On 01-06-2013, at 02:56, Justin wrote:
> I build a test package in order to publish my own package to bioconductor.
>
> I am using package.skeleton
> Step 1. create test package "mypkg"
> f <- function(x,y) x+y
> package.skeleton(list=c("f"), name="mypkg")
>
> Step 2. build tar.gz file
>
You should seek local statistical help. This list is not the right
place to seek what appears to be statistical consulting and, indeed,
basic statistical instruction.
-- Bert
On Fri, May 31, 2013 at 6:27 PM, Luis Fernando García Hernández
wrote:
> Dear Friends,
>
> I am new on R so I ask you to
Hello peter,
Thanks for the comment. wilcox.exact is simpler as you pointed out but the
fact that it is no longer being developed is somewhat concerning.
Regards
Janh
On Fri, May 31, 2013 at 6:50 PM, Peter Ehlers wrote:
> On 2013-05-30 20:20, Janh Anni wrote:
>
>> Hello Greg,
>>
>> Thank you
I build a test package in order to publish my own package to bioconductor.
I am using package.skeleton
Step 1. create test package "mypkg"
 f <- function(x,y) x+y
 package.skeleton(list=c("f"), name="mypkg")
Step 2. build tar.gz file
{mars:/local/workspace01/zhangju/R_autopackage_Elbow}../bi
Hello, R users!
I am struggling with the following problem:
I need to compute a P-value for a mixture of two chi-squared
distributions. My P-value is given by:
P = 0.5*prob(sqrt(chi2(1)) <= x) + 0.5*prob(sqrt(chi2(2)) <= x)
In words, I need to compute the p-value for 5050 mixture of the square
Hello, R users!
I am struggling with the following problem:
I need to compute a P-value for a mixture of two chi-squared
distributions. My P-value is given by:
P = 0.5*prob(sqrt(chi2(1)) <= x) + 0.5*prob(sqrt(chi2(2)) <= x)
In words, I need to compute the p-value for 5050 mixture of the square
Is this what you want? I was not clear on your algorithm, but is looks
like you wanted descending values:
> testx <-
+ function(n, verbose = FALSE)
+ {
+ mat <- cbind(optA = sample(n, n, TRUE), perm = seq(n))
+ if (verbose){
+ cat("***starting matrix\n")
+ print(mat)
+
Dear Friends,
I am new on R so I ask you to excuse me if this question sounds fool. I
want to see if there is a significativa relationship between the mating
(response variable) and several explanatory variables such as individual
number (categorical), leg movemente (continous) and the reuse of
in
Dear R Users,
I created a function which returns a value every time it's run (A
simplified toy example is attached on this mail).
For example spat(a,b,c,d) # run the first time and it gives you ans1=
10, perm=1 ;
run the second time and gives you ans2= 7, perm=2 etc
I store both the result
The code below produces the plot hosted here:
http://www.span-lab.com/ChartStop.jpeg
error.bar <- function(x, y, upper, lower=upper, length=0.1,...){
if(length(x) != length(y) | length(y) !=length(lower) | length(lower) !=
length(upper))
stop("vectors must be same length")
arrows(
Hi,
You could reduce those steps by:
as.data.frame(do.call(rbind,a2))
A.K.
- Original Message -
From: Abdul Rahman bin Kassim (Dr.)
To: John Kane ; "r-help@r-project.org"
Cc:
Sent: Friday, May 31, 2013 11:47 AM
Subject: Re: [R] Returning combine output from R loop
Dear Kane,
Thanks
On Fri, 31 May 2013 18:10:19 -0500 Robert Baer wrote:
> On 5/31/2013 11:59 AM, Ranjan Maitra wrote:
> > Hi John,
> >
> > I suspect you may be missing a c()?
> >
> > On Fri, 31 May 2013 06:05:45 -0800 John Kane
> > wrote:
> >
> >> paks <- install.packages( "Hmisc", "plyr")
> > paks <- install.p
Dear Kevin,
I generally prefer your solution. I didn't realize that col2rgb() worked
with hex-colour input (as opposed to named colours), so my code converting
hex numbers to decimal is unnecessary; and using ifelse() is clearer than
replacing the non-matches.
