Re: [R] How to unload a package or undo library(package)
See the rw-FAQ, Q4.8 On Mon, 9 Jan 2006, Ales Ziberna wrote: If I do detach(package:blockmodeling) My package blockmodeling does not appear in (.packages()) [1] methods stats graphics grDevices utils datasets [7] base However, if I want to install a newer version from a local zip file, I get: utils:::menuInstallLocal() package 'blockmodeling' successfully unpacked and MD5 sums checked Error: cannot remove prior installation of package 'blockmodeling' Is there any way around that? Best, Ales Ziberna -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gabor Grothendieck Sent: Sunday, January 08, 2006 10:42 PM To: Alea }iberna Cc: r-help@stat.math.ethz.ch Subject: Re: [R] How to unload a package or undo library(package) Here are some things to try: detach() - detach most recent attached package detach(2) - detach package which is in position 2 on search list. Same as detach() detach(package:mypackage) - mypackage from search list search() - display search list On 1/8/06, Alea }iberna [EMAIL PROTECTED] wrote: Hello! I would like to unload a package form a current R session. I tried datach(package:packagename), however it does not work. The reason I want to unload it is that I want to correct some files in the package and reinstall it without closing an R session. Best, Ales Ziberna PS: I am using R 2.1.1 on Windows XP __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] paste tab and print
On Mon, 9 Jan 2006 [EMAIL PROTECTED] wrote:
Dear all,
info = paste('a', 'b', sep='\t')
print(info , quote=F)
doesn't produce the same result with R201 and R220
(under Windows2000)
(There are no such versions of R, and neither is current.)
R 2.0.1 : [1] a b
R 2.2.0 : [1] a\tb
I did read the CHANGESR220 file
Did you mean CHANGES? That is for Windows-specific changes. You
meed to look in the NEWS file.
and tried also the search engine but couldn't find an answer. I
certainly missed the point, and apologize about that.
So if somebody could tell me how to insert a tab inside
strings under R.2.2.0., it would be very kind.
You have. A tab inside a string is printed as \t (see ?print.default).
However, cat will show you the effect
info = paste('a', 'b', sep='\t')
print(info)
[1] a\tb
cat(info, \n)
a b
(if this survives emailing, or try it yourself).
--
Brian D. Ripley, [EMAIL PROTECTED]
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UKFax: +44 1865 272595
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Missing value representation in Excel before extraction to R with RODBC
On Mon, 9 Jan 2006, Petr Pikal wrote: Hi I believe it has something to do with the column identification decision. When R decides what is in a column it uses only some values from the beginning of a file. Not R, Excel. Excel tells ODBC what the column types are. I do not use RODBC as read.delim(clipboard, ...) is usually more convenient but probably there is a way how to tell RODBC what is in the column instead of let R decide from the top of the file. Using as.is=TRUE stops RODBC doing any conversion. But I may be completely mistaken. HTH Petr On 6 Jan 2006 at 20:47, Fredrik Lundgren wrote: From: Fredrik Lundgren [EMAIL PROTECTED] To: R-help r-help@stat.math.ethz.ch Date sent:Fri, 6 Jan 2006 20:47:29 +0100 Subject: [R] Missing value representation in Excel before extraction to R with RODBC Dear list, How should missing values be expressed in Excel before extraction to R via RODBC. I'm bewildered. Sometimes the representation with NA in Excel appears to work and shows up in R as NA but sometimes the use of NA in Excel changes the whole vector to NA's. Blank or nothing or NA as representation for missing values in Excel with dateformat gives NA's of the whole vector in R but with general format in Excel gives blanks for missing values in R. How should I represent missing values in Excel? Best wishes and thanks for any help Fredrik Lundgren -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] [R-pkgs] sudoku
First, thanks a lot! to David Brahms for finally tackling this
important problem, and keeping the R language major league !
;-) :-) {but the thanks! is meant seriously!}
Detlef == Detlef Steuer [EMAIL PROTECTED]
on Sun, 8 Jan 2006 12:21:52 +0100 writes:
Detlef Hey, you spoiled my course! :-)
Detlef I planned using this as an excersise. Alternative
Detlef ideas anyone ...
Well, you could *add* to it:
1) When I have been thinking about doing this myself (occasionally
in the past weeks), I had always thought that finding *ALL*
solutions was a very important property of the algorithm I would
want to design.
(since this is slightly more general and useful than proofing
uniqueness which the current algorithm does not yet do anyway).
