Hi,
# Example of my problem of saving pdf file graphics in R-2.6.0
> x<-1:10;y<-1:10
> plot(x,y,type="b")
# attempting to save the plot as a *pdf file fails
# and the following error meassge is shown.
Error: Invalid font type
In addition: Warning messages:
1: font family not found in PostScri
No.
On Oct 16, 2007, at 11:32 PM, Moshe Olshansky wrote:
> Are your polygons convex?
>
> --- Haiyong Xu <[EMAIL PROTECTED]> wrote:
>
>> Hi there,
>> Is there any package which can calculate the
>> overlapping area of two
>> polygons or output the coordinates of the
>> overlapping of two polygons?
Are your polygons convex?
--- Haiyong Xu <[EMAIL PROTECTED]> wrote:
> Hi there,
> Is there any package which can calculate the
> overlapping area of two
> polygons or output the coordinates of the
> overlapping of two polygons?
>
> Thanks.
> Haiyong
>
> ___
Hi there,
Is there any package which can calculate the overlapping area of two
polygons or output the coordinates of the overlapping of two polygons?
Thanks.
Haiyong
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLE
Lately I'm getting this error quite a bit:
Error in La.svd(x, nu, nv) : error code 1 from Lapack routine 'dgesdd'
I'm running R 2.5.0 on a 64 bit Intel machine running Fedora (8 I think).
Maybe the 64 bit platform is more fragile about declaring convergence.
I'm seeing way more of these errors t
Thomas Lumley wrote:
> On Tue, 16 Oct 2007, Gad Abraham wrote:
>
>> Gad Abraham wrote:
>>> Hi,
>>>
>>> I'm using survreg() from the survival package for parametric survival
>>> regression (modelling inter-arrival times of patients to a waiting list
>>> as exponentially distributed, with various re
Terry Therneau wrote:
> Gad Abraham wrote:
>> Hi,
>>
>> I'm using survreg() from the survival package for parametric survival
>> regression (modelling inter-arrival times of patients to a waiting list
>> as exponentially distributed, with various regressors such as queue size
>> and season).
>>
I guess that is not available, but you can fit MA(1)+GARCH(1,1) to the first
difference of the series using garchFit available in the (Rmetrics) fGarch
package.
-Hannu
On 10/17/07, jStat <[EMAIL PROTECTED]> wrote:
>
>
> I'm searching for a function to fit a conditional mean structure (ARIMA)
> an
I'm searching for a function to fit a conditional mean structure (ARIMA) and
a conditional variance structure (GARCH) to a data set for one model.
Particularly, I'm trying to fit an IMA(1,1)+GARCH(1,1) model to a data set.
However, I can't seem to find a function that will let me specify both the
Excel 2007 xlsx files are zip files that contain XML files which
define the spreadsheet -- its all readable text. Create an
Excel 2007 xlsx file, rename its extension to .zip, unzip it
and you can look at all the constituent files using any text
editor or your browser.
On 10/16/07, Marc Schwartz
I think its your parameterization that is problematic.
ED50^hill is tough for it to work with since both are varying.
Try reparameterizing using ED50hill = ED50^hill as a parameter
so that the parameters become Emax, ED50hill and hill. You
can back transform afterwards.
On 10/16/07, Lanre Oku
On 17/10/2007, at 2:52 PM, Duncan Murdoch wrote:
> Okay, I see it now. The bug shows up when the \itemize command
> is not at the start of a line; you can avoid it by inserting a line
> feed there. The cause is apparently that the translator from .Rd
> format to troff (or whatever that is)
On 16/10/2007 8:18 PM, Rolf Turner wrote:
> On 17/10/2007, at 1:00 PM, Duncan Murdoch wrote:
>
>> On 16/10/2007 7:46 PM, Rolf Turner wrote:
>>> I'm getting an anomalous result from using the itemize command in
>>> a documentation
>>> file. My usage is something like
>>> \itemize{
>>> \item Mel
If your vector is x then
which(is.na(x))
produces that inecies.
--- Megh Dal <[EMAIL PROTECTED]> wrote:
> I have a vector with some of it's elements are NA. I
> am looking for a function to detect what are the
> corresponding index number of NA values. Anyone can
> help me on this regard?
>
>
I have a vector with some of it's elements are NA. I am looking for a function
to detect what are the corresponding index number of NA values. Anyone can help
me on this regard?