I'm not so sure about avoiding the c
On 5/31/2013 11:59 AM, Ranjan Maitra wrote:
Hi John,
I suspect you may be missing a c()?
On Fri, 31 May 2013 06:05:45 -0800 John Kane
wrote:
paks <- install.packages( "Hmisc", "plyr")
paks <- install.packages( c("Hmisc", "plyr"))
install.packages(paks)
You can use the command l
HI,
Try this:
data1 <- data.frame("var1"=c(1,2,3),"var2"=c("A","B","C"),"var3"=c(4,5,6))
#your example
data2 <- data.frame("var1"=c(1,2,3),"var2"=c("5","6","9"),"var3"=c(4,5,6))
#your example
data3<- data.frame(var1=c(5,6,5,5),var2=c(4,4,5,3),var3=c(1,4,3,5))
data4<- data.frame(var1=c(1,2,3),va
On 2013-05-30 20:20, Janh Anni wrote:
Hello Greg,
Thank you so much for your kind assistance. It looks like there's no way
around using the formula format. I longed in vain for a simpler script
more like the wilcox.test format. Thanks again.
Janh
I don't see why the formula syntax would be
On Fri, 31 May 2013, Michal Kvasni?ka wrote:
Hallo.
Many thanks for your answer. Let me check please that I do understand
it correctly. Does it mean that the estimated log-likelyhood function
is (in the Gaussian case)
sum y * log F(x'b / exp(z'g)) + sum (1 - y) * log(1 - F(x'b / exp(z'g))
wh
On May 31, 2013, at 2:38 PM, Stephen Sefick wrote:
> R version 3.0.0 (2013-04-03)
> Platform: x86_64-redhat-linux-gnu (64-bit)
>
> locale:
> [1] LC_CTYPE=en_US.utf8 LC_NUMERIC=C
> [3] LC_TIME=en_US.utf8LC_COLLATE=en_US.utf8
> [5] LC_MONETARY=en_US.utf8LC_MESSAGES=en_US.utf8
> [
Hi,
On Fri, May 31, 2013 at 5:38 PM, Stephen Sefick wrote:
> R version 3.0.0 (2013-04-03)
> Platform: x86_64-redhat-linux-gnu (64-bit)
>
> locale:
> [1] LC_CTYPE=en_US.utf8 LC_NUMERIC=C
> [3] LC_TIME=en_US.utf8LC_COLLATE=en_US.utf8
> [5] LC_MONETARY=en_US.utf8LC_MESSAGES=en_U
Hi Johnny,
I like the ideas here, just one small request. Please don't try to take
over the comment() function! comment() is already a function in the base
package, please don't mask it with yours.
Thanks for considering my humble request.
Best,
Ista
On Fri, May 31, 2013 at 1:25 PM, Johnny Zha
R version 3.0.0 (2013-04-03)
Platform: x86_64-redhat-linux-gnu (64-bit)
locale:
[1] LC_CTYPE=en_US.utf8 LC_NUMERIC=C
[3] LC_TIME=en_US.utf8LC_COLLATE=en_US.utf8
[5] LC_MONETARY=en_US.utf8LC_MESSAGES=en_US.utf8
[7] LC_PAPER=CLC_NAME=C
[9] LC_ADDRESS=C
Thanks for the discussion. I've also wanted to be able to find nearest
colors. I took the code and comments in this thread and simplified the
function even further. (Personally, I think using closures results in
Rube-Goldberg code. YMMV.) The first example below is what I use for
'group' color
On 31.05.2013 16:58, Gary Dong wrote:
Dear R users,
I am estimating a nested logit model using "mlogit", but keep getting this
error message:
"Error in x[[1]] : subscript out of bounds"
We need a reproducible example.
Uwe Ligges
Anyone can tell me what this error means?
Simple MNL mode
Another possibility:
IE <- speciesTime1[,-1] - speciesTime2[,-1]
Imm <- data.frame(addmargins(as.matrix(ifelse(IE<0, -1, 0)*IE), 2))
Imm
Exti <- data.frame(addmargins(as.matrix(ifelse(IE>0, 1, 0)*IE), 2))
Exti
-
David L Carlson
Associate Professor of Anthropolo
Hi All,
Thanks all for your kind help else it would have been very tough to go
ahead. I convey my regards to all of you.