2) The current sudoku() prints the result itself and returns a
matrix; improved, it should return an object of class sudoku,
with a print() and a plot() method;
3) The plot() method should of course also work for unfinished
sudoku objects, and in fact, the *input* to sudoku() should
also be allowed to be a (typically unfinished) sudoku object.
4) Then you could have your students use grid and
grid.locator() for GUI *input* of a sudoku; i.e. you'd have
another function which returns a (typically unfinished)
sudoku object.
5) You could start looking at *solving* the more general sudokus
where the blocks are not 3x3 squares anymore, but more
general rectangular polygons of 9 squares each.
6) Now you need to refine the GUI from 4) because your users
need to be able to *draw* the block shapes for the
generalized sudokus.
7) Given 1) is solved, the problem of *generating* sudokus,
that David already mentioned in his announcement, becomes
more relevant: You want to be sure that the sudokus you
generate have exactly one solution. And your generating
algorithm could start with a very full sudoku (that has
exactly 1 solution) and erases squares as much as possible,
always checking that no other solution becomes possible.
You see, there's lot of interesting exercises left for your
course. (;-)
Martin
Detlef On Fri, 6 Jan 2006 11:43:44 -0500 Brahm, David
Detlef [EMAIL PROTECTED] wrote:
Any doubts about R's big-league status should be put to
rest, now that we have a Sudoku Puzzle Solver. Take
that, SAS! See package sudoku on CRAN.
The package could really use a puzzle generator --
contributors are welcome!
-- David Brahm ([EMAIL PROTECTED])
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to unload a package or undo library(package)
Thank you! I guess it can not be done! Best, Ales Ziberna -Original Message- From: Prof Brian Ripley [mailto:[EMAIL PROTECTED] Sent: Monday, January 09, 2006 9:19 AM To: Ales Ziberna Cc: r-help@stat.math.ethz.ch Subject: Re: [R] How to unload a package or undo library(package) See the rw-FAQ, Q4.8 On Mon, 9 Jan 2006, Ales Ziberna wrote: If I do detach(package:blockmodeling) My package blockmodeling does not appear in (.packages()) [1] methods stats graphics grDevices utils datasets [7] base However, if I want to install a newer version from a local zip file, I get: utils:::menuInstallLocal() package 'blockmodeling' successfully unpacked and MD5 sums checked Error: cannot remove prior installation of package 'blockmodeling' Is there any way around that? Best, Ales Ziberna -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gabor Grothendieck Sent: Sunday, January 08, 2006 10:42 PM To: Alea }iberna Cc: r-help@stat.math.ethz.ch Subject: Re: [R] How to unload a package or undo library(package) Here are some things to try: detach() - detach most recent attached package detach(2) - detach package which is in position 2 on search list. Same as detach() detach(package:mypackage) - mypackage from search list search() - display search list On 1/8/06, Alea }iberna [EMAIL PROTECTED] wrote: Hello! I would like to unload a package form a current R session. I tried datach(package:packagename), however it does not work. The reason I want to unload it is that I want to correct some files in the package and reinstall it without closing an R session. Best, Ales Ziberna PS: I am using R 2.1.1 on Windows XP __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] How to restore workspace from .RDataTmp?
Can I restore a workspace from .RDataTmp (under Windows), and how should I do this? Whenever I try, I get the messages Error in load(name, envir = .GlobalEnv) : error reading from connection (in the R command window) and/or Fatal error: unable to restore saved data in .RData (Windows). I was not able to find any documentation of this. Any help is appreciated. Helene PD Dr. Helene Wagner Senior scientist Swiss Federal Research Institute WSL Zuercherstrasse 111 CH-8903 Birmensdorf Phone: +41-44-739 25 87 Fax:+41-44-739 22 15 Email: [EMAIL PROTECTED] http://www.wsl.ch/staff/helene.wagner/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] need palette of topographic colors similar to topo.colors()
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
have a look at http://colorbrewer.org/
and install the package RColorBrewer
David
On Jan 7, 2006, at 20:34, bogdan romocea wrote:
Dear useRs,
I got stuck trying to generate a palette of topographic colors that
would satisfy these two requirements:
- the pallete must be 'anchored' at 0 (just like on a map), with
light blue/lawn green corresponding to data values close to 0 (dark
blue to light blue for negative values, green-yellow-brown for
positive values)
- the brown must get darker for higher positive values.
topo.colors() fails both requirements and AFAICS lacks any options to
control its behavior.
