tapply is also very useful:
my.df<-data.frame(x=rnorm(20, 50, 10),group=factor(sort(rep(c("A", "B"), 10
tapply(my.df$x,my.df$group,function(x){(x-mean(x))/sd(x)})
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Behalf Of Matthew Dubins
Sent: 26 September 2007
> The idea is that you're modeling an irregular shaped object, a body of
> water, a river or estuary, say. It's fairly common practice to use a
> grid squished and rotated so that the main flow is along one axis, and
> the other axis spans the flow in most spots. So there is a single
> trans
I try to reproduce the SAS proc reg stepwise model selection procedure in R,
but the only function I found was "step" which select new variables based on
AIC. The SAS procedure I use add a new variable to the model based on F
statistics and a pre defined significant level. Then before any new va
Hi
[EMAIL PROTECTED] wrote:
>
>
>> So I applied my corrected margins to Tim's Cairo trick and voila:
>> http://www.broad.mit.edu/~finnyk/Rlogo_swiss.png
>> This is hands-down the best version, in my opinion!
>
> Yes, it is definitely much nicer than the version on www.r-project.org
> now. :-
On Wed, 26 Sep 2007, mfrumin wrote:
>
> hey all,
>
> I feel like I must be missing something rather plain, but I don't get it.
> how is one supposed to use R as a PgSQL client on Windows? Assume my
> windows desktop is on the same network as a PgSQL server, and I just need to
> use R to connect a
hadley wickham <[EMAIL PROTECTED]> wrote:
> You might be able to do this with the ggplot2 package - see for
> example http://had.co.nz/ggplot2/coord_map.html, which shows plots on
> map coordinate systems. Because the design of ggplot2 means the
> coordinate system and geom (eg. points vs tiles)
You might be able to do this with the ggplot2 package - see for
example http://had.co.nz/ggplot2/coord_map.html, which shows plots on
map coordinate systems. Because the design of ggplot2 means the
coordinate system and geom (eg. points vs tiles) operate
independently, you can draw image plots
(ht
Hello all:
A question from a new user. I have data on a geo-referenced curvilinear
grid. This is a grid with 75 rows and 51 columns, is not aligned
north-south, and the rows and columns are not straight. (And the
coordinates are in meters.) I want to make image plots of this data,
but where th
Hello,
One possibility which gives an exact result and has
the complexity of O(n*log(n)) where n is the number of
vertices (edges) in the polygon would be to use
Green's theorem. One consequence of it is that id D is
a 2 dimensional region which boundary is a simple (and
piecewise continuously dif
> I feel like I must be missing something rather plain, but I don't get
> it. how is one supposed to use R as a PgSQL client on Windows? Assume
> my windows desktop is on the same network as a PgSQL server, and I just
> need to use R to connect and pull down some data.
>
> The thing that is co
hey all,
I feel like I must be missing something rather plain, but I don't get it.
how is one supposed to use R as a PgSQL client on Windows? Assume my
windows desktop is on the same network as a PgSQL server, and I just need to
use R to connect and pull down some data.
The thing that is conf
On 27/09/2007, at 12:27 PM, [EMAIL PROTECTED] wrote:
> Hello, Listers
>
> I'm trying to run blloean logit model with R.
>
> My code is:
>
>> library(boolean)
>> library(foreign)
>> pr <- read.dta ("prcore1.dta")
>> bp <- boolprep ("(a&b)|c", "cwt", a="O1", b="t", c="DM2
>> + ah + md + con + n3 +
Hello,
I got error message when applying the plot function to the cox.zph
object to create the Schoenfeld residual plots.
> plot(zph.revasFit[1])
Error in plot.window(xlim, ylim, log, asp, ...) :
need finite 'ylim' values
In addition: Warning messages:
1: NaNs produced in: sqrt(x$var
Dear All:
I tried to replicate a case study described by Prof. Harrell in Chapter 7 of
his Regression Modeling Strategies book, but failed on using anova.Design to
reproduce his table 7.1, Following is the code:
rm(list=ls())
library(Hmisc)
library(Design)
getHdata(counties)
counties$older <- c
Hello, Listers
I'm trying to run blloean logit model with R.