Upananda
On Fri, May 31, 2013 at 10:35 PM, John Kane wrote:
> Arh, a sloppy copy and paste.
>
> Thanks
>
> John Kane
> Kingston ON Canada
>
>
> > -Original Message-
Thank you very much for your feedback either through r-help list or direct
contact. It seemed that "Rinfo" could be a good alternative the package name.
Based on the feedback I got, I have made the following changes:
(1) A user can now use the functions download, rate, comment, like without time
On May 31, 2013, at 4:21 AM, ELIAS Patrick wrote:
> Hi
>
> At first, as a new user of R (why have I been waiting for so long ?), let me
> tell you how I highly appreciate this fanstastic free tool! (The enthusiasm
> of a new fan?!)
>
> When recently carrying out an extreme value analysis, I c
This was a known problem which Kurt Hornik and I solved earlier today.
Short version: the (Debian testing Linux) machine which produces them
was updated to texinfo 5.1, and that is not compatible with R 3.0.1.
This lack of back-compatibility is really rather annoying, and if you
meet it, you n
On May 31, 2013, at 6:01 AM, Ulf Sandvik wrote:
> Hi,
>
> I have fitted a shared frailty model using coxph in the survival
> package with 'center' as random effect. Now I'm trying to obtain the
> conditional survival curve for a new test case that comes from one of
> the specified centers in the
Arh, a sloppy copy and paste.
Thanks
John Kane
Kingston ON Canada
> -Original Message-
> From: maitra.mbox.igno...@inbox.com
> Sent: Fri, 31 May 2013 11:59:05 -0500
> To: r-h...@stat.math.ethz.ch
> Subject: Re: [R] how to install R 3.0.1
>
> Hi John,
>
> I suspect you may be miss
Hi John,
I suspect you may be missing a c()?
On Fri, 31 May 2013 06:05:45 -0800 John Kane
wrote:
> paks <- install.packages( "Hmisc", "plyr")
paks <- install.packages( c("Hmisc", "plyr"))
> install.packages(paks)
> You can use the command library() to get a list of what is installe
On 31-05-2013, at 18:18, Upananda Pani wrote:
> Does it mean the packages are already updated ?
>
Yes. Unless you got error messages.
Try library(…) with one of the packages.
Berend
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/
Try again. I'm not having any trouble accessing those pages though the help
system or directly by pasting the urls into my browser.
-
David L Carlson
Associate Professor of Anthropology
Texas A&M University
College Station, TX 77840-4352
-Original Message
Dear Kane,
Great and thanks for the do.call function.
Abd Rahman
From: arun [smartpink...@yahoo.com]
Sent: Saturday, June 01, 2013 12:23 AM
To: Abdul Rahman bin Kassim (Dr.)
Cc: R help; John Kane
Subject: Re: [R] Returning combine output from R loop
Hi,
Y
Bert,
I have not studied the help in enough depth. My, limited, understanding of
recursion comes from the linux command line - e.g., rm -r will remove all
files in a folder by descending (probably not the right word) into the
folder
, removing all of the files, and then removing the folder itself
This might supply a hint on what to look for.
https://stat.ethz.ch/pipermail/r-help/2009-July/204388.html
John Kane
Kingston ON Canada
> -Original Message-
> From: ecol...@hotmail.com
> Sent: Fri, 31 May 2013 12:06:38 +
> To: r-help@r-project.org
> Subject: [R] question about trpaths
Does it mean the packages are already updated ?
On Fri, May 31, 2013 at 9:35 PM, Prof Brian Ripley wrote:
> On 31/05/2013 16:53, Upananda Pani wrote:
>
>> When I am updating packages, I got the following output:
>>
>> The downloaded binary packages are in
>> C:\Users\upani\AppData\Local
On May 31, 2013, at 7:50 AM, James F. Reid wrote:
> Dear all,
>
> I've found the html versions of
> 'An Introduction to R' [http://cran.r-project.org/doc/manuals/R-exts.html]
> 'Writing R Extensions' [http://cran.r-project.org/doc/manuals/R-intro.html
> ]
> to be empty. Not sure if this intentio
Dear all,
I am a new user of R. I use r to estimate a jump-diffusion AR model. When I
calculate the standard error regarding of the parameters, I get negative
variance. Could anyone explain why this happen or Could you give me some help
to fix it?