#---unsatisfactory topo.colors() behavior
topoclr - function(tgt)
{
clr - topo.colors(length(tgt))
clr - clr[round(rank(tgt),0)]
plot(tgt,pch=15,col=clr)
}
par(mfrow=c(2,1)) ; topoclr(-50:50) ; topoclr(-20:80)
An acceptable solution would be something like this
grayclr - function(tgt)
{
tgt - sort(tgt) ; neg - which(tgt 0)
clrneg - gray(0:length(tgt[neg])/length(tgt[neg]))
clrpos - gray(length(tgt[-neg]):0/length(tgt[-neg]))
clr - c(clrneg,clrpos)
plot(tgt,pch=15,col=clr)
}
par(mfrow=c(2,1)) ; grayclr(-50:50) ; grayclr(-20:80)
if only I could make gray() use blue/brown instead of black (I tried a
couple of things but got stuck again).
Any suggestions?
Thank you,
b.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
-BEGIN PGP SIGNATURE-
Version: GnuPG v1.4.1 (Darwin)
iD8DBQFDwjXx7EoGVUIQyhERAq/0AKCPKQjlqtVl+RxVlOVlGXf2WxnvSwCfdZcD
mEpL3eSW8KI+eYFSSQZJvzM=
=/5Ix
-END PGP SIGNATURE-
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to restore workspace from .RDataTmp?
Hi See http://finzi.psych.upenn.edu/R/Rhelp02a/archive/63390.html There is not much to do in such a case. Maybe only to use some binary editor. Recommendation: do not use .Rdata file for storing data Cheers Petr On 9 Jan 2006 at 10:26, Helene Wagner wrote: Date sent: Mon, 09 Jan 2006 10:26:50 +0100 To: r-help@stat.math.ethz.ch From: Helene Wagner [EMAIL PROTECTED] Subject:[R] How to restore workspace from .RDataTmp? Can I restore a workspace from .RDataTmp (under Windows), and how should I do this? Whenever I try, I get the messages Error in load(name, envir = .GlobalEnv) : error reading from connection (in the R command window) and/or Fatal error: unable to restore saved data in .RData (Windows). I was not able to find any documentation of this. Any help is appreciated. Helene PD Dr. Helene Wagner Senior scientist Swiss Federal Research Institute WSL Zuercherstrasse 111 CH-8903 Birmensdorf Phone: +41-44-739 25 87 Fax:+41-44-739 22 15 Email: [EMAIL PROTECTED] http://www.wsl.ch/staff/helene.wagner/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] repeat { readline() }
--- Henrik Bengtsson [EMAIL PROTECTED] a écrit :
Hi.
Using Rterm v2.2.1 on WinXP, is there a way to
interrupt a call like
repeat { readline() }
without killing the Command window? Ctrl+C is not
interrupting the loop:
To interupt the loop add and condition for a break
like this :
if () break
R : Copyright 2006, The R Foundation for Statistical
Computing
Version 2.2.1 Patched (2006-01-01 r36947)
snip/snip
repeat { readline() }
^C
^C
^C
^C
On Unix it works. The problem seems to get the
interrupt signal to
occur outside the readline() call so that repeat
is interrupted. Doing
repeat { readline(); Sys.sleep(3) }
and it is likely that can generate an interrupt
signal outside readline().
It seem like readline()/readLines(n=1) or an
underlying method catches
the interrupt signal quietly and just waits for a
symbol to come
through. Try readline() by itself and press Ctrl+C.
Maybe this is a
property of the Windows Command terminal, I don't
know, but is it a
wanted feature and are R core aware of it? Note
that, in Rgui it is
possible to interrupting such a loop by pressing
ESC.
