data frame and would like to convert it into a matrix, how do I do
> that?
either use the df for the initialisation values
mat = matrix(df, ...)
or
as.matrix() could do the trick.
__
R-help@r-project.org mailing list
https:
Hi
what about
as.matrix(data_frame)
Regards
Petr Pikal
[EMAIL PROTECTED]
[EMAIL PROTECTED] napsal dne 23.01.2008 07:38:50:
> Hello,
>
> I have a data frame and would like to convert it into a matrix, how do I
do
> that?
>
>
>
> Thanks
>
>
>
> --My Coyne
>
>
>
>
>
>
>
>
>
>
Hello,
I have a data frame and would like to convert it into a matrix, how do I do
that?
Thanks
--My Coyne
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r
I would suggest that you view unix and linux as being essentially the
same, from the point of view of using R.
I use ESS for syntax coloring, help with indentation and parentheses
matching, that sort of thing, and it works very well.
-Don
At 11:08 AM -0500 1/22/08, Wensui Liu wrote:
>Dear All,
.
Just to close the query, here are the data and my R code to use nlme
to test for a strain difference in receptor binding using nlme and the
self start function SSmicmen.
Cheers,
Dave
"rownames","y","x","strain","pool"
"1",1,54.0423393249512,0.169009417295456,"dba","5_10"
"2",2,96.19451904
On Jan 22, 2008 8:39 PM, dxc13 <[EMAIL PROTECTED]> wrote:
>
> useR's,
>
> I want to create a "movie" of a sin function (from 0 to pi/2) using
> levelplot() in the lattice package. I basically want to create 20 or so
> plots of the sin function starting with an amplitude of 0 and ending at
> amplit
useR's,
I want to create a "movie" of a sin function (from 0 to pi/2) using
levelplot() in the lattice package. I basically want to create 20 or so
plots of the sin function starting with an amplitude of 0 and ending at
amplitude 1. By using a loop and plotting these in succession, it will have
Note that if you do use NA rather than 99 as others have suggested then
the A==4 term should use ifelse rather than multiplication since 0 *
NA = NA, not 0:
transform(Data, new =
(A == 1) * ((B == 1) - (B == 2)) + (A == 2) * ((B == 2) - (B ==1))
+ ifelse(A == 4, NA, 0))
In fact, although more
Thanks Charles and Gabor! Sorry Charles, the numbers were wrong in my
example. You had the correct one.
On 1/22/08, Charles C. Berry <[EMAIL PROTECTED]> wrote:
>
> On Tue, 22 Jan 2008, tom soyer wrote:
>
> > Hi,
> >
> > I am trying to reproduce some functionalities of Excel pivot table in R,
> > s
I am running 64-bit Ubuntu 7.10 and unfortunately remember seeing that
error message but not how I got it to go away.
I would first try compiling netcdf-3.6.2 from source, without changing the
default directories for installation.
Looking at the error message it seems like the 3 shared librarie
On Tue, 22 Jan 2008, tom soyer wrote:
> Hi,
>
> I am trying to reproduce some functionalities of Excel pivot table in R,
> sadly, I couldn't figure out how to do it. I am wondering if this is even
> possible in R. Does anyone know?
>
Using 'ftable()', I can match your format, but the cell values
I think you are looking for ftable:
xt <- xtabs(sales ~ company + year + quarter, data = DF)
ftable(quarter ~ year + company, xt)
You also might want to look at the reshape package and
the rpad package. Here is a demo of a pivot table in R using
rpad for the user interface and reshape for the da
Michal --
setMethod creates a nested function named .local when method arguments
do not match generic arguments. This changes the environment in which
deparse(substitute()) evaluates, and probably is a significant warning
flag about using these types of idioms with S4.
Creating .local is meant I
Hi,
I am trying to reproduce some functionalities of Excel pivot table in R,
sadly, I couldn't figure out how to do it. I am wondering if this is even
possible in R. Does anyone know?
Here is an example:
year=rep(2003,16)
quarter=rep(1:4,each=4)
sales=1:16
company=rep(c("a","b","c","d"),4)
df=da
Any insight?
I really appreciate your input.
wensui
On 1/22/08, Wensui Liu <[EMAIL PROTECTED]> wrote:
> Dear All,
> I finally have chance to have R install on our unix server. However,
> the system admin asked me if I prefer command-line or gui interface.