-
Building a website is a piece of cake.
[[alternative HTML version
On 17/10/2007, at 1:00 PM, Duncan Murdoch wrote:
> On 16/10/2007 7:46 PM, Rolf Turner wrote:
>> I'm getting an anomalous result from using the itemize command in
>> a documentation
>> file. My usage is something like
>> \itemize{
>> \item Melvin
>> \item Irving
>> \item Clyde
>> \item Fred
>>
On 16/10/2007 7:46 PM, Rolf Turner wrote:
> I'm getting an anomalous result from using the itemize command in a
> documentation
> file. My usage is something like
>
> \itemize{
> \item Melvin
> \item Irving
> \item Clyde
> \item Fred
> }
>
> (This was place inside ``\details{ }''.)
I just p
I'm getting an anomalous result from using the itemize command in a
documentation
file. My usage is something like
\itemize{
\item Melvin
\item Irving
\item Clyde
\item Fred
}
(This was place inside ``\details{ }''.)
(Previously I had enclosed the text following each item in braces but
t
Sorry for the long message. I'm doing my best to try to explain myself.
I have fitted a spline to my data, I have fitted a spline, filled in
the missing data by replicating the spline coefficients associated to
the last node. I obtained a number of dendograms by different
combination of distance a
Azza,
By "sign changes" are you looking at how long runs of similar results are
before switching, e.g. HHTHTTTH sees four changes, while sees just
one?
JD
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PL
If you follow the posting and provide a reproduciable example, it
would be easier to suggest a solution. One thing you need to so is an
'str(disperser.mx)' and I will bet it shows it as a dataframe and not
a matrix. Here is a sample of code that shows if it is a matrix it
works, otherwise it give
I am trying to get a random matrix based on an original matrix called
disperser.mx, with dimensions 30x73
When I write the following code:
>scramble = sample (disperser.mx)
>newmat = matrix(scramble, nrow=30)
I get the following warning message and a very weird matrix with 30 rows but
only 3 co
On Tue, 16 Oct 2007, azzza wrote:
>
> Thats what is frustrating meI've done a lot of reading, but there doesnt
> seem to be much info on sign changes..I dont udnerstand why the
> poportion of sign changes is much less than 50%, despite the proportion of
> heads being equal to that
On Tue, Oct 16, 2007 at 04:44:54PM -0400, Zembower, Kevin wrote:
> Daniel, thanks for your suggestion. So, it's just done like this:
> > pnorm(21, mean=20, sd=10/4) - pnorm(19, mean=20, sd=10/4)
> [1] 0.3108435
> > # OR
> > pnorm(21, mean=20, sd=10/sqrt(16)) - pnorm(19, mean=20,
> sd=10/sqrt(16))
>
Jim,
Thanks. Actually I just got it working a few minutes ago with:
tryCatch({download.file(url, destfile = file, quiet = FALSE, mode =
"wb")}, silent = FALSE, condition = function(err) { } )
but I like your suggestion better. I'll attempt to log the list of
url's downloaded ok and those which e
I think this is closer to what you want. You can determine what you
want to do; this one just goes to the next iteration:
date <- as.POSIXlt(as.Date("2007-10-15", "%Y-%m-%d"))
for (i in 1:difftime(as.POSIXlt(as.Date("2007-10-15",
"%Y-%m-%d")),"2007-10-01"))
{
if (date$wday != 0 & da
Dear all,
Just a quick one, hopefully. I have a histogram made from the method
'hist()'. How do I get labels on the bars? Such that the bars will have
the x axis on the bar, not the frequency of the point but the number of
the point itself. To make a quick summary, I want the the numbers from
Hi.
I'm sorry to revisit a problem that's been much discussed, but I haven't yet
been able to overcome it.
I am running R 2.5.1 on Windows XP Professional 5.1 (Service Pack 2), and I
believe I have MySQL 5.0.45 installed (I downloaded and installed
mysql-essential-5.0.45-win32.msi from
http:/
I am trying to download a bunch of files from a server, for which I am
using download.file( ) within a for loop. The script is working fine
except until download.file hits a URL which has no file, at which
point it exits. I want to change this behavior to simple log the
failure and maintain state w
Daniel, thanks for your suggestion. So, it's just done like this:
> pnorm(21, mean=20, sd=10/4) - pnorm(19, mean=20, sd=10/4)
[1] 0.3108435
> # OR
> pnorm(21, mean=20, sd=10/sqrt(16)) - pnorm(19, mean=20,
sd=10/sqrt(16))
[1] 0.3108435
>
Thanks, again.