Cheers
Henrik
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis for R
Frank uses the term hierarchical keyword organization which I agree is a good way to organize a system designed to help users. In fact, this is one reason why I like the R graphics gallery which allows one to quickly find a particular type of plot based on keyword, examine the plot to see if it's close to what's desired, and then get the detailed code to examine or modify for one's own specific purpose. It's an example of going from general concept to specific details. R's HTML help pages already have a keyword system but it takes you to the specifics too quickly. I'd recommend revising the current keyword system in the help pages (or adding to it) to create what Frank calls data manipulation examples gallery. In other words a code gallery that users could browse quickly and simply copy and paste code from it to their application. Think of the keywords as different How to topics (e.g. how to create a data frame, how to reshape data, etc.). ** I think this sort of thing would save time for users of all levels.** New users could find code quickly WITHOUT submitting a request to R-HELP email list. Advanced, experts, and gurus would no longer have to respond to such requests for the umpteenth time. Think of this as the examples that did not make it to the help files. Because it's a wiki folks could add to it the examples that are truly helpful. Creating such a system requires 3 steps (at a very high level): 1) ** Develop a hierarchical keyword system ** Combine the current keyword system (http://finzi.psych.upenn.edu/R/doc/html/search/SearchEngine.html) with something more like the left-hand frame of the function finder (http://biostat.mc.vanderbilt.edu/s/finder/finder.html). Essentially a list of keywords organized by how to do X in R. Users could browse this list and click on a how to topic to get to more specific keyworks or see the code gallery for that particular keyword. Once this list of keywords gets generated then it would would remain mostly static over time. If changes are required then have the site maintainer add the word, but the keyword list is not open to public revision. 2) ** Add code as content for each keyword. ** Without quality and quantity of content, this proposed system is not worth much. No one will use it without content -- I don't care what fancy tool we use to create or manage such a thing. I suspect that much of the code to start this gallery could come from R tips (http://www.ku.edu/~pauljohn/R/Rtips.html). After amassing a good size collection of code, allow the public to start adding to the code (but not the keywords identified in #1 above.) 3) ** Link 1 and 2 above, which are on the wiki, with the existing help files that get installed with R **. So when a user chooses HTML Help from the Help menu (in the windows version of R, for example) he/she would see an additional clickable link that says something like How To. Clicking on this would take the user to the list of keywords for the code gallery on the online wiki. This is their starting point. From here the user would click on appropriate keywords to browse the code gallery. The code itself could be clickable to bring up the very detailed help pages much like the R Graphics Gallery does (for example clicking on the green color rnorm in the first graph in the Graphics Gallery takes me to the following hyperlinked help page: http://addictedtor.free.fr/graphiques/help/index.html?pack=statsalias=rnormfun=Normal.html). I'm wondering how much of the above could be done without requiring much work from the R CORE team? I'd recommend a small group of individuals (10 - 20 or so) to start getting the content together since that may be the most time intensive part. (You can't expect 1 person to do it all, and 1000's of people won't make much progress.) I can lend a few hours per month if there was a cadre of dedicated individuals who are passionate about making this happen. However, I have very few programming skills, almost none outside of R, of which I'm a relative beginner. This is the vision I have for the wiki. What do others think? ~Nick -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Frank E Harrell Jr Sent: Saturday, January 07, 2006 6:05 AM To: Detlef Steuer Cc: r-help@stat.math.ethz.ch; [EMAIL PROTECTED]; [EMAIL PROTECTED] Subject: Re: [R] Wikis for R Detlef Steuer wrote: On Thu, 5 Jan 2006 11:23:04 -0200 Fernando Henrique Ferraz P. da Rosa [EMAIL PROTECTED] wrote: Martin Maechler writes: If you go to the bottom of that wikipedia page, you see that there is an R Wiki -- and has been for several years now (!) at a Hamburg (De) university. http://fawn.unibw-hamburg.de/cgi-bin/Rwiki.pl?RwikiHome (...) So, are you sure that another R Wiki is desirable, rather than have people who believe in Wiki's for R use the existing one(s)? I believe the main challenge will (similar as for an R-beginners mailing list) to have well-qualified editors to be willing to
[R] (no subject)
Dear R People: I am trying to build a package (yet again!) I have both PCTex and WinEdt. I want the *.tex files to use WinEdt. How should I set that, please? Just in the path? Also, where would I get Rd.sty, please? Thanks, R Version 2.2.1 Windows Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown mailto: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Suggestion for big files [was: Re: A comment about R:]