> I have experience with R on linux befor
On 23/01/2008, at 2:02 PM, hadley wickham wrote:
> No one else mentioned this, but if those 99s represent missings, you
> should be using NA not a special numeric value.
Amen, bro. Using ``99'' to represent a missing value is
a heinous, if all too often inflicted, crime against
No one else mentioned this, but if those 99s represent missings, you
should be using NA not a special numeric value.
Hadley
On Jan 22, 2008 5:40 PM, Dimitri Liakhovitski <[EMAIL PROTECTED]> wrote:
> Thanks a lot, everyone!
> Dimitri
>
>
> On 1/22/08, Gabor Grothendieck <[EMAIL PROTECTED]> wrote:
On 1/22/08, Judith Flores <[EMAIL PROTECTED]> wrote:
> Hi,
>
>Is there an analog function of textplot in the
> lattice package? I need to add a data frame to a
> lattice plot. I work in a Windows environment and I am
> using R v 2.6.1
There's nothing built-in, but if you are happy with fixed w
David Scott wrote:
> I am a total dunce when it comes to encodings though. How do you find the
> encoding of a file?
>
You don't. Either you know it, or you are up the proverbial creek (or
roof). The "8-bit ascii" encodings is one of the greater computer crimes
of the last century precisely b
Hello Bill,
Thanks! Indeed that works. Can you give me a hunch why?
Does it have anything to do with environments and scope?
~michal
Bill.Venables wrote:
>
> Try putting a ... argument in the method for g as well
>
> setGeneric("g", function(object, ...) standardGeneric("g"))
>
> setMethod
Dear All,
I recently got a 64bit machine and had netcdf-3.6.2 installed. Then I tried
to install ncdf package but got the following error message when using
netcdflib:
gcc -std=gnu99 -I/home/ljin/share/R-2.6.1/include
-I/home/ljin/share/R-2.6.1/include
-I. -I/usr/local/include-fpic -g -O2 -c
Try putting a ... argument in the method for g as well
setGeneric("g", function(object, ...) standardGeneric("g"))
setMethod("g", "ANY",
function(object, ...) ### change
{
nam <- deparse(substitute(object))
cat("name:", nam, "\n")
object
} )
Now it works.
Bill Venables
CSIRO Labo
Hi,
Is there an analog function of textplot in the
lattice package? I need to add a data frame to a
lattice plot. I work in a Windows environment and I am
using R v 2.6.1
Thank you,
Judith
Be a bette
Hello everyone,
I encountered the following confusing behavior of 'deparse' and
'substitute' while programming with S4 classes (see example below). It
seems like the presence of '...' argument in the definition of the
generic generates the problem. I have no clue why, can anyone explain
that to me
Thanks a lot, everyone!
Dimitri
On 1/22/08, Gabor Grothendieck <[EMAIL PROTECTED]> wrote:
> Slight correction of the English:
>
> - if A is 1 then the first term equals the coefficient of (A == 1).
> That is the first term equals 1 if B==1 and equals -1 if B==2.
> If A does not equal 1 then the
On Wed, 23 Jan 2008, David Scott wrote:
> On Tue, 22 Jan 2008, Prof Brian Ripley wrote:
>
>> On Wed, 23 Jan 2008, David Scott wrote:
>>
>>>
>>> I have encountered a problem with reading a .csv file on a linux box. I
>>> can read the file on my windows machine (under XP) but on the linux box it
>
On Tue, 22 Jan 2008, Prof Brian Ripley wrote:
> On Wed, 23 Jan 2008, David Scott wrote:
>
>>
>> I have encountered a problem with reading a .csv file on a linux box. I
>> can read the file on my windows machine (under XP) but on the linux box it
>> gives :
>>
>>> patients <- read.csv("../Patient
Dear Prof. Ripley,
Thanks very much.
Changing the locale did not help, but finding and installing (or re-installing)
xorg-x11-fonts for 75 and 100 dpi did the trick.
It's still a bit of a mystery to me, but my attempt to install xorg-x11-fonts
for 100 dpi appeared to fail, but nevertheless I found
Thank you very much.