My code is:
> library(boolean)
> library(foreign)
> pr <- read.dta ("prcore1.dta")
> bp <- boolprep ("(a&b)|c", "cwt", a="O1", b="t", c="DM2
> + ah + md + con + n3 + rel + slo + pyrs
> + sp1 + sp2 + spl3")
> answer <- boolean (bp, link
[1][logo.gif]
Destination vacances
[2]Merveilles de l'Egypte
[rect-jaune.gif] [3]La Sicile mystérieuse
[rect-jaune.gif] [4]Athènes et ses joyaux
[rect-jaune.gif] [5]Les Cyclades en Grèce
[rect-jaune.gif] [6]Mykonos la magn
On Wednesday 26 September 2007, Lorenzo Isella wrote:
> Dear All,
> I hope this is not a FAQ, but my online research was not fruitful.
> Consider a standard 2D plot generated with the "plot" command.
> I would like to introduce inside the graph some text with an arrow
> pointing to a specific posit
Dear All,
I hope this is not a FAQ, but my online research was not fruitful.
Consider a standard 2D plot generated with the "plot" command.
I would like to introduce inside the graph some text with an arrow
pointing to a specific position of the plotted function.
Is this doable in R? Can anyone pr
Thank you Greg - I will read these carefully. Lancet should carry great weight
with the clinical audience.
Do you know of any references that address the fact that the paired differences
at 30 days, 60 days, etc. are typically correlated?
Regards,
-Cody
-Original Message-
From: Gre
Here are a couple to look at, they may be helpful and the references in
them may give you a specific example that you can use (read them through
yourself, then decide if you want your docs to read them).
Kenneth F Schulz and David A Grimes (2005), "Multiplicity in randomised
trials I: endpoints an
Hi,
Thanks so much! I got what I needed: z scores, according to group
membership, in one vector.
Matthew Dubins
Erik Iverson wrote:
> Hello -
>
> First, I doubt you really want to cbind() those two vectors within the
> data.frame() function call.
>
> test.data <- data.frame(x, group) is pro
Hello -
First, I doubt you really want to cbind() those two vectors within the
data.frame() function call.
test.data <- data.frame(x, group) is probably what you want. That may
be the source of your trouble.
If you really want a vector returned, the following should work given
your test.dat
I came across a post by Karl Knoblick regarding the modeling of longitudinal
data (see https://stat.ethz.ch/pipermail/r-help/2007-May/132137.html). I am
often asked by physicians to perform what Karl refers to in his post as option
1: to perform paired t-tests against baseline at each follow up
Here is one approach (someone with better linear algebra skills may be
able to shorten this, some steps could be combined, but I wanted to show
each step):
# create x1-x3
x1 <- rnorm(100, 50, 3)
x2 <- rnorm(100) + x1/5
x3 <- rnorm(100) + x2/5
# find current correlations
cor1 <- cor( cbind(x1,x
On Wed, 2007-09-26 at 15:18 -0500, Jacques Wagnor wrote:
> Dear List,
>
> Is there any way to password-protect script files (either within R or
> otherwise)?
You might want to review this thread:
http://thread.gmane.org/gmane.comp.lang.r.general/94290/
which covers perhaps a similar concern.
Duncan Temple Lang wrote:
>
>> ?wordReport gives a lot of information, but I think it makes
>> us wish for more :-)
>>
>> Where can I find all the ways to write Word documents using R?
>
> (... alternative methods deleted ...)
>
> One could also create the document in XML, either directly to
> W
Hi,
I want to be able to create a vector of z-scores from a vector of
continuous data, conditional on a group membership vector.
Say you have 20 numbers distributed normally with a mean of 50 and an sd
of 10:
x <- rnorm(20, 50, 10)
Then you have a vector that delineates 2 groups within x:
g
I am trying to generate a fourth vector,z, given three known and fixed
vectors, x1,x2,x3 with corresponding known and fixed correlations with
themeselves and with z. That is, all correlations are known and
prespecified. How can I do this?
Thank you,
ben
___
Dear List,
Is there any way to password-protect script files (either within R or
otherwise)?
platform i386-pc-mingw32
arch i386
os mingw32
system i386, mingw32
status
major 2
minor 5.1
year 2007
month 06
day27
s
On Wed, 26 Sep 2007, Francisco J. Zagmutt wrote:
> I believe the argument to format is "scientific" i.e.
