Thanks to everyone who wrote in with suggestions. I will check out the
books mentioned.
The book I mentioned "Resampling: The New Statistics" is actually available
free online at:
http://www.resample.com/content/text/index.shtml
It seems pretty good as an introduction. But then again, I am new
The fact that I've been using R for quite a while now and did not know
about this document is supporting evidence of the need to get this sort
of information out there.
However that big list is going to daunt some people, it would have
daunted me at the beginning. At a time when you are digesting
On Wed, 17 Dec 2003, Savano S. Pereira wrote:
> UseRs,
>
> I used the optim function
>
> valor.optim <- optim(c(1,1,1),logexp1,method
> ="BFGS",control=list(fnscale=-1),hessian=T);
>
> and I want to calculate the derivates, [ ... snip ... ]
>
> but I found, [ ... snip ... ]
>
> The derivates are
The suggestions of Tom (posting guide) and Andy (Eric Raymond's "How To Ask
Questions The Smart Way") are both good. Perhaps a good place to put an
actual posting guide and a link to Raymond's page would be at the page
pointed to by the link at the bottom of every posting to R-help (ie
https:/
UseRs,
I used the optim function
valor.optim <- optim(c(1,1,1),logexp1,method
="BFGS",control=list(fnscale=-1),hessian=T);
and I want to calculate the derivates,
psi1<-valor.optim$par[1]
psi2<-valor.optim$par[2]
psi3<-valor.optim$par[3]
a0=exp(psi1);
a1=exp(psi2)/(20+ex
> From: Tom Mulholland
>
> I have empathy for lots of the points already made, more
> often on the life
> is not always easy and you have to work at it flavour because
> that's where
> you make the real gains.
>
> One particular message early in the piece cited an example of
> what a good
> re
I have empathy for lots of the points already made, more often on the life
is not always easy and you have to work at it flavour because that's where
you make the real gains.
One particular message early in the piece cited an example of what a good
request might look like. Other lists sometime sen
Niels Waller wrote:
>
> R users,
>
> I recently upgraded (?) to Windows XP from 2000. I am trying to build an R
> package. I have done this many times on my old system and I am not sure why
> it is not working in XP.
>
> To build the package I call a bat file that specifies all the necessary
Thanks. As a follow-up question, is it considered acceptable programming
practice for "<-" functions to modify their x argument?
-- Tony Plate
At Thursday 12:23 AM 12/18/2003 +0100, Peter Dalgaard wrote:
Tony Plate <[EMAIL PROTECTED]> writes:
> > xx <- rbind("colnames<-"(x[,c("rel1","age0","a
Tony Plate <[EMAIL PROTECTED]> writes:
> > xx <- rbind("colnames<-"(x[,c("rel1","age0","age1","sex0","sex1")], nn),
> + "colnames<-"(x[,c("rel2","age0","age2","sex0","sex2")], nn),
> + "colnames<-"(x[,c("rel3","age0","age3","sex0","sex3")], nn))
> PS. To advanced R users: Is the above usa
A two level solution might be possible as part of this too.
If you got ?whatever off your disk then it could contain a
link to the corresponding wiki page. If you didn't have
a connection you would still get what you get now but just
couldn't follow the link. Whenever a new version of R came
ou
Another way to approach this is to first massage the data into a more
regular format. This may or may not be simpler or faster than other
solutions suggested.
> x <- read.table("clipboard", header=T)
> x
rel1 rel2 rel3 age0 age1 age2 age3 sex0 sex1 sex2 sex3
113 NA 25 232
On 17 Dec 2003 at 12:51, Jonathan Baron wrote:
> On 12/17/03 12:19, Gabor Grothendieck wrote:
> >
> >
> >In rereading this one idea occurred to me. What if the entire R help
> >system were turned into a wiki? That is,
> >
> >?whatever
> >
> >would take you to the help page, but not on your comp
This is just a response to the part where you refer to an apply
loop really being a for loop. In a sense this true, but
it should nevertheless be recognized that the apply solution
has a number of advantages over for:
- it nicely separates the problem into a single line that is
independent of
[EMAIL PROTECTED] writes:
> Dear Splus and R users:
> I have a problem in fitting a NLME model, the error message is:
>
> "step halving factor reduced below minimum in PNLS step"
>
> What does it mean and how to fix the problem, could anyone help me
> about it?