I found .noarch.rpm's for the first 4 of the 6 you listed below and installed
them and the problem went away.
Strangely, when I tried to intstall (using rpm -Uvh) the 100 dpi ones I got a
message saying that they were already installed. Nevertheless, when I restarted
the X ser
On Wed, 23 Jan 2008, David Scott wrote:
>
> I have encountered a problem with reading a .csv file on a linux box. I
> can read the file on my windows machine (under XP) but on the linux box it
> gives :
>
>> patients <- read.csv("../Patients.csv", header = FALSE,
> + col.names
Have you also changed your locale? F8 defaults to UTF-8 locales, whereas
people usually set up RHEL3 with an 8-bit locale. That changes the font
selection, and you may find that running in en_US works whereas en_US.utf8
does not.
Note that the font you quote is an 8 point 100dpi font, at 11 p
I have encountered a problem with reading a .csv file on a linux box. I
can read the file on my windows machine (under XP) but on the linux box it
gives :
> patients <- read.csv("../Patients.csv", header = FALSE,
+ col.names = patientsNames)
Error in type.convert(data[[i]],
Slight correction of the English:
- if A is 1 then the first term equals the coefficient of (A == 1).
That is the first term equals 1 if B==1 and equals -1 if B==2.
If A does not equal 1 then the first term is zero and can be ignored.
- terms 2 and 3 are interpreted analogously
- if A==3 (or o
Wittner, Ben, Ph.D. wrote:
> I recently upgraded my OS to Fedora 8 from Red Hat Enterprise Work Station 3.
> Before I upgraded certain operations would produce a warning to the effect
> that
> a desired font was not available so one had been substituted, which was okay.
> After the upgrade to Fedo
It occured to me afterwards that this was not what you
wanted. I think Jerome Asselin in
http://finzi.psych.upenn.edu/R/Rhelp02a/archive/15483.html
has a solution that may do what you want
Try
legend(3, 0.45, legend = c("x1", "x2", "mean(x1)",
"mean(x2)"), pch=c(22,22,30,30),
col = c("
I recently upgraded my OS to Fedora 8 from Red Hat Enterprise Work Station 3.
Before I upgraded certain operations would produce a warning to the effect that
a desired font was not available so one had been substituted, which was okay.
After the upgrade to Fedora 8, the plotting operation halts mid
box.lty = 0
assuming I understand the question.
--- Tom Boonen <[EMAIL PROTECTED]> wrote:
> Is there any way suppress box color and frame of a
> box drawn by
> legend(,fill)? I am able to suppress the color, but
> not the frame (see
> the example below). Many thanks! (This follows up
> from a
Have a look at stripplot in lattice. I think it may do
what you want if you cbind e & f and then create an
identifier to plot against.
e <- c(17358865 , 17966995 , 21306539 , 27880531,
34166504, 36111044, 36266288,
36854306 , 43786190 , 44322336 , 45529444, 46302360,
53479132, 58567262,
6
> Dear list,
>
> Has anyone created a version of SSmicmen that allows testing for
> group differences? The basic Michaelis-Menten equation is:
>
> (Bmax * X) / (Kd + X).
>
> The nlme package allows modeling of random effects for Bmax and Kd
> as needed, but I curious how I can build in group di
Is there any way suppress box color and frame of a box drawn by
legend(,fill)? I am able to suppress the color, but not the frame (see
the example below). Many thanks! (This follows up from a question
asked on the list in 2006 by Florian Koller)
Tom
x1 <- rnorm(100)
x2 <- rnorm(100, 2)
hist(x1, m
Try this:
z1 <- c(1,-1,0,99)[Data$A]
z2 <- c(-1,1,0,99)[Data$A]
Data$new <- ifelse(Data$B == 1, z1,z2)
(This does not generalize, however, and assumes that the values you gave are
exact. Gabor's approach would work more generally)
-- Bert Gunter
Genentech Nonclinical Statistics
-Original Me
You could create a lookup table or use recode in the car package.
Another possibility is to use a logical/arithmetic expression. The
following expression says that
- if A is 1 then use the first term equals the coefficient, namely 1
if B ==1 and -1 if B == 2.
Also, if A is not 1 then that term
Dimitri Liakhovitski wrote:
> Hello,
> I have 2 variables in my sample Data: Data$A and Data$B
> Variable Data$A can assume values: 1, 2, 3, and 4.