> axis(2, at=at, labels=format(at, scientific=FALSE))
Yes, but abbreviations of argument names are allowed.
Here setting a small positive value of options(scipen) (e.g. 2) gives
floating-poi
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Alberto Monteiro wrote:
> ?wordReport gives a lot of information, but I think it makes us wish for
> more :-)
>
> Where can I find all the ways to write Word documents using R?
>
Using either of the R/DCOM client packages (rcom and RDCOMClient)
At 7:25 AM -0700 9/26/07, Samuel Okoye wrote:
>Hello,
>
> I have got the following problem:
>
> > setwd("C:/temp")
>> library(xlsReadWrite)
>> MyData <- read.xls(file="Mappe1.xls", colNames = TRUE,dateTimeAs
>>= "isodatetime")
>> attach(MyData)
>> MyData
> name value time
What is the error message? What does 'str(MyData)' show? I read your
data in and it worked fine.
> x <- read.table(textConnection(" name value times
+ 1 A1 2 2006-05-12
+ 2 A2 3 2006-05-16
+ 3 A3 1 2006-05-12
+ 4 A4 4 2006-05-12
+ 5 A5 2 2006-05-16
+ 6 A6
Prof Ripley,
Thank you for your post. Below is the output of traceback(). I'm still not
sure what the problem is. Thank you.
4: as.matrix.data.frame(frame)
3: as.matrix(frame)
2: rpart.matrix(m)
1: rpart(lowergi ~ ., data=dset, method="class")
On 9/26/07, Prof Brian Ripley <[EMAIL PROTECTED]>
I would appreciate confirmation that the function vcov(model.nlme)
gives the var-cov matrix of the fixed effects in an nlme model.
Presumably the random-effects var-cov matrix is given by cov(ranef
(model.nlme)?
Rob Forsyth
__
R-help@r-project.org
R-listers,
Given a polygon and a circle defined by its center coordinates and a
radius, I would like to calculate the area of overlap. I know that I
can create a polygon from the circle and then use available packages to
get the area of the intersection. However, because the polygon is of a
Thank you Wensui and Professor Ripley for your responses.
Prof. Ripley, your assumptions regarding the context in which I'm using 'WLS'
and 'regression' are correct. The function solve.QP in the quadprog package
sounds like a great way to go. Thank you, and I will try this method.
Westley A.
On 26.09.2007, at 13:46, Olena Morozova wrote:
> I am very new to R and statistical analysis in general. I am trying
> to plot
> a matrix of several hundred rows against a vector of 4 values. This
> all has
> to be on the same graph with different rows represented by
> different color.
> Thi
I am very new to R and statistical analysis in general. I am trying to plot
a matrix of several hundred rows against a vector of 4 values. This all has
to be on the same graph with different rows represented by different color.
This sounds like it should not be hard to do, but I am having problems
I believe the argument to format is "scientific" i.e.
axis(2, at=at, labels=format(at, scientific=FALSE))
Best regards,
Francisco
Duncan Murdoch wrote:
> On 9/26/2007 11:24 AM, Jacques Wagnor wrote:
>> Dear List:
>>
>> Below is how I specify an axis:
>>
>> axis(2, at=c(0.5, 0.0005))
>>
>> R
On Wed, 26 Sep 2007, Juned Siddique wrote:
> I'm using rpart to fit a tree using a large dataset: 7000 observations, 4651
> variables. All but one of the variables (age) are binary. When I run the
> code:
>
> fit1 <- rpart(lowergi ~ ., data=dset,method="class")
>
> I get the error:
>
>
> Error in
You seem to be assuming that 'regression' has to do with 'gaussian
assumption'. However, I presume WLS stands for 'weighted least squares',
and 'regression' is historically associated with fitting linear models by
least squares.
I don't see why even in the model-based framework you assert that
Cary Dehing-Oberije wrote:
> Dear all,
>
> I am using transcan to impute missing values (single imputation). I have
> several dichotomous variables in my dataset, but when I try to impute
> the missings sometimes values are imputed that were originally not in
> the dataset. So, a variable with 2 v
if your regression under gaussian assumption, then you can't
constraint your predicted to be positive.
I don't know much about your dep in the model. but given more
appropriate distribution assumption, the constraint is doable. One
possibility that I can think of is poisson.