-Kevin
-Original Message-
From: [EMA
On 10/16/07, Dirk Eddelbuettel <[EMAIL PROTECTED]> wrote:
> options(download.file.method="wget")
>
> in your Rprofile and you should be fine for all subsequent file operations.
I added
# # Set download options
options(download.file.method="wget")
to /usr/lib/R/etc/Rprofile.site.
It does n
On Tue, Oct 16, 2007 at 04:30:48PM -0400, Zembower, Kevin wrote:
> Now I'd like to know how to use R to solve this type of problem. In all
> my other problems using normal curves, I used dnorm or pnorm, but
> neither of these includes anything regarding the number of trials.
pnorm can be used lik
-- Forwarded message --
From: John C Frain <[EMAIL PROTECTED]>
Date: 16 Oct 2007 21:28
Subject: Re: [R] Updating R-Software without complete new installation
To: Vladimir Eremeev <[EMAIL PROTECTED]>
A word of warning. There is a danger that some package that you
depend on may not
[Yes, this is related to a homework problem, but is not the problems
itself.]
In my mathematical statistics class, we've just learned about properties
of estimators, and I can now solve manually problems like this:
A sample of size n = 16 is drawn from a normal distribution where sigma
= 10 but m
On 10/16/07, Marc Schwartz <[EMAIL PROTECTED]> wrote:
> On Tue, 2007-10-16 at 14:38 +0100, Arnold Akem wrote:
> > Hey Seniors,
> >
> > Really new to R, please has anyone imported a dataset from MS office
> > excel 2007 into R yet? It seem to be giving me hard times which I did
> > not expect as i
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of azzza
> Sent: Tuesday, October 16, 2007 12:49 PM
> To: r-help@r-project.org
> Subject: Re: [R] Need some help
>
>
>
> THANKYOU guyz! yes, Jim's code was right (it was similar to someone
> elses)I
Here is a more general R function to solve "any" linear system (under/over
determined):
ls.min <- function(x, y) {
# solves: x %*% b = y
d <- svd(x)
# min-norm solution
b.min <- d$v %*% diag(1/d$d, length(d$d)) %*% t(d$u) %*% y
return(b.min)
}
> # underdetermined case
> x <- matrix(c(2, -1, 4,
sum(toss == 1) /length(toss) # assuming heads == 1
On 10/16/07, azzza <[EMAIL PROTECTED]> wrote:
>
>
> THANKYOU guyz! yes, Jim's code was right (it was similar to someone
> elses)I somehow missed his reply!
> Yes, that was exactly what i was looking for. lastly, how do i find the
> frequency o
Dear R users,
I need to calculate the univariate impulse response function for a series of
data. Unfortunately the vars package does not support univariate analysis. If I
try to evaluate a single series like this:
VAR(y=xres,p=1,type="none",ic="AIC")
the result is
Error in VAR(y = xres, p = 1,
THANKYOU guyz! yes, Jim's code was right (it was similar to someone
elses)I somehow missed his reply!
Yes, that was exactly what i was looking for. lastly, how do i find the
frequency of heads perhaps?
Marc Schwartz wrote:
>
> On Tue, 2007-10-16 at 11:53 -0700, azzza wrote:
>>
>>
>> ok
On 17/10/2007, at 7:52 AM, Alberto Monteiro wrote:
> Scionforbai wrote:
>>
>> I just wonder: why should R and its community try to support
>> such an awful program, with its protected formats and unmantained
>> features/bugs?
>>
> By such logic, why should R be ported to Windows? :-)
>
> Short an
Thank you guyz. your codes gave me the results I was looking for. And thanks
for the reference suggestion. Lastly, how do I code the frequency of heads?
Daniel Lakeland wrote:
>
> On Tue, Oct 16, 2007 at 02:06:47PM -0400, jim holtman wrote:
>> If what you are asking for is to see how many ti
I am looking for a function for MI (mutual information) for
continuous variables X, Y.
I prefer not to discretize X,Y as it leaves the problems of optimal
bin number etc.