> Variable Data$B identifies my cases and can assume values: 1 and 2.
>
> I need to recode my variable Data$A into a new variable Data$new such that:
hi,
I want to plot a dotplot graph but unfortunately R does not have it any more.
It suggest to use either the stripchart or the dotchart and i prefer to play
around with the stripchart graph. Sadly, the result is not like i want where
I'm actually wants the plots/points were scattered aro
Dear list,
Has anyone created a version of SSmicmen that allows testing for group
differences? The basic Michaelis-Menten equation is:
(Bmax * X) / (Kd + X).
The nlme package allows modeling of random effects for Bmax and Kd as
needed, but I curious how I can build in group differences? I ha
On Tue, 22 Jan 2008, James W. MacDonald wrote:
> This is questionable advice for many CRAN packages, and horrible advice
> for a Bioconductor package. If there are any dependencies (and BioC
> packages often have many, and their dependencies may have
> dependencies...) you can end up in download h
Hi Franzi,
Up to I know you can´t predict values without you have x2,x3 and x4 parameters.
So you have three possible solution
1) set x2, x3 and x4 to Zero, *but* it will depend so much of what you want,
because if you set them to zero, it means that you are adjusting something like
mod<-lm(y~
Hello,
I have 2 variables in my sample Data: Data$A and Data$B
Variable Data$A can assume values: 1, 2, 3, and 4.
Variable Data$B identifies my cases and can assume values: 1 and 2.
I need to recode my variable Data$A into a new variable Data$new such that:
People who are Data[Data$B %in% 1, ] a
Hi just wondering if there is a package that can get the maximum likelihood
or method of moments estimator for distributions with censored data? The
distributions I'm interested in are: Exponential, pareto, beta, gamma and
lognormal.
--
View this message in context:
http://www.nabble.com/MLE-fo
On Tuesday 22 January 2008 13:52:29 Thomas Steiner wrote:
> Thank you very much Duncan for your quick answers.
>
> > You're not passing a function as myfunk1, you're passing mf, which is
> > the result of evaluating myfun1, so it's a numeric vector.
>
> Yes, this is exacty my problem.
> If I leave
the FinTS package includes in scripts\ch02.R a comparison of 4 different
AFD unit root functions with a published example.
it also includes a function plotArmaTrueacf that computes the roots from
the AR part of a theoretical or fitted model. From this, you can see if
any roots lie near the un
Andrea Onofri wrote:
> Dear all,
>
> I'm using R to perform multiple comparison testing on agriculture
> genotype trials. To perform the Duncan's MRT, I use the qtukey()
> function with the following syntax:
>
> qtukey(p = ((1 - 0.05) ^ (pos - 1)), nmeans = pos, df = ni)
>
> I experience a stran
On 1/22/2008 10:19 AM, [EMAIL PROTECTED] wrote:
> Dear R users,
> I have been having a problem with my file Rprofile.site. I did already ask
> the list some suggestions which have been well taken into account but
> unfortunately have not completely resolved my problem. I seem to have 2 files
> o
It is possible to place two functions in a recursive function
Main results so as to simultaneously?
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting
Dear All,
I finally have chance to have R install on our unix server. However,
the system admin asked me if I prefer command-line or gui interface.
I have experience with R on linux before but never use R on unix. Here
are my questions that I need you guys help.
1) is there a good gui for R/unix li
Dear Duncan,
thanks a lot for your answer. I was think a was distracted by the FED
rate cut ;)
Now it works.
Have a nice day
Thomas
myfun1<-function(x,pa) {
return(pa[1]*x^2+pa[2]*x+pa[3])
}
myfun2<-function(x,param,myfunk1,pa) {
return(param[1]*myfunk1(x,pa)+param[2]*myfunk1(-x,pa))
}
test<-
If anyone gets R working with Rmpi and Grid Engine, please let me
know. I will need to set up a compute farm with SGE.