Attachment is the code.
I thank you all in ad
Hi,
I have fitted a shared frailty model using coxph in the survival
package with 'center' as random effect. Now I'm trying to obtain the
conditional survival curve for a new test case that comes from one of
the specified centers in the model.
The data set on which the model is fitted contains 10
Hi
At first, as a new user of R (why have I been waiting for so long ?), let me
tell you how I highly appreciate this fanstastic free tool! (The enthusiasm of
a new fan?!)
When recently carrying out an extreme value analysis, I consumed a lot of time
for dealing with the arguments of the qgpd
Dear all,
I've found the html versions of
'An Introduction to R' [http://cran.r-project.org/doc/manuals/R-exts.html]
'Writing R Extensions' [http://cran.r-project.org/doc/manuals/R-intro.html
]
to be empty. Not sure if this intentional, some transitional state of sort
or if it is a genuine bug i
Trying to implement a simple regression using biglm package for quite some
time. But is feeling frustrated with errors. Please suggest any way around for
this error.
> formula1 <- IsBadBuy ~ RefId
> for (i in chunk(car, by=1000))
+ {
+ if (i[1]==1)
+ {
+ message("first chun
Hello!
I try to use Tinn R (latest Version) With Windows 8. Wnen try to send a
command, always get the error trpaths[4]. I have configured profilesite, but it
doesnât work at all.
Also I set the access to read and write from R folder, anyway, problem remain.
Does anyone else usng Tinn-R in
On May 31, 2013, at 17:10 , Stefano Sofia wrote:
> I find difficult to understand why in
> lm(log(Y) ~ X)
> Y is assumed lognormal.
> I know that if Y ~ N then Z=exp(Y) ~ LN, and that if Y ~ LN then Z=log(Y) ~ N.
> In
> lm(log(Y) ~ X)
> I assume Y ~ N(mu, sigma^2), and then exp(Y) would be distri
On 31/05/2013 16:53, Upananda Pani wrote:
When I am updating packages, I got the following output:
The downloaded binary packages are in
C:\Users\upani\AppData\Local\Temp\RtmpmC7A9U\downloaded_packages
So What to do after this ?
Nothing. These will be removed when you quit R.
On
When I am updating packages, I got the following output:
The downloaded binary packages are in
C:\Users\upani\AppData\Local\Temp\RtmpmC7A9U\downloaded_packages
So What to do after this ?
On Fri, May 31, 2013 at 7:49 PM, Steve Friedman wrote:
> Thanks for the clarification.
> On May 31,
Dear Kane,
Thanks for your response and improve R script. With additional R script below,
my question has been resolved. Thanks again for your kind help.
b1<-data.frame(a2[1])
b2<-data.frame(a2[2])
b3<-data.frame(a2[3])
bb<-rbind(b1,b2,b3)
---
Abd Rahman
___
I find difficult to understand why in
lm(log(Y) ~ X)
Y is assumed lognormal.
I know that if Y ~ N then Z=exp(Y) ~ LN, and that if Y ~ LN then Z=log(Y) ~ N.
In
lm(log(Y) ~ X)
I assume Y ~ N(mu, sigma^2), and then exp(Y) would be distributed by a LN, not l
og(Y).
Where is my mistake?
Moreover, in
gl
Dear R users,
I am estimating a nested logit model using "mlogit", but keep getting this
error message:
"Error in x[[1]] : subscript out of bounds"
Anyone can tell me what this error means?
Simple MNL model worked with the same data.
Thank you!
Gary
[[alternative HTML version deleted
One way is to put them in a list.
Does this help?
a0 <- data.frame(initial_size=sample(30,10),sp=gl(2,5,10),
grow=as.numeric(as.character(gl(2,5,10)))*0.5)
a2<- list()
for( i in 1:3){
a1 <- a0$initial_size+a0$grow
a2[[i]] <- cbind(sp=a0$sp,initial_size=a1+i,yr=i)
}
John Kane
Kingsto
On 31/05/2013 14:59, Duncan Murdoch wrote:
On 31/05/2013 9:49 AM, Christian Hoffmann wrote:
Obviously,
chooseCRANmirror()
is run at every start. Can I permanently store my choice with q() and
'yes' ?