Can any one give a pointer to calculate mutual information using
Gausian kernel estimator for two continuous variables ?
wan
Here is a solution using SVD:
w <- matrix(c(1, 5), ncol=2)
sw <- 2
w.svd <- svd(w)
sw %*% w.svd$u %*% diag(1/w.svd$d, length(w.svd$d)) %*% t(w.svd$v)
> sw %*% w.svd$u %*% diag(1/w.svd$d, length(w.svd$d)) %*% t(w.svd$v)
[,1] [,2]
[1,] 0.07692308 0.3846154
>
This, of course, has a
On Tue, 2007-10-16 at 11:53 -0700, azzza wrote:
>
>
> ok, so suppose a coin is tossed 1000 times. Each time head occurs, we win a
> dollar, otherwise we lose a dollar. Let S(n) be our accumulated winnings
> after n tosses. For instance, if the sequence HHHTT occurs in the first five
> tosses, th
Ok, so n= the toss number, and s(n) is the accumulated winnings after n
tosses. Now, each time we have a heads, we win a dollar, and each time we
have a tails, we lose a dollar. So, s(n) is th sign changes in 1000 tosses.
In the beginning, S(0) must be 0, and S(-1) must be zero too. ok, so if on
On Tue, 16 Oct 2007, Ravi Varadhan wrote:
> QR is good for overdetermined LS problems, and I don't think that it can be
> used for "minimum norm" solution of underdetrmined LS problems. You need
> LAPACK's Fortran routine DGELS. I am not sure if this currently available
> in R.
It is in include
Dear Ralf,
Unfortunately, Anova.mlm(), and indeed Anova() more generally, won't
handle a model with only a constant. As you point out, this isn't
reasonable for repeated-measures ANOVA, where it should be possible to
have only within-subjects factors. When I have a chance, I'll see what
I can do t
Turns out someone asked this before ;)
http://tolstoy.newcastle.edu.au/R/e2/devel/07/04/2981.html
Ravi Varadhan wrote:
>
> QR is good for overdetermined LS problems, and I don't think that it can
> be
> used for "minimum norm" solution of underdetrmined LS problems. You need
> LAPACK's Fortra
On 10/16/07, Sarah Barry <[EMAIL PROTECTED]> wrote:
> Hi,
>
> I am trying to produce a 30x30 lattice grid. The 30 variables naturally
> fall into three groups of ten and I would like to add thicker axis lines
> around these to highlight this. However, I can only do this separately,
> so far, and
QR is good for overdetermined LS problems, and I don't think that it can be
used for "minimum norm" solution of underdetrmined LS problems. You need
LAPACK's Fortran routine DGELS. I am not sure if this currently available
in R.
Ravi.
ok, so suppose a coin is tossed 1000 times. Each time head occurs, we win a
dollar, otherwise we lose a dollar. Let S(n) be our accumulated winnings
after n tosses. For instance, if the sequence HHHTT occurs in the first five
tosses, then S(5) = $1.00 wheras if the sequence H occurs, S(5) =
Scionforbai wrote:
>
> I just wonder: why should R and its community try to support
> such an awful program, with its protected formats and unmantained
> features/bugs?
>
By such logic, why should R be ported to Windows? :-)
Short answer: because some of the data you want to use
is writen in Excel
R's developers have made the right decision. Like it or not, my company
colleagues and "customers" provide me most data in Excel. I want to use R
to analyze/plot/etc the data, and sometimes to provide them R applications
to do the analyses themselves instead of the current Excel analyses (sic)
th
Chris,
if you really want to use the stl() function, one possible solution
is to do
my.ts=ts(my.ts,start=1800,frequency=2).
Rogerio
--- Original Message ---
From: Christoph Scherber
Date: Wed, 10 Oct 2007 16:16:39 +0200
Dear R users,
I am trying to ´detect´ the trend in an artificial time
On Tue, Oct 16, 2007 at 02:06:47PM -0400, jim holtman wrote:
> If what you are asking for is to see how many times it crosses the
> axis when 'accumulating' the values of the top (+1, -1), then the
> following will do it - this is for 1000 and shows there are 32
> crossings of the axis.
I think wh
I just wonder: why should R and its community try to support such an
awful program, with its protected formats and unmantained
features/bugs?