[hadley wickham] [François Pinard] Selecting a sample is easy. Yet, I'm not aware of any SQL device for easily selecting a _random_ sample of the records of a given table. On the other hand, I'm no SQL specialist, others might know better. There are a number of such devices, which tend to be rather SQL variant specific. Try googling for select random rows mysql, select random rows pgsql, etc. Thanks as well for these hints. Googling around as your suggested (yet keeping my eyes in the MySQL direction, because this is what we use), getting MySQL itself to do the selection is a bit discouraging, as according to comments I've read, MySQL does not seem to scale well with the database size according to the comments I've read, especially when records have to be decorated with random numbers and later sorted. Yet, I did not drive any benchmark myself, and would not blindly take everything I read for granted, given that MySQL developers have speed in mind, and there are ways to interrupt a sort before running it to full completion, when only a few sorted records are wanted. Another possibility is to generate a large table of randomly distributed ids and then use that (with randomly generated limits) to select the appropriate number of records. I'm not sure I understand your idea (what mixes me in the randomly generated limits part). If the large table is much larger than the size of the wanted sample, we might not be gaining much. Just for fun: here, sample(1, 10) in R is slowish already :-). All in all, if I ever have such a problem, a practical solution probably has to be outside of R, and maybe outside SQL as well. -- François Pinard http://pinard.progiciels-bpi.ca __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] two y-axis in xy-plot
Hi there, I am wondering if it is possible to do an xyplot with two y-axes. I'd like to print two parameters in a time series but they both have different scales. Which parameter in xyplot can I add to achieve this result? Thanks a lot for any help. Antje [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A comment about R:
François Pinard wrote: [Uwe Ligges] François Pinard wrote: [David Forrest] [...] A few end-to-end tutorials on some interesting analyses would be helpful. I'm in the process of learning R. While tutorials are undoubtedly very useful, and understanding that working and studying methods vary between individuals, what I (for one) would like to have is a fairly complete reference manual to the library [...] organised by topics. Have a look at help.start() -- Search Engine Keywords -- Section Keywords by Topic. Yes, thanks. This is quite in the spirit, or direction, of what I was proposing. Is that resource exhaustive? (I'm asking out of laziness, as it might take me several months to really check.) It is exhaustive in the following sense: - the help page has the appropriate keyword - the package is installed One serious drawback (for me) is that it requires an heavy weight browser to be used, with Javascript enabled. I do not find this very practical. Another point is that the presentation, while useful, is a rather dry. In another message, I suggested the Emacs Lisp Reference Manual as a good example of a fluid presentation of a voluminous library. There might be some workable compromise between the current situation with R, even through the Keywords by Topic, and that fluidity. (Wikis also have the drawback of requiring heavy machinery, and the editor they force us into if usually unbearable.) I may be back with this subject, but only in a good while. I'm slowly building a kind of documentation plan I want (yet in French), as I learn R, and guess I may complete my base learning in one or two years from now (hoping I'll stay courageous enough). If I then get something usable or shareable enough, I'll offer it -- because I like returning a little something for the nice tools given to me! :-) So we are looking forward to see the better system. Uwe Ligges In any case, thanks for listening! __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
At 20:12 08/01/06, Jack Tanner wrote: Philippe's idea to start a wiki that grows out of the content on http://zoonek2.free.fr/UNIX/48_R/all.html is really great. Here's why. My hypothesis is that the basic reason that people ask questions on R-help rather than first looking elsewhere is that looking elsewhere doesn't get them the info they need. People think in terms of the tasks they have to do. The documentation for R, which can be very good, is organized in terms of the structure of R, its functions. This mismatch -- people think of tasks, the documentation thinks in functions -- causes people to turn to the mailing list. Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. Michael Dewey http://www.aghmed.fsnet.co.uk __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] wicked wikis for R
From: Arin Basu [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date: 8 Jan 2006 19:18:17 - Subject: [R] wicked wikis for R Message: 41 Date: Sun, 08 Jan 2006 13:52:33 +1100 From: paul sorenson [EMAIL PROTECTED] Subject: Re: [R] Wikis etc. To: Frank E Harrell Jr [EMAIL PROTECTED], r-help r-help@stat.math.ethz.ch -snip- Among others, here's one long-term benefit for the newbies. Instead of people getting admonished/thrashed with harsh expressions/advices like go see the mailing list publishing etiquettes, or you should search the archives and help files, and read all manuals, and ask others first before posting here... (which can turn away many a newcomer from posting or using the mailing list or using R for that matter), wiki could make life a little easy for newbies/less experienced who could then receive more polite one liners like, please check the wikipages..., or solution #xyz in the wikipages for the solution. Sorry, I don't get the point here. Some people will keep feeling offensed when they're just told to read the man/wiki pages, and others will simply change their answers from RTFM to RTFW. Nobody can force people into reading the manuals, or reading the posting guide. This is definitely one problem that the wiki will not solve. I like the idea of the wiki, but we have to consider pragmatically, not as a panacea from problems beyond its scope. Regards, Jean-Christophe Bouëtté. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Suggestion for big files [was: Re: A comment about R:]