No, the result is not stored as an object in your global workspace, it
is saved by setting
Hi John
This has been an interesting discussion.
Though you have a solution for your needs, you might be interested in
this javascript implementation that allows you to visually compare color
distances in various color spaces
http://stevehanov.ca/blog/index.php?id=116
And, all the theory of c
On 31/05/2013 14:44, Steve Friedman wrote:
You can't. You must copy them to the new installation directory. After that
you can use the update package command to check for and install the
upgrades packages.
Not so if you organized your packages sensibly in a separate library.
See
http://cran.r
Thanks for the clarification.
On May 31, 2013 10:19 AM, "Prof Brian Ripley" wrote:
> On 31/05/2013 14:44, Steve Friedman wrote:
>
>> You can't. You must copy them to the new installation directory. After
>> that
>> you can use the update package command to check for and install the
>> upgrades pa
Thanks for the help. I think I have it figured out...
inside of merge dfs[-1] lops off the first element in the list and
merges with dfs[[1]] then this is repeated for the entire list? With
Recall inside of a function this process repeats until there are no more
objects to merge?
many thank
There may be a better way but my practice is to simply create a vector of the
optional packages that I am using and run an install.packages:
Example:
paks <- install.packages( "Hmisc", "plyr")
install.packages(paks)
You can use the command library()
to get a list of what is installed
Obviously,
chooseCRANmirror()
is run at every start. Can I permanently store my choice with q() and 'yes' ?
Cheers Christian
--
Christian W. Hoffmann,
CH - 8915 Hausen am Albis, Switzerland
Rigiblickstrasse 15 b, Tel.+41-44-7640853
c-w.hoffm...@sunrise.ch,
christ...@echoffmann.ch,
www.echoffm
On 31/05/2013 9:49 AM, Christian Hoffmann wrote:
Obviously,
chooseCRANmirror()
is run at every start. Can I permanently store my choice with q() and 'yes' ?
No, the result is not stored as an object in your global workspace, it
is saved by setting an option to a URL. (See the help page, o
You can't. You must copy them to the new installation directory. After that
you can use the update package command to check for and install the
upgrades packages.
On May 31, 2013 9:43 AM, "Upananda Pani" wrote:
> Hi John,
>
> Thanks for your reply .How to Update all the packages ( Which i am alre
Hi John,
Thanks for your reply .How to Update all the packages ( Which i am already
using ) automatically to the new version.?
With regards,
Upananda
On Fri, May 31, 2013 at 7:01 PM, John Kane wrote:
> Sorry I misread your post. Just download the 3.0.1 for Windows and
> install. You wil
Sorry I misread your post. Just download the 3.0.1 for Windows and install.
You will need to reinstall any additional packages that you have installed.
John Kane
Kingston ON Canada
> -Original Message-
> From: upananda.p...@gmail.com
> Sent: Fri, 31 May 2013 18:11:28 +0530
> To: r-hel
Hi John,
I am using Microsoft Window Vista Service Pack 2.
Regards,
Upananda
On Fri, May 31, 2013 at 6:47 PM, John Kane wrote:
> http://www.r-project.org/ and go from there I imagine.
>
> You did not supply any information about your operating system so it is
> difficult to give more detailed
I'm not sure I understand. If you fit an ANCOVA using the lm() function,
like this,
fit <- lm(Y ~ X*as.factor(batch))
summary(aov(fit))
and the hypothesis for equality of slopes is rejected, i.e., the
X:as.factor(batch)) term is significant, then this same model already has
batch-specific
http://www.r-project.org/ and go from there I imagine.
You did not supply any information about your operating system so it is
difficult to give more detailed advice.
John Kane
Kingston ON Canada
> -Original Message-
> From: upananda.p...@gmail.com
> Sent: Fri, 31 May 2013 18:11:28 +05
Hi All,
I want to switch over from 2.13.1 to 3.0.1. Is it advisable to switch over.