On 9/25/07, Westley Ri
marcg wrote:
>
> Hello
>
> with follwing code I want to produce the wireframe and add some points on
> it:
>
> wireframe(z ~ x * y, data=dem, aspect = c(1, .5),
> scales = list(arrows = FALSE),
> panel.3d.wireframe = function(x, y, z,...) {
> panel.3dwire(x =
>Transition matrices are Markov transition matrices among different
> life stages of organisms -- in the simplest case (Leslie matrices,
Ben,
Thanks for your clear explanation and plot examples. I like the dotplots alot
and added a few modifications below. Since I often compare rows and col
> So I applied my corrected margins to Tim's Cairo trick and voila:
> http://www.broad.mit.edu/~finnyk/Rlogo_swiss.png
> This is hands-down the best version, in my opinion!
Yes, it is definitely much nicer than the version on www.r-project.org
now. :-)
--e
__
On 9/26/07, Wensui Liu <[EMAIL PROTECTED]> wrote:
> RDCOMClient and rcom are great. but I can't find much manual or
> tutorial about them.
They both have home pages that will lead you to whatever
information exists on them:
http://sunsite.univie.ac.at/rcom/
http://www.omegahat.org/RDCOMClient/
I have a WLS regression with 1 dependent variable and 3 independent variables.
I wish to constrain the predicted values (the fitted values) so that they are
greater than zero (i.e. they are positive). I do not know how to impose this
constraint in R. Please respond if you have any suggestions
Hello List,
I'm building a package for R, and I want to use the font family
'symbol', because it seems to be the most consistent of the four font
families that par guarantees. The problem is that when I tried to run
it on a different machine, I got an X11 error message saying that that
font famil
RDCOMClient and rcom are great. but I can't find much manual or
tutorial about them.
On 9/26/07, Gabor Grothendieck <[EMAIL PROTECTED]> wrote:
> >From R, you can write an XML or HTML document and read it right into Word
> in sufficiently new versions of Word. Go into Word and save a sample
> Word
I'm using rpart to fit a tree using a large dataset: 7000 observations, 4651
variables. All but one of the variables (age) are binary. When I run the
code:
fit1 <- rpart(lowergi ~ ., data=dset,method="class")
I get the error:
Error in dimnames(X) <-list(dn[1L]], unlist(collabs, use.names=FALSE)
>From R, you can write an XML or HTML document and read it right into Word
in sufficiently new versions of Word. Go into Word and save a sample
Word document in the format of your choice to see what it looks like.
Filtered HTML is particularly readable. Alternately, the R packages
RDCOMClient and
joe,
some procs in SAs calculates log likelihood differently than what it
is supposed to be. try using proc nlmixed and specifying the LL
explicitly.
in your case, I has stronger faith in R result instead of SAS result.
On 9/26/07, Joe Yarmus <[EMAIL PROTECTED]> wrote:
> In accordance with Venable
On 9/26/2007 11:24 AM, Jacques Wagnor wrote:
> Dear List:
>
> Below is how I specify an axis:
>
> axis(2, at=c(0.5, 0.0005))
>
> R displays the numbers in scientific notation. What
> argument/parameter should I use to tell R to display the numbers as
> specified rather than in scientific no
Hello,
I have got the following problem:
> setwd("C:/temp")
> library(xlsReadWrite)
> MyData <- read.xls(file="Mappe1.xls", colNames = TRUE,dateTimeAs =
> "isodatetime")
> attach(MyData)
> MyData
name value times
1 A1 2 2006-05-12
2 A2 3 2006-05-16
3 A3
Dear List:
Below is how I specify an axis:
axis(2, at=c(0.5, 0.0005))
R displays the numbers in scientific notation. What
argument/parameter should I use to tell R to display the numbers as
specified rather than in scientific notation?