I found Reservoir-Sampling algorithms of time complexity O(n(1+log(N/n))) by Kim-Hung Li , ACM Transactions on Mathematical Software Vol 20 No 4 Dec 94 p481-492. He mentions algorithm Z and K and proposed 2 improved versions alg L and M. Algorith L is really easy to implement but relatively slow, M doesn't look very difficult and is the fastest. Heberto Ghezzo McGill University Montreal - Canada Quoting François Pinard [EMAIL PROTECTED]: [Martin Maechler] FrPi Suppose the file (or tape) holds N records (N is not known FrPi in advance), from which we want a sample of M records at FrPi most. [...] If the algorithm is carefully designed, when FrPi the last (N'th) record of the file will have been processed FrPi this way, we may then have M records randomly selected from FrPi N records, in such a a way that each of the N records had an FrPi equal probability to end up in the selection of M records. I FrPi may seek out for details if needed. [...] I'm also intrigued about the details of the algorithm you outline above. I went into my old SPSS books and related references to find it for you, to no avail (yet I confess I did not try very hard). I vaguely remember it was related to Spearman's correlation computation: I did find notes about the severe memory limitation of this computation, but nothing about the implemented workaround. I did find other sampling devices, but not the very one I remember having read about, many years ago. On the other hand, Googling tells that this topic has been much studied, and that Vitter's algorithm Z seems to be popular nowadays (even if not the simplest) because it is more efficient than others. Google found a copy of the paper: http://www.cs.duke.edu/~jsv/Papers/Vit85.Reservoir.pdf Here is an implementation for Postgres: http://svr5.postgresql.org/pgsql-patches/2004-05/msg00319.php yet I do not find it very readable -- but this is only an opinion: I'm rather demanding in the area of legibility, while many or most people are more courageous than me! :-). -- François Pinard http://pinard.progiciels-bpi.ca __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] [R-pkgs] sudoku
As far as generating a sudoku, it can't be too hard because I have a program
on my cell phone that does it with a size less than 325K. I don't know the
best way to generate these, but one way I was thinking of was starting with
a filled up one then randomize the columns and rows. Then make some of them
blank. The cell-phone version often generates puzzles that have non-unique
solutions. Though I admit this is sometimes annoying, it also can make the
puzzle harder.
Thanks,
Roger
On 1/9/06, Martin Maechler [EMAIL PROTECTED] wrote:
First, thanks a lot! to David Brahms for finally tackling this
important problem, and keeping the R language major league !
;-) :-) {but the thanks! is meant seriously!}
Detlef == Detlef Steuer [EMAIL PROTECTED]
on Sun, 8 Jan 2006 12:21:52 +0100 writes:
Detlef Hey, you spoiled my course! :-)
Detlef I planned using this as an excersise. Alternative
Detlef ideas anyone ...
Well, you could *add* to it:
1) When I have been thinking about doing this myself (occasionally
in the past weeks), I had always thought that finding *ALL*
solutions was a very important property of the algorithm I would
want to design.
(since this is slightly more general and useful than proofing
uniqueness which the current algorithm does not yet do anyway).
2) The current sudoku() prints the result itself and returns a
matrix; improved, it should return an object of class sudoku,
with a print() and a plot() method;
3) The plot() method should of course also work for unfinished
sudoku objects, and in fact, the *input* to sudoku() should
also be allowed to be a (typically unfinished) sudoku object.
4) Then you could have your students use grid and
grid.locator() for GUI *input* of a sudoku; i.e. you'd have
another function which returns a (typically unfinished)
sudoku object.
5) You could start looking at *solving* the more general sudokus
where the blocks are not 3x3 squares anymore, but more
general rectangular polygons of 9 squares each.
6) Now you need to refine the GUI from 4) because your users
need to be able to *draw* the block shapes for the
generalized sudokus.
7) Given 1) is solved, the problem of *generating* sudokus,
that David already mentioned in his announcement, becomes
more relevant: You want to be sure that the sudokus you
generate have exactly one solution. And your generating
algorithm could start with a very full sudoku (that has
exactly 1 solution) and erases squares as much as possible,
always checking that no other solution becomes possible.
You see, there's lot of interesting exercises left for your
course. (;-)
Martin
Detlef On Fri, 6 Jan 2006 11:43:44 -0500 Brahm, David
Detlef [EMAIL PROTECTED] wrote:
Any doubts about R's big-league status should be put to
rest, now that we have a Sudoku Puzzle Solver. Take
that, SAS! See package sudoku on CRAN.
The package could really use a puzzle generator --
contributors are welcome!