>
> Any suggestion/help would be
> From: "Gabor Grothendieck" <[EMAIL PROTECTED]>
> Date: Wed, 17 Dec 2003 15:02:49 -0500 (EST)
>
> Define function f to take a vector as input representing
> a single input row. f should (1) transform this to a vector
> representing the required row of output or else (2) produce
> NULL if no r
Define function f to take a vector as input representing
a single input row. f should (1) transform this to a vector
representing the required row of output or else (2) produce
NULL if no row is to be output for that input row.
Then use this code where z is your input matrix:
t( matrix( un
Dear Splus and R users:
I have a problem in fitting a NLME model, the error message is:
"step halving factor reduced below minimum in PNLS step"
What does it mean and how to fix the problem, could anyone help me
about it?
Any suggestion/help would be greatly appreciated.
Mei
_
R users,
I recently upgraded (?) to Windows XP from 2000. I am trying to build an R
package. I have done this many times on my old system and I am not sure why
it is not working in XP.
To build the package I call a bat file that specifies all the necessary
paths -- but the "build" file (whi
>From the file defining GetColNames:
/* "GetRowNames" and "GetColNames" are utility routines which
* locate and return the row names and column names from the
* dimnames attribute of a matrix. They are useful because
You have not applied them to the dimnames attribute. Extracting
dimnames at
Hi all,
The last e-mails about beginners gave me the courage to post a question;
from a beginner's perspective, there are a lot of questions that I'm
tempted to ask. But I'm trying to find the answers either in the
documentation, either in the about 15 free books I have, either in the
help arch
>
> Dear useRs,
>
> I need of jacobian of a tranformation, R have this function?
If you use transform() on a response in my data structures (from my
rmutil library), the Jacobian is calculated automatically and stored
in the data structure. All my modelling functions then use it
automatically.
Can someone lend me a hand with extracting the dimnames from a SEXP? I've
looked through R-exts, but I couldn't find an example.
Here is the code I'm using to grab the jth column name and print it, but the
colnames I'm getting are garbage.
None of the following are working.
void printInfo(SEXP
Barry Rowlingson <[EMAIL PROTECTED]> writes:
>> But this is a lot of work to set up. I'd rather take small
>> steps. I do plan to look into phpbb as an alternative to
>> bazookaboard*, but not today, and probably not tomorrow. So if
>> things proceed without me, so be it.
>>
>
> Or set up a s
Peter Dalgaard wrote:
[snip]
Or, try looking at a smaller example where things can be worked out
explicitly: One-way ANOVA with random btw.group variation. Say 5
groups and 3 obs per group. If I got this right (please do check!),
the estimate of the between-group variance is 1/3 times the differenc
But this is a lot of work to set up. I'd rather take small
steps. I do plan to look into phpbb as an alternative to
bazookaboard*, but not today, and probably not tomorrow. So if
things proceed without me, so be it.
Or set up a server running Zope and Plone, and then you can have
wikis, board
sorry, that's the problem if I do not check my mails before sending one - I
read the proposal of a wiki or forum and like these ideas, perhaps it is
better than a new mailing list.
Martin
P.S.: my summary of replies to the original idea where mainly based on
off-list mails, sorry I should have
On 12/17/03 12:19, Gabor Grothendieck wrote:
>
>
>In rereading this one idea occurred to me. What if the entire R help
>system were turned into a wiki? That is,
>
>?whatever
>
>would take you to the help page, but not on your computer --
>rather to the same page on the wiki. You would then find
Try the excellent canned demos that exist package. You can see a
complete list of all the packages you have:
demo(package = .packages(all.available = TRUE))
I'd certainly show the graphics demo.
HTH, Andy
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of G
In rereading this one idea occurred to me. What if the entire R help
system were turned into a wiki? That is,
?whatever
would take you to the help page, but not on your computer --
rather to the same page on the wiki. You would then find the
docs as they exist now plus the experiences of ot
Rolf Turner wrote:
Gabor Grothendieck wrote:
My personal view on this is that there is need for a friendly
list with a more "customer service" attitude than r-help.
God save us from a ``"customer service" attitude'' --- bland,
fatuous, feel-good useless twaddle! If you want a ``custome
s
Dear R-user,
there have been already a lot of discussion with some good points against such
a list and the opposite opinions as well.