> version
_
platform i386-pc-ming
In accordance with Venables and Ripley, SAS documentation and other
sources AIC with sigma^2 unknown is calculated as:
AIC = -2LL + 2* #parameters = n log(RSS/n) + 2p
For the fitness data:
(http://support.sas.com/ctx/samples/index.jsp?sid=927), SAS gets an AIC
of 64.534 with model oxygen = runt
We have been asked to write a paper on the snow package for
parallel computing in R for a parallel computing journal and
would like to include some references to examples of the use of
snow in practice beyond our own use. If you think you have a
good example we would like to hear from you. Please
On 26.09.2007, at 09:54, Prof Brian Ripley wrote:
> On Wed, 26 Sep 2007, Friedrich Leisch wrote:
>
>>> On Tue, 25 Sep 2007 20:16:05 -0400,
>>> Wiebke Timm (WT) wrote:
>>
>> > You might want to check if there is a neural gas algorithm in R.
>> > kmeans generally has a high variance since
Dear all,
I am using transcan to impute missing values (single imputation). I have
several dichotomous variables in my dataset, but when I try to impute
the missings sometimes values are imputed that were originally not in
the dataset. So, a variable with 2 values (severe weight loss or
no/limited
> Where can I find all the ways to write Word documents using R?
There aren't many. Look at
http://www.user2007.org/program/presentations/kuhn.pdf
to get Word documents via OpenOffice.
Max
__
R-help@r-project.org mailing list
https://stat.ethz.
?wordReport gives a lot of information, but I think it makes us wish for
more :-)
Where can I find all the ways to write Word documents using R?
Namely:
(1) is there any way to open a new document and save it automatically?
The sequence:
WordOpen("new_file.doc"); WordInsertText("R rulez!\n");
On Wed, 26 Sep 2007, Friedrich Leisch wrote:
>> On Tue, 25 Sep 2007 20:16:05 -0400,
>> Wiebke Timm (WT) wrote:
>
> > You might want to check if there is a neural gas algorithm in R.
> > kmeans generally has a high variance since it is very dependent on
> > the initialization. Neural gas
All great ideas. I tried strsplit first and it worked, but thanks everyone!
Best-
LB
On 9/25/07, Gabor Grothendieck <[EMAIL PROTECTED]> wrote:
> Perhaps you could clarify what the general rule is but assuming
> that what you want is any word after a colon it can be done with
> strapply in the gsu
Hi All R-user,
Anyone please let me know how to avoid printing index on the screen.
With regards,
_
100’s of Music vouchers to be won with MSN Music
__
R-help@r-project.org mailing list
h
> On Tue, 25 Sep 2007 20:16:05 -0400,
> Wiebke Timm (WT) wrote:
> You might want to check if there is a neural gas algorithm in R.
> kmeans generally has a high variance since it is very dependent on
> the initialization. Neural gas overcomes this problem by using a
> ranked li
Hello
R-classicist won't like the following question due to there's no minimal
reproducible example and the question was posted already.
Anyway I'm not able understand this rather complicated version of "add points
to wireframe".
what I have is matrix 3x2000 with a dem<-(x,y,z, coordinates) (n
So I applied my corrected margins to Tim's Cairo trick and voila:
http://www.broad.mit.edu/~finnyk/Rlogo_swiss.png
This is hands-down the best version, in my opinion!
Best,
Finny
On Wed, Sep 26, 2007 at 06:35:40AM -0500, [EMAIL PROTECTED] wrote:
>
>
> >>http://www.broad.mit.edu/~finnyk/Rhome
hi everyone,
i know r since last summer and i love it. i'm studying economics and
use it for econometrical tasks at university. besides that in a
private project a buddy of mine and me do some economic evaluation
with data stored in a MYSQL-database. we export the values from our
online MYSQL data
FYI, Peter Dalgaard's original posting from 2004 that I used is here:
http://tolstoy.newcastle.edu.au/R/help/04/06/1094.html
Per his suggestion, I changed the smoothing parameter to be:
"pnmsmooth -size 1 1" instead of "pnmsmooth -size 5 5" which he
originally described. The new graphic is here:
>> http://www.broad.mit.edu/~finnyk/Rhome.jpg
> If you run Eric Lecoutre's code to produce the graphic, available at
> http://www.r-project.org/misc/acpclust.R, unchanged except for the
> addition of these lines:
>
> library(Cairo)
> Cairo(600,400,file="Rlogo_swiss.png",type="png",bg="white")
You can trace this function:
install.packages("debug")
library(debug)
mtrace(sqlFetch)
sqlFetch(channel,"t_studie")
Then you'll have the new window showing function code and allowing you to
execute it step by step, view intermediate results, variables, etc.