I mean, from both philosophical and technical point of view: R is free
software and should rather try to be 'viral' than to compete. It
already has the stren
Jim,
I tried str(yarn). I received the following output:
'data.frame': 28 obs. of 3 variables:
$ NIR: num [1:28, 1:268] 3.07 3.07 3.08 3.08 3.10 ...
..- attr(*, "dimnames")=List of 2
.. ..$ : NULL
.. ..$ : NULL
$ density: num 100.0 80.2 79.5 60.8 60.0 ...
$ train : logi TR
You should be reading Feller v1 (p 86, 3rd ed) to see that the number of
zero crossings in this process is proportional to sqrt(n) not n.
url:www.econ.uiuc.edu/~rogerRoger Koenker
email[EMAIL PROTECTED]Department of Economics
vox: 217-333-4558Un
try:
str(yarn)
to see what the structure is.
On 10/16/07, Bricklemyer, Ross S <[EMAIL PROTECTED]> wrote:
> All,
>
> I am working with NIR spectral data and it was great to find that the example
> in ?plsr also used spectral data. Unfortunately, I am having difficulty
> figuring out how the "y
If what you are asking for is to see how many times it crosses the
axis when 'accumulating' the values of the top (+1, -1), then the
following will do it - this is for 1000 and shows there are 32
crossings of the axis.
> x <- sample(c(-1,1), 1000, TRUE)
> plot(cumsum(x), type='l')
> # now if you a
All,
I am working with NIR spectral data and it was great to find that the example
in ?plsr also used spectral data. Unfortunately, I am having difficulty
figuring out how the "yarn" dataset is structured to allow for the plsr model
to read:
library(pls)
data(yard)
yarn.oscorespls <- mvr(den
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of azzza
> Sent: Tuesday, October 16, 2007 9:06 AM
> To: r-help@r-project.org
> Subject: Re: [R] Need some help
>
>
>
> You are right, I was a bit too vague. I am trying to simulate
> 1000 coin
> Tosse
System:
Linux kernel 2.6.15 Ubuntu dapper
R version 2.5.1
ESS 5.2.11 on Emacs 21.4.1
-
Colleagues
I'm not sure if R-help or ESS is the right list for this query, so
please forgive me if you think this posting is to the wrong list. I'd
like to use Mark Bravington's package
On Tue, Oct 16, 2007 at 10:29:17AM -0400, Lanre Okusanya wrote:
> Thanks.
> I am just not used to having such a huge difference when changing the
> initial condition by 1 point. it usually tends to be an issue when you
> are way off (especially since the hill converged at 1.69). Does it
> have some
Hi Oarabile,
I'm not sure to full understand how you plan to use your function ... but it
seems that do.call("rbind", ...) should address your concern.
HTH,
Best regards
F
- Original Message -
From: "Oarabile Molaodi" <[EMAIL PROTECTED]>
To:
Sent: Tuesday, October 16, 2007 11:47 AM
Subje
Thats what is frustrating meI've done a lot of reading, but there doesnt
seem to be much info on sign changes..I dont udnerstand why the
poportion of sign changes is much less than 50%, despite the proportion of
heads being equal to that of tails.
Marc Schwartz wrote:
>
> You
On Tue, 2007-10-16 at 19:21 +0200, Scionforbai wrote:
> > Such workarounds should normally be avoided.
>
> You forgot to mention: Excel should normally be avoided.
>
> Risk of scrambling data while exporting to a simple ascii formatted text file?
> Is it a joke?
No. Excel is notorious for this.
> Such workarounds should normally be avoided.
You forgot to mention: Excel should normally be avoided.
Risk of scrambling data while exporting to a simple ascii formatted text file?
Is it a joke?
__
R-help@r-project.org mailing list
https://stat.ethz.
Hi,
I am trying to produce a 30x30 lattice grid. The 30 variables naturally
fall into three groups of ten and I would like to add thicker axis lines
around these to highlight this. However, I can only do this separately,
so far, and I don't know how to superimpose the grid with the thicker
l
The best way to read or write Excel files is with the RExcel package. The
development package available from
http://sunsite.univie.ac.at/rcom/download/devel/RExcel.installer_1.80-14.zip
reads both Excel 2003 and Excel 2007 files. In this development release,
the installer is structured as an ord
Hi,
I'm trying to construct what I think should be a fairly simple plot,
yet I'm having a tremendously difficult time. I'm trying to create a
very simple graph showing the effect of interest rates on option
prices. I have three sets of option prices that I've calculated
using rMetrics.