Thx,
--Chi
On Jan 21, 2008 8:19 PM, Mark Kimpel <[EMAIL PROTECTED]> wrote:
> try Rmpi package
>
> On Jan 21, 2008 7:13 PM, markaoki <[EMAIL PROTECTED]> wrote:
>
> > hi,
> > Does
have you looked at lsoda{odesolve}?
have you looked at the scripts\CSTR subdirectory in the fda package? it
includes an example worked in both R and Matlab with slightly better
answers in R but with a much longer compute time.
sg
The fda package
Peter Dalgaard wrote:
> Markku Karhunen wrote:
Dear Dr. Bates, and R-help,
I just found the reason I got the error message is because I copied
the code directly from the book. When I tried the code in
"~\library\nlme\scripts" under the R installation directory like the
following, I got the same answere as in the book.
anova(fm2BW.lme, L = c("
Dear all,
I'm using R to perform multiple comparison testing on agriculture
genotype trials. To perform the Duncan's MRT, I use the qtukey()
function with the following syntax:
qtukey(p = ((1 - 0.05) ^ (pos - 1)), nmeans = pos, df = ni)
I experience a strange behaviour when the number of mean
Dear Dr. Bates, and R-help,
I've tried the anova function to test the difference between two
coefficients, as shown on page 225 of your book "Mixed Effects Models
in S and S-Plus (Statistics and Computing)".
When I type: anova( fm2BW.lme, L = c(TimeDiet2 = 1, TimeDiet3 = -1) )
I got the follow
> Rather, non-interactive R does not run an event loop. The usual way
> around this is to use a pty, as R run from a pty is considered to be
> interactive.
>
> (Whether a fifo and a named pipe are the same concept is moot: some OSes
> have one and not the other.)
>
> The plan is to use thr
Dear R users,
I have been having a problem with my file Rprofile.site. I did already ask the
list some suggestions which have been well taken into account but unfortunately
have not completely resolved my problem. I seem to have 2 files of
Rprofile.site on my computer. If I open the file through
Rather, non-interactive R does not run an event loop. The usual way
around this is to use a pty, as R run from a pty is considered to be
interactive.
(Whether a fifo and a named pipe are the same concept is moot: some OSes
have one and not the other.)
The plan is to use threads in due course
On 1/22/2008 9:50 AM, Fränzi Korner wrote:
> Hello
>
>
>
> how can I predict from a lm-object over a range of values of one explanatory
> variable without having to specify values for all the other explanatory
> variables?
>
>
>
> e.g.
>
>
>
> mod<-lm(y~x1+x2+x3+x4)
>
>
>
> x1.new
I was told that they had a UPS failure on one of the servers at the
weekend. It has been up and down for parts of each of the last three
days, with many down periods (both short and long).
On Tue, 22 Jan 2008, Peter Dalgaard wrote:
Stefan Grosse wrote:
I am having problems to access the r-p
Agreed, i had no idea that this is a Bioconductor package.
G.
On Tue, Jan 22, 2008 at 09:49:50AM -0500, James W. MacDonald wrote:
> This is questionable advice for many CRAN packages, and horrible advice
> for a Bioconductor package. If there are any dependencies (and BioC
> packages often hav
Hello
how can I predict from a lm-object over a range of values of one explanatory
variable without having to specify values for all the other explanatory
variables?
e.g.
mod<-lm(y~x1+x2+x3+x4)
x1.new<-seq(0, 100)
predict(mod, new=list(x1=x1.new))
Here, predict() does not
This is questionable advice for many CRAN packages, and horrible advice
for a Bioconductor package. If there are any dependencies (and BioC
packages often have many, and their dependencies may have
dependencies...) you can end up in download hell, all because you have
ignored the functionality
j daniel wrote:
>
>
> I would like to print the "address" of the smaller dendrograms on the edge
> similar to this:
>
> addr <- function(n) {
> if(!is.leaf(n)) {
> attr(n, "edgetext") <- paste("height of",(attr(n,"height"))
> }
> n
> }
> labeledDends <- dendrapply(de
j daniel wrote:
>
>
> I would like to print the "address" of the smaller dendrograms on the edge
> similar to this:
>
> addr <- function(n) {
> if(!is.leaf(n)) {
> attr(n, "edgetext") <- paste("height of",(attr(n,"height"))
> }
> n
> }
> labeledDends <- dendrapply(de
xx<- file.info(dir()); xx
xx[order(xx$mtime),] ?