-- David Brahm ([EMAIL PROTECTED])
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] wicked wikis for R
Jean-Christophe BOUETTE wrote: From: Arin Basu [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date: 8 Jan 2006 19:18:17 - Subject: [R] wicked wikis for R Message: 41 Date: Sun, 08 Jan 2006 13:52:33 +1100 From: paul sorenson [EMAIL PROTECTED] Subject: Re: [R] Wikis etc. To: Frank E Harrell Jr [EMAIL PROTECTED], r-help r-help@stat.math.ethz.ch -snip- Among others, here's one long-term benefit for the newbies. Instead of people getting admonished/thrashed with harsh expressions/advices like go see the mailing list publishing etiquettes, or you should search the archives and help files, and read all manuals, and ask others first before posting here... (which can turn away many a newcomer from posting or using the mailing list or using R for that matter), wiki could make life a little easy for newbies/less experienced who could then receive more polite one liners like, please check the wikipages..., or solution #xyz in the wikipages for the solution. Sorry, I don't get the point here. Some people will keep feeling offensed when they're just told to read the man/wiki pages, and others will simply change their answers from RTFM to RTFW. Nobody can force people into reading the manuals, or reading the posting guide. This is definitely one problem that the wiki will not solve. I like the idea of the wiki, but we have to consider pragmatically, not as a panacea from problems beyond its scope. That would be an excellent comment if people seeking help were paying for a service. But they are not. Frank Regards, Jean-Christophe Bouëtté. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] decide between polynomial vs ordered factor model (lme)
Dear alltogether, two lme's, the data are available at: http://www.anicca-vijja.de/lg/hlm3_nachw.Rdata explanations of the data: nachw = post hox knowledge tests over 6 measure time points (= equally spaced) zeitn = time points (n = 6) subgr = small learning groups (n = 28) gru = 4 different groups = treatment factor levels: time (=zeitn) (n=6) within subject (n=4) within smallgroups (=gru) (n = 28), i.e. n = 4 * 28 = 112 persons and 112 * 6 = 672 data points library(nlme) fitlme7 - lme(nachw ~ I(zeitn-3.5) + I((zeitn-3.5)^2) + I((zeitn-3.5)^3) + I((zeitn-3.5)^4)*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) fit5 - lme(nachw ~ ordered(I(zeitn-3.5))*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) Model df AIC BIClogLik Test update(fit5, method = ML)1 29 2535.821 2666.619 -1238.911 update(fitlme7, method = ML) 2 16 2529.719 2601.883 -1248.860 1 vs 2 L.Ratio p-value update(fit5, method = ML) update(fitlme7, method = ML) 19.89766 0.0978 shows that both are ~ equal, although I know about the uncertainty of ML tests with lme(). Both models show that the ^2 and the ^4 terms are important parts of the model. My question is: - Is it legitim to choose a model based on these outputs according to theoretical considerations instead of statistical tests that not really show a superiority of one model over the other one? - Is there another criterium I've overseen to decide which model can be clearly prefered? - The idea behind that is that in the one model (fit5) the second contrast of the factor (gru) is statistically significant, although not the whole factor in the anova output. In the other model, this is not the case. Theoretically interesting is of course the significance of the second contrast of gru, as it shows a tendency of one treatment being slightly superior. I want to choose this model but I am not sure whether this is proper action. Both models shows this trend, but only one model clearly indicates that this trend bears some empirical meaning. Thanks for any suggestions, leo here are the outputs for each model: fitlme7 - lme(nachw ~ I(zeitn-3.5) + I((zeitn-3.5)^2) + I((zeitn-3.5)^3) + I((zeitn-3.5)^4)*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) plot(augPred(fitlme7), layout=c(14,8)) summary(fitlme7); anova(fitlme7); intervals(fitlme7) Linear mixed-effects model fit by REML Data: hlm3 AIC BIClogLik 2582.934 2654.834 -1275.467 Random effects: Formula: ~1 | subgr (Intercept) StdDev: 0.5833797 Formula: ~zeitn | subject %in% subgr Structure: General positive-definite, Log-Cholesky parametrization StdDevCorr (Intercept) 0.6881908 (Intr) zeitn 0.1936087 -0.055 Residual1.3495785 Fixed effects: nachw ~ I(zeitn - 3.5) + I((zeitn - 3.5)^2) + I((zeitn - 3.5)^3) + I((zeitn - 3.5)^4) * gru