You might want to do some more research on "Bernoulli Trials" and "Fair
Coins", which would provide some enlightenment on why you would not
"expect" 500 sign changes in 1,000 tosses and why you should, if the
coin is "fair", expect to *approach* a 50/50 distribution of heads and
tails in a large nu
Several others wondered before and it has been fixed in R-patched.
Uwe Ligges
Filippo Piro wrote:
> I wonder why using the MS Windows GUI menu to save a graphic as PDF in
> R2.6.0 results in the following message:
>
> Error: invalid specification font
>
> furthermore: Warning messages:
> 1:
You are right, I was a bit too vague. I am trying to simulate 1000 coin
Tosses. Then to write a code for the number of heads/Tails.naturally, we
would expect the proportion of heads to be 50% so the number of heads would
be around 500. Secondly, I'm trying to look at the number of sign change
On Tue, 2007-10-16 at 14:38 +0100, Arnold Akem wrote:
> Hey Seniors,
>
> Really new to R, please has anyone imported a dataset from MS office
> excel 2007 into R yet? It seem to be giving me hard times which I did
> not expect as it use to go well with the previous versions.
>
> Thanks
On 16 October 2007 at 16:37, Rainer M Krug wrote:
| Liviu Andronic wrote:
| > On 10/16/07, Rainer M. Krug <[EMAIL PROTECTED]> wrote:
| >> I always change the variables in the terminal window before I start R, i.e.
| >>
| >> export http_proxy=SERVER:3128
| >> export ftp_proxy=SERVER:3128
| >>
| >>
Please read the Posting Guide and provide reproducible code. What do you
mean by "import"? -- via RODBC?... as a delimited text file? ... using
read.table(), scan(),... ???
Bert Gunter
Genentech Nonclinical Statistics
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Hi,
Henrique's solution is indeed very elegant. But after a while, I thought I
needed more control over individual lines. Therefore, I switched to the more
complex method you also suggest.
I want to thank the both of you for the help.
Regards,
Dieter
Jim Lemon wrote:
> Dieter Vanderelst wrot
I wonder why using the MS Windows GUI menu to save a graphic as PDF in R2.6.0
results in the following message:
Error: invalid specification font
furthermore: Warning messages:
1: font family not found in PostScript database
2: font family not found in PostScript database
Filippo Piro
Hey Seniors,
Really new to R, please has anyone imported a dataset from MS office excel
2007 into R yet? It seem to be giving me hard times which I did not expect as
it use to go well with the previous versions.
Thanks in advance.
arnoldo
-
On 10/16/07, Scionforbai <[EMAIL PROTECTED]> wrote:
> I would start R with the command:
>
> http_proxy="http://SERVER:3128"; R
>
> and then from R I would try:
>
> install.packages("Rcmdr", dep = TRUE, method = "wget")
> install.packages("Rcmdr", dep = TRUE, method = "wget")
--- Please select a CR
Dear Sirs
I can't try the package sets because I have a old mac system. Package
sets needs R = 2.6. I need to group some variables into a set of new
variables defined by a particular modality:
Example:
my.df = data.frame(var1=c(1,2,2,1,2,2,1,2), var2=c(2,2,1,1,2,2,1,1),
var3=c(1,2,2,1,1,1,1,
Hi, sorry, I'm an idiot.. and I know I'm missing something stupid..
I thought if we solve an underdetermine system with QR, my soln is:
min ||x|| (L2 sense) such that Ax = b
then say i have:
> w <- matrix(c(1, 5), ncol=2)
> sw = 2
> qrW = qr(t(w) %*% w)
> qr.coef(qrW, t(w) %*% sw)
[,1]
Hi,
sorry if this is explained somewhere but I didn't find anything.
How can I use "Anova" from the car package to test a modell without
between subject's factors? Suppose I have the following data
mat.1 mat.2 mat.3 di ex
1 858588 1 1
2 909293 1 1
3 9797
I would start R with the command:
http_proxy="http://SERVER:3128"; R
and then from R I would try:
install.packages("Rcmdr", dep = TRUE, method = "wget")
provided that you have wget installed on your system (which I think).