Well, I would like to propose that we start a testing phase either with
- only "internal" membership, that means only people from this dept. + perhaps
some ot
Hello,
On Wednesday 17 December 2003 05:43, Gabor Grothendieck wrote:
> My personal view on this is that there is need for a friendly
>
> list with a more "customer service" attitude than r-help.
well that sounds for me like a shop - "customer service"- ;-) and that's what
R should not become, i
Dear All,
--On woensdag 17 december 2003 11:59 -0500 Jonathan Baron
<[EMAIL PROTECTED]> wrote:
However, I volunteer to set up a VERY simple bulletin board using
Bazookaboard, for a start. If it becomes too big, I may have to
switch to something with more features. Too see an example, see
my cl
Dear All!
Tomorrow morning I will have to demonstrate R to a professor here at the
Semmelweis University. He uses Windows and Statistica. I will have 20
minutes and I would like to convince him that R is powerful, and it even
could be used in teaching the students basic medical statistics.
Could
Hello,
Roger Bivand wrote:
> appropriate light. One basic characteristic seems to be that if the
> question does indicate seriousness about trying to analyse data, respect
> for the task at hand, then predictably lots of good advice comes quickly.
yes, I also experienced that (from the questione
Mehdi Kadiri wrote:
Hello evry one,
I'm a frensh consulting Engineer in statistics and i work under R times to
times.
I would like to build an Graphic User Interface as we can do under MS Excel
but i don't know how to do it.
If you want to program the interface in VB, you can use the tools in
thi
I completely agree with Frank Harrell's suggestion that email is
a problem for beginners (who often don't know about the various
searchable archives, or find them overwhelming because the
massive amount that they contain, much of which is bound to be
irrelevant or too advanced).
I don't think a Wi
I agree that
- wikis (see the successful one for the lua programming
language at: http://lua-users.org/wiki/ )
- forums
are nice. Actually someone did set up an R wiki some time
ago at:
http://fawn.unibw-hamburg.de/cgi-bin/Rwiki.pl?RwikiHome
yet no one really used it. Some critical ma
> "Pascal" == Pascal A Niklaus <[EMAIL PROTECTED]>
> on Wed, 17 Dec 2003 16:52:07 +0100 writes:
Pascal> Hi all,
Pascal> I tried to save a complete log of a R session we had in a seminar
Pascal> today... but I didn't succeed.
Pascal> 1) R | tee session.log
Pascal>
My opinion is that separate lists are not needed (and I'm not clear on how
the person with the original idea summarized opinions in a way that
led to the conclusion that a new list is needed), but that a different
medium may be needed. The problem with e-mail is that to many users,
especially thos
Thomas Lumley <[EMAIL PROTECTED]> writes:
> On Tue, 16 Dec 2003, Gary Allison wrote:
>
> > Hi all,
> > I didn't get a response to my post of this issue a week ago, so I've
> > tried to clarify:
> >
> > When I use lme to analyze a model of nested random effects, the variance
> > estimates of level
Greetings all,
In follow up to this thread (I am copying all participants), I want to
provide some additional data.
In review, Peter Flom the original poster, received the following
warning message when using read.spss() to import a .SAV format SPSS data
set into R:
Warning message:
c:\NDRI\cva
Hi all,
I tried to save a complete log of a R session we had in a seminar
today... but I didn't succeed.
1) R | tee session.log
This saves both input and output, but I do get the cursor key escape
sequences from editing (cursor-up to get last command etc) instead of
the actual command line exe
On Tue, 16 Dec 2003, Gary Allison wrote:
> Hi all,
> I didn't get a response to my post of this issue a week ago, so I've
> tried to clarify:
>
> When I use lme to analyze a model of nested random effects, the variance
> estimates of levels higher in the hierarchy appear to have much more
> varian
"Peter Flom" <[EMAIL PROTECTED]> writes:
> What do others think? Has anyone else subscribed to the beginner list
> yet?
I won't. There is not enough time in the day.
best,
-tony
--
[EMAIL PROTECTED]http://www.analytics.washington.edu/
Biomedical and Health Informatics Universi
On 17-Dec-03 Peter Flom wrote:
> After thinking this over, I think it's a good idea to have the beginner
> list (and I have subscribed).
> [...]
> What do others think? Has anyone else subscribed to the beginner list
> yet?
>
> Peter
Perhaps there has now been enough discussion of whether such
Gabor Grothendieck wrote:
> My personal view on this is that there is need for a friendly
> list with a more "customer service" attitude than r-help.
God save us from a ``"customer service" attitude'' --- bland,
fatuous, feel-good useless twaddle! If you want a ``custome
service'' attitude go a
See ?winDialog and the "See Also" section there. Maybe that would suffice
for your purpose.