To switch off tracing, use
mtrace(sql
Hi,
I have some "simple" questions and annotations about neural networks:
1) Which R-package (or which software) would you use to train and validate a
multilayer (2 hidden layers) feed forward neural network. I think "AMORE" is
the only one that can do this task in R.
2) When using neur
Not sure which of the questions yo want answered in your email.
However, if its the one regarding the boxplot try:
dd <- read.table("test.txt",header=T)
attach(dd)
boxplot(x)
outlier <- function(y){
out <- boxplot(y, range = 1)$out
outliers <- which(y %in% out)
return(list(out=out,outliers=
Hi.
It looks like the letter 'e' at the end of the table name is not latinic
'e'.
sqlFetch constructs the SQL query internally from the supplied table name:
ans <- sqlQuery(channel, paste("SELECT * FROM", dbname),
...)
What will be the answer for
sqlQuery(channel, paste("SELECT * FROM
Hello,
I wrote
> setwd("D:/")
> dd <- read.table(file="test.txt",header=TRUE)
> attach(dd)
> boxplot(x)
> outlier <- function(y){
+ out <- boxplot(y, range = 1)$out
+ outliers <- which(y == out)
+ dev.off()
+ return(out,outliers)
+ }
> outlier(x)
$out
[1] 1.950208 2.082025 4.7
Hello,
I wrote
> setwd("D:/")
> dd <- read.table(file="test.txt",header=TRUE)
> attach(dd)
> boxplot(x)
> outlier <- function(y){
+ out <- boxplot(y, range = 1)$out
+ outliers <- which(y == out)
+ dev.off()
+ return(out,outliers)
+ }
> outlier(x)
$out
[1] 1.950208 2.082025 4.7
How about
a <- .33
b <- .55
legend("bottom", fill=c("red","blue"),
legend=c(bquote(p == .(a)), bquote(p == .(b))), bty="n")
or look at ?substitute
- Peter Ehlers
stat stat wrote:
> I have following syntax for putting a legend :
>
> legend("bottom", fill=c("red","blue"), legend=expression(
You can use bquote (see ?bquote or the example in ?plotmath using bquote).
Here you go,
pvalue <- 0.3
legend("bottom", fill=c("red","blue"), legend=c(bquote(p==.(pvalue)),
expression(p==0.50)), bty="n")
Med venlig hilsen
Frede Aakmann Tøgersen
> -Oprindelig meddelelse-
> Fra: [E
Hello,
I've created an application (IDE for ecological modelling) on the basis of
Eclipse which uses Rserve
http://www.rforge.net/Rserve/ http://www.rforge.net/Rserve/
to archieve this.
I also implemented a small api to send or access data from or to R and Java.
The transfer is very fast. I'v
Dear R ussers,
I noticed a small problem when ussing for example the function "
plotMeamns "under Rcmdr.
In this case a graph will be ploted, giving the means on the Y-axis, by a
factor on the X-axis.
All is correct when doing this, ussing 'sd' for error bars.
The problem occures when ussing c
(Ted Harding) wrote:
> Pat Altham (now retired) developed extensive teaching (and
> other) materials in R at the Cambridge University Statistical
> Laboratory. From her personal web page:
>
> "Some of the computer languages I have had to try to
>learn since graduating in 1964: Cambridge auto
Oh yes.
I did searched for help, but Ijust didn't read carefully, I read
"MAAS", instead of MASS..
Carlos
On 9/25/07, Peter Dalgaard <[EMAIL PROTECTED]> wrote:
> Carlos "Guâno" Grohmann wrote:
> > Hello,
> > After a long time, I needed the truehist function, but my system
> > couldn't found it
I have following syntax for putting a legend :
legend("bottom", fill=c("red","blue"), legend=expression(p==0.30, p==0.50),
bty="n")
However what I want is that : the value "0.30" should be a value of a variable
instead of a constant, so that I can put the name of this variable and in
legend it
> On Tue, 25 Sep 2007 09:17:23 -0500,
> hadley wickham (hw) wrote:
>> > but I can understand your desire to do
>> > that. Perhaps just taking a static snapshot using something like
>> > wget, and hosting that on the R-project website would be a good
>> > compromise.
>>
>> Hmm
86 matches
Mail list logo