__
R-help@r-project.org mai
Another approach that usually works well is to use the option: algorithm =
"port". This uses the "nl2sol" routine.
foo.nls <- nls(var~Emax*(Dose^hill)/((EC50^hill)+(Dose^hill)),
start=list(Emax=-4,EC50=269,hill=1), algorithm="port", trace=T,data=foo)
This generally has more robust convergence
On Tue, 2007-10-16 at 07:49 -0700, Thomas Lumley wrote:
> On Mon, 15 Oct 2007, Gabor Grothendieck wrote:
>
> > Here is an alternative:
> >
> > sub(".*(..)$", "\\1", x)
> >
>
> For sufficiently small values of 3 ;)
> all.equal(2., 3)
[1] TRUE
;-)
Marc
__
Frédéric Chiroleu cirad.fr> writes:
>
> Hi,
>
> I misunderstand the definition of Canberra distance in R.
>
> On Internet and in function description pages of dist() from stats and
> Dist() from amap, Canberra distance between vectors x and y, d(x,y), is :
>
> d(x,y) = sum(abs(x-y)/(x+y))
>
On Tue, 16 Oct 2007, Gad Abraham wrote:
> Gad Abraham wrote:
>> Hi,
>>
>> I'm using survreg() from the survival package for parametric survival
>> regression (modelling inter-arrival times of patients to a waiting list
>> as exponentially distributed, with various regressors such as queue size
>>
Hi Christoph,
There's a couple of things you need to do. Firstly, you need to
reorder the factor according to how you want the data sorted
df$tld <- reorder_factor(df$tld, tapply(df$spam1, df$tld, mean))
is one way to do that.
The reason that position dodge isn't working for you is because it
On Mon, 15 Oct 2007, Gabor Grothendieck wrote:
> Here is an alternative:
>
> sub(".*(..)$", "\\1", x)
>
For sufficiently small values of 3 ;)
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
Hi Christian,
On 16 October 2007 at 15:39, Christian Kohler wrote:
| Dear R-Users,
|
| I am having some trouble getting an installation of RCurl 0.8-1 to work
| properly on a Debian (Etch) machine.
|
|
| The command 'R CMD INSTALL RCurl_0.8-1.tar.gz' yields the following error:
|
| Installin
Liviu Andronic wrote:
> On 10/16/07, Rainer M. Krug <[EMAIL PROTECTED]> wrote:
>> I always change the variables in the terminal window before I start R, i.e.
>>
>> export http_proxy=SERVER:3128
>> export ftp_proxy=SERVER:3128
>>
>> and then start R - I did it this morning, and it worked.
>
> I alw
Hi
"Klaus Friis Østergaard" <[EMAIL PROTECTED]> napsal dne 16.10.2007
10:34:15:
>
> 2007/10/15, Petr PIKAL <[EMAIL PROTECTED]>:
> Hi
>
>
> Well, let us put it another way. Do you want for each unique combination
> of Hole and Feature to subtract a value from one data frame, let us call
> it
On Mon, Oct 15, 2007 at 11:19:35PM -0500, Alex Baugh wrote:
> However, I don't know where to begin to write a program to do
> contrasts with a resampling technique.
select a random sample (with replacement) from the population with
factor level 1, and a random sample from the population with fact
On 10/16/07, Rainer M. Krug <[EMAIL PROTECTED]> wrote:
> I always change the variables in the terminal window before I start R, i.e.
>
> export http_proxy=SERVER:3128
> export ftp_proxy=SERVER:3128
>
> and then start R - I did it this morning, and it worked.
I always start up Gentoo with these var
Thanks.
I am just not used to having such a huge difference when changing the
initial condition by 1 point. it usually tends to be an issue when you
are way off (especially since the hill converged at 1.69). Does it
have something to do with the algorithm or is the hill just very
finicky?
Lanre
Dear r-help mailing list,
thanks for the advices on the last question,through them I've solved it.
But now, I would know, how is possible to compare two(or more) cluster
dendrograms, because for each cluster dendrogram coming from different data
frame the height is measured with different uni
Hi!
I would suggest trying out a few different starting values as a first
unsystematic approach.
For example changing hill=1 to hill=2 results in convergence:
foo.nls<-nls(var~Emax*(Dose^hill)/((EC50^hill)+(Dose^hill)),
start=list(Emax=-4,EC50=269,hill=2),trace=T,data=foo)
Christian
___
1 - 100 of 128 matches
Mail list logo