HTH,
Andy
> From: Mehdi Kadiri
>
> Hello evry one,
> I'm a frensh consulting Engineer in statistics and i work
> under R times to
> times.
> I would like to build an Graphic User Interface as we can do
Dear all,
I would like to raise the question regarding the Intel Itanium processors. Is
anyone using them in 64bit mode? I am mostly interested in memory-consuming
applications, e.g. the normalization of a large number of microarrays.
Andy Liaw told me that he is using R on a dual AMD Opteron in
Pascal,
If every run of my simulation produced results like you saw, I would not
be concerned. But a sizable fraction of my simulation runs produce much
larger standard deviations in level 1, though level 3's estimates stay
small. I've posted the results from 500 runs at:
http://david.science
> The aim is to have a GUI betwen a user and the console or the
function (for
exemple toto(a,b,c) )
In the GUI , i would like to have 3 boxes empty where i can put the values
of a, b, and c, and an other box where I click to Submit and a last bos to
read the result.
Take a look at http://www.sciv
Hello evry one,
I'm a frensh consulting Engineer in statistics and i work under R times to
times.
I would like to build an Graphic User Interface as we can do under MS Excel
but i don't know how to do it.
The aim is to have a GUI betwen a user and the console or the function (for
exemple toto(a,b,
After thinking this over, I think it's a good idea to have the beginner
list (and I have subscribed).
While I greatly appreciate this list, and the tremendous amount of help
I've gotten from it, the style of this list is, usually, to give fairly
short replies (e.g. "try ?function") This is fine
--- Andrew Criswell <[EMAIL PROTECTED]> wrote:
...
> My search on Amazon fails to locate the book Brandon
> mentions,
> "Resampling: The New Statistics". Is there more
> information on Author,
> ISBN, etc.?
FYI, try
http://www.resample.com/content/text/index.shtml
or
the main site at
htt
When I alter the levels of a factor, why does it alter the names too?
f <- factor(c(A="one",B="two",C="one",D="one",E="three"),
levels=c("one","two","three"))
names(f)
-- gives [1] "A" "B" "C" "D" "E"
levels(f) <- c("un","deux","trois")
names(f)
-- gives NULL
I'm using R 1.8.0 f
You have an NA in your data, it says. That makes the design unbalanced
(it it is not already unbalanced by having 50 obs with a 2x2
classification: I can't see the pattern from your extract but guess 25
subjects don't divide into two equal groups).
That you get the same effects in both strata
Running lme on your data set results exactly in what you expect - or do
you expect something different?
Pascal
> L1<-factor(F1f)
> L2<-factor(F2f)
> L3<-factor(F3f)
> lme(value ~ 1,random = ~ 1 | L1/L2/L3)
Linear mixed-effects model fit by REML
Data: NULL
Log-restricted-likelihood: 438.9476
F
Thanks, you've helped me alot!
-S.
On Wed, Dec 17, 2003 at 09:43:44AM +0100, Philipp Pagel wrote:
> rowMeans(USArrest)
>
> does what you want.
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hi all,
I have a strange problem and rigth now I can't figure out a
solution.
Trying to calculate an ANOVA with one between subject factor (group)
and one within (hemisphere). My dependent variable is source
localization (data). My N = 25.
My data.frame looks like this:
> ML.dist.stack
sub
On Wed, Dec 17, 2003 at 08:27:41AM +0100, Sven C. Koehler wrote:
> I am kind of new to R.
> I would like to calculate the mean of the numbers of this expression:
>
> data(USArrests)
> USArrests[row.names(M) == "Alabama",]
>
> class() tells me it's a ``data.frame,'' what I actually desire
On Tue, 16 Dec 2003, Gabor Grothendieck wrote:
>
>
> My personal view on this is that there is need for a friendly
> list with a more "customer service" attitude than r-help.
This is not a balanced view. In a project like ours, you really do need to
put participation in balance. If you don't of
rowMeans(mydf) will do this for a data frame mydf.
Be careful though to use it only with all-numeric data frames (there is an
implicit as.matrix going on), and often it makes more sense to store such
data in a matrix.
apply(mydf, 1, mean) would also work, but is slower.
On Wed, 17 Dec 2003, Sve
Dear r-helpers!
I am kind of new to R.
I would like to calculate the mean of the numbers of this expression:
data(USArrests)
USArrests[row.names(M) == "Alabama",]
class() tells me it's a ``data.frame,'' what I actually desire is to get
all numbers of a row as a vector or a list to let me
64 matches
Mail list logo