--- Alberto Monteiro <[EMAIL PROTECTED]> wrote:
> Is there any (list.files)-like function that sorts
> the files by
> (modification) date?
>
> Alberto Monteiro
>
> __
> R-help@r-project.org mailing lis
It is definitely on CRAN:
http://cran.at.r-project.org/src/contrib/Descriptions/lattice.html
You can download and install it "by hand", but if you want to
make install.packages work, please give us at least an error message
or something.
G.
On Tue, Jan 22, 2008 at 03:29:19PM +0100, Armin Goralc
Hi list
I tried to install package lattice on FreeBSD, but install.package()
does not seem to find it in the repositories, even trying different
mirrors. Could it be that lattice package is not available for
FreeBSD?
--
Armin Goralczyk, M.D.
--
Universitätsmedizin Göttingen
Abteilung Allgemein- u
Create a data frame from the coefficients of your summary.lm objects
and use xtable.data.frame to latex that. At the R console this will
display the relevant source code to see how to do it:
xtable:::xtable.lm
xtable:::xtable.summary.lm
On Jan 22, 2008 9:02 AM, 宋时歌 <[EMAIL PROTECTED]> wrote:
> D
It is not a good idea to use "sample' when building an
example like this! Running the code does not give the
example dataframe.
This is crude but it will do what you want.
x <- " Z Y X
1 4 Yes
2 1 No
3 2 Perhaps
4 3 Yes
5 4 No
6 5 No
7 1 Ye
Hi!
To label your dendrogram edges with the path to each of them, execute the
following script (assuming that your dendrogram is 'dend', see last 2
lines).
dendrapplyGlobal <- function(dend,attrName,FUN,...,attrNameTo=NULL) {
if (is.null(attrNameTo)) {
attrNameTo <- attr
Actually, I'm running 2.6.1. The old version is in the path, but I am
working with the most recent version. I am working in DOS and am at the
prompt c:\program files\r\r-2.6.1\bin. From here I do all of the work in
building the package (build, check, install).
> -Original Message-
> From:
Dear All,
Is there a way to present results from multiple models in one LaTeX
table? I did some google search and found out that xtable cannot
automate this process
(https://stat.ethz.ch/pipermail/r-help/2006-August/74.html), are
there other alternatives? What about Design and Hmisc? Thanks.
Dear Users,
Anyone knows a good package to works with risk management?
In particularly, if exist works in R about Solvency or Basileia projects?
Best Regards
Ana Patrícia Martins
[[alternative HTML version deleted]]
__
R-help@r-
Doran, Harold wrote:
> Thanks, Uwe. Before I modify this path, I want to make sure of one
> thing. My path is set according to the specifications in the document
> prescribed by Duncan Murdoch (at link below). Indeed, my path includes
> the proper location of my MikTex and pdflatex.exe files. Her
Thanks, Uwe. Before I modify this path, I want to make sure of one
thing. My path is set according to the specifications in the document
prescribed by Duncan Murdoch (at link below). Indeed, my path includes
the proper location of my MikTex and pdflatex.exe files. Here is my path
from the command y
Stefan Grosse wrote:
> I am having problems to access the r-project.org homepage, someone else as
> well?
>
> (I know there are CRAN mirrors but they link back on the main page if I
> search
> something)
>
> Stefan
>
>
It's up for me now, but I had rather slow access earlier in the day.
--
On 1/22/2008 8:04 AM, Stefan Grosse wrote:
> I am having problems to access the r-project.org homepage, someone else as
> well?
>
> (I know there are CRAN mirrors but they link back on the main page if I
> search
> something)
They look fine from here. (By the way, the r-project.org homepage
On 1/22/2008 7:52 AM, Thomas Steiner wrote:
> Thank you very much Duncan for your quick answers.
>
>> You're not passing a function as myfunk1, you're passing mf, which is
>> the result of evaluating myfun1, so it's a numeric vector.
>
> Yes, this is exacty my problem.
> If I leave it away, the p
Hello everyone,
I'm working on some ggwr model and I obtained a .ggwr object, now I'm ascking:
Can I StepAIC the object to evaluate the best model and decide what variables,
should get in???
Thanks
Luca Moiana
PhD Candidate - Environmental Science
University of Milan - Bicocca
_
I am having problems to access the r-project.org homepage, someone else as
well?