I am using Windows Vista.
Please suggest me installation procedure as i am not very comfortable in
Installing R and If any good documentations can be found, Please send me
the link.
Thanks and Regards,
Upananda
library(plyr)
colnames(Y)[2]<- colnames(X)
join(X,Y,type="left",by="k1")
# k1 k2
#1 A 1
#2 NA
#3 C 3
#4 B 2
A.K.
- Original Message -
From: nevil amos
To: r-help
Cc:
Sent: Friday, May 31, 2013 4:07 AM
Subject: [R] merge without NA last
I am trying to create a merge
It is hard to know exactly what you mean with such a generic question.
If you mean "treat survival as a counting process", then the answer is yes. The survival
package in S (which is the direct ancestor of the Splus package, which is the direct
ancestor of the R package) was the very first to d
Hallo.
Many thanks for your answer. Let me check please that I do understand
it correctly. Does it mean that the estimated log-likelyhood function
is (in the Gaussian case)
sum y * log F(x'b / exp(z'g)) + sum (1 - y) * log(1 - F(x'b / exp(z'g))
where F is standard normal CDF, and the rest is a
Hi,
I would like to compare two batches of a product over time to see if they
behave similarly, i.e same slope and intercept. This is a stability study. I
will be performing ANCOVA analysis for this. According to ICH and FDA
guidelines, if the test rejects the hypothesis of equality of slopes,
On Fri, 31 May 2013, Michal Kvasni?ka wrote:
Hallo.
First many thanks to its authors for glmx package and hetglm()
function especially. It is absolutely great.
Glad it is useful for you!
Now, let me ask my question: what model of heteroskedasticity hetglm()
uses? Is the random part of the G
On Thu, 30 May 2013, Jim Silverton wrote:
Hi,
I am looking for an R package that can handle a mixture of two beta
continuous distributions or a mixture of two beta discrete discrete
distributions.
The "betareg" package provides a function betamix() for finite mixture
models of beta regress
Hallo.
First many thanks to its authors for glmx package and hetglm()
function especially. It is absolutely great.
Now, let me ask my question: what model of heteroskedasticity hetglm()
uses? Is the random part of the Gaussian probit model
norm(0, sd = exp(X2*beta2))
where norm is the Gau
Dear Mr. Nello,
Thank you very much for your prompt reply and solution to my question. I have
tried the three options. Need to spend more to understand do.cal function.
With best regards,
Abd Rahman
From: Blaser Nello [nbla...@ispm.unibe.ch]
Sent: Frid
Le vendredi 31 mai 2013 à 18:07 +1000, nevil amos a écrit :
> I am trying to create a merge where the first value contains NA values. I
> wish to retain these in order. however when I use all.x=T and sort=F they
> are retained but na values are placed last:
>
> > X<-data.frame(k1=c("A",NA,"C","B
In line with what you are doing now, but saving the intermediate results
you could use something like this.
a3 <- a0
for( i in 1:3)
{
a1 <- a0$initial_size+a0$grow
a2<- cbind(sp=a0$sp,initial_size=a1+i,yr=i)
a3 <- cbind(a3, a2)
}
a3
However, I would suggest one of the following solutions i
I am trying to create a merge where the first value contains NA values. I
wish to retain these in order. however when I use all.x=T and sort=F they
are retained but na values are placed last:
> X<-data.frame(k1=c("A",NA,"C","B"))
> print (X)
k1
1A
2
3C
4B
> Y<-data.frame(k2=c(1,
> John Fox
> on Thu, 30 May 2013 17:14:06 -0400 writes:
> Dear all,
> My thanks to everyone who addressed my question. I've
> incorporated Eik Vettorazzi's suggestion for improved
> conversion of hexadecimal RGB colours to decimal numbers,
> and Martin Maechler's
> John Fox
> on Thu, 30 May 2013 09:58:18 -0400 writes:
> Dear Martin,
>> -Original Message- From: Martin Maechler
>> [mailto:maech...@stat.math.ethz.ch] Sent: Thursday, May
>> 30, 2013 9:18 AM To: John Fox Cc: r-help@r-project.org
>> Subject: Re: [R] measu
79 matches
Mail list logo