(I know there are CRAN mirrors but they link back on the main page if I search
something)
Stefan
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listi
Thank you very much Duncan for your quick answers.
> You're not passing a function as myfunk1, you're passing mf, which is
> the result of evaluating myfun1, so it's a numeric vector.
Yes, this is exacty my problem.
If I leave it away, the problem will not be resolved (it needs pa or not)
myfun1
> I am using 'arrows' funtion to plot the variance as error bar, BUT error
> bar goes only one side of the data point, I need to plot the error bar
on
> both side of the data point (plot is attached), I am using following
> commands to plot,
>
> plot(file3$lat,file3$STotwoKm,pch=21,cex=2.5,ylim=c
Thanks, John,
Here is some code to show what I want to do. BTW, it seems there is a
bug in svalue in gWidgetstcltk for gtext when using the drop=T
argument.
getsel <- function(obj, toolkit, ...) {
### get the selected text from gtext
getWidget <- gWidgetstcltk:::getWidget
if(tclvalue(tktag.ranges
Karin Lagesen wrote:
> I am sorry if this is a faq or tutorial somewhere, but I am unable to
> solve this one.
>
> What I am looking for is a count of how many different
> categories(numbers in this case) that appears for a given factor.
>
> Example:
>
>
>> l <- c("Yes", "No", "Perhaps")
>> x <-
I am sorry if this is a faq or tutorial somewhere, but I am unable to
solve this one.
What I am looking for is a count of how many different
categories(numbers in this case) that appears for a given factor.
Example:
> l <- c("Yes", "No", "Perhaps")
> x <- factor( sample(l, 10, replace=T), level
Domenico Vistocco wrote:
> Pilar Loren wrote:
>
>> Hi, is it possible to do a multivariable barplot with ggplot2?
>>
>> I have something like that:
>>
>>
>>
>>> df
>>>
>>>
>>LENGTH LAT
>> 091639 10.002 42.26282
>> 091640 30.808 42.26834
>> 091641 21.5
hello Charilaos
thank you for your reply.
i know how to use R to calculate the results. i want to simplify the results
mathematically.
i found a reference that helps.
see mardia, kent, bibby, "multivariate analysis", (2003) pg 457,458 for the
correct simplifiations.
(for those inter
On 22/01/2008 6:51 AM, Thomas Steiner wrote:
> Okay, let me try to better say what I meant:
>
> myfun1<-function(x=5,pa) {
> return(pa[1]*x^2+pa[2]*x+pa[3])
> }
> myfun2<-function(x=5,param,myfunk1) {
> return(param[1]*myfunk1(x)+param[2]*myfunk1(x))
> }
> test<-function(pars1,pars2,lo,up){
>
On 22/01/2008 5:30 AM, Thomas Steiner wrote:
> I want to use a function as an argument to ingtegrate it twice.
> See the following (senseless) example of a double integration:
>
> test<-function(sf,lo,up,rest) {
> innerFkn<-function(sf,lo) {
> inte=integrate(f=sf,lower=lo,upper=4)
> retu
Pilar Loren wrote:
> Hi, is it possible to do a multivariable barplot with ggplot2?
>
> I have something like that:
>
>
>> df
>>
>LENGTH LAT
> 091639 10.002 42.26282
> 091640 30.808 42.26834
> 091641 21.591 42.31689
> 091642 22.030 41.53246
> 091643 22.744 42
Okay, let me try to better say what I meant:
myfun1<-function(x=5,pa) {
return(pa[1]*x^2+pa[2]*x+pa[3])
}
myfun2<-function(x=5,param,myfunk1) {
return(param[1]*myfunk1(x)+param[2]*myfunk1(x))
}
test<-function(pars1,pars2,lo,up){
mf=myfun1(x=2,pa=8*pars1)
integ=integrate(f=myfun2,lower=lo,u
Markku Karhunen wrote:
> Thanks, Dr. Maechler.
>
>> No, there's no such track.
>> [ Matlab users coming to R may produce wrong R code
>> by using 0:n-1 instead of 0:(n-1) ; but I don't assume this
>> would be the case ]
>>
>>
>>
> Been there, done that!
>
>> MK> We use just a
1 - 100 of 125 matches
Mail list logo