Value Std.Error DF t-value p-value (Intercept) 4.528757 0.17749012 553 25.515542 0. I(zeitn - 3.5) 0.010602 0.08754449 553 0.121100 0.9037 I((zeitn - 3.5)^2) 0.815693 0.09765075 553 8.353171 0. I((zeitn - 3.5)^3) 0.001336 0.01584169 553 0.084329 0.9328 I((zeitn - 3.5)^4) -0.089655 0.01405811 553 -6.377486 0. gru1 0.187181 0.30805090 24 0.607630 0.5491 gru2 0.532665 0.30805090 24 1.729147 0.0966 gru3-0.046305 0.30805090 24 -0.150317 0.8818 I((zeitn - 3.5)^4):gru1 -0.007860 0.00600928 553 -1.307993 0.1914 I((zeitn - 3.5)^4):gru2 -0.001259 0.00600928 553 -0.209516 0.8341 I((zeitn - 3.5)^4):gru3 -0.000224 0.00600928 553 -0.037225 0.9703 Correlation: (Intr) I(-3.5 I((-3.5)^2 I((-3.5)^3 I((z-3.5)^4) I(zeitn - 3.5) 0.071 I((zeitn - 3.5)^2) -0.465 0.000 I((zeitn - 3.5)^3) 0.000 -0.914 0.000 I((zeitn - 3.5)^4) 0.401 0.000 -0.977 0.000 gru1 0.000 0.000 0.000 0.000 0.000 gru2 0.000 0.000 0.000 0.000 0.000 gru3 0.000 0.000 0.000 0.000 0.000 I((zeitn - 3.5)^4):gru1 0.000 0.000 0.000 0.000 0.000 I((zeitn - 3.5)^4):gru2 0.000 0.000 0.000 0.000 0.000 I((zeitn - 3.5)^4):gru3 0.000 0.000 0.000 0.000 0.000 gru1 gru2 gru3 I((-3.5)^4):1 I((-3.5)^4):2 I(zeitn - 3.5) I((zeitn - 3.5)^2) I((zeitn - 3.5)^3) I((zeitn - 3.5)^4) gru1 gru2 0.000 gru3 0.000 0.000 I((zeitn - 3.5)^4):gru1 -0.287 0.000 0.000 I((zeitn - 3.5)^4):gru2 0.000 -0.287 0.000 0.000 I((zeitn - 3.5)^4):gru3 0.000 0.000 -0.287 0.000 0.000 Standardized Within-Group Residuals: Min
[R] how to run the data editor by command?Thanks!
Thanks! -- Liu jcheng [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] how to run the data editor by command?Thanks!
?fix ?edit 2006/1/9, 刘加成 [EMAIL PROTECTED]: Thanks! -- Liu jcheng [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 黄荣贵 Deparment of Sociology Fudan University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] How to use filled.contour(x,y,z) data for levelplot(z)?
Dear all,
We used the following function to create a spatial plot of a raster image:
filled.contour(xx,yy,zz, color = terrain.colors, nlevels=10,
main=naamjaar, plot.axes = { contour(Xcoord/1000,Ycoord/1000,lim.data,
nlevels = 4, col=4,drawlabels = T, axes = FALSE, frame.plot = FFALSE,
add = TRUE);axis(1); axis(2);
points(fire[,2:3]/1000,col=red,pch=*,cex=2,lwd=3)
})
we however would like to create 5 maps with only one legend. This seems
not to be possible with filled.contour follow the help().
We therefore started looking at levelplot(zz) to create a multipanel view.
*However how could we use x and y coordinates in levelplot without using
a formula (since x,y are only the coordinates of the matrix z)?
libary(lattice)
rownames(zz) - xx
colnames(zz) - yy
levelplot(zz)
like this the all the row and col names are displayed in x and y axis
without summarizing data similar to filled.contour function?
* or can this be done with an upgrade of filled.contour?
Thanks,
Jan
windows R 2.2
Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] decide between polynomial vs ordered factor model (lme)
I think that these models are not nested and thus the LRT produced by anova.lme() will not be valid; AIC and BIC could be more relevant. In terms of interpretability, I'd say that a model treating 'zeitn' as a factor is much easier to explain than a model with 4th order polynomial. I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/(0)16/336899 Fax: +32/(0)16/337015 Web: http://www.med.kuleuven.be/biostat/ http://www.student.kuleuven.be/~m0390867/dimitris.htm - Original Message - From: Leo Gürtler [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Monday, January 09, 2006 2:59 PM Subject: [R] decide between polynomial vs ordered factor model (lme) Dear alltogether, two lme's, the data are available at: http://www.anicca-vijja.de/lg/hlm3_nachw.Rdata explanations of the data: nachw = post hox knowledge tests over 6 measure time points (= equally spaced) zeitn = time points (n = 6) subgr = small learning groups (n = 28) gru = 4 different groups = treatment factor levels: time (=zeitn) (n=6) within subject (n=4) within smallgroups (=gru) (n = 28), i.e. n = 4 * 28 = 112 persons and 112 * 6 = 672 data points library(nlme) fitlme7 - lme(nachw ~ I(zeitn-3.5) + I((zeitn-3.5)^2) + I((zeitn-3.5)^3) + I((zeitn-3.5)^4)*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) fit5 - lme(nachw ~ ordered(I(zeitn-3.5))*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) Model df AIC BIClogLik Test update(fit5, method = ML)1 29 2535.821 2666.619 -1238.911 update(fitlme7, method = ML) 2 16 2529.719 2601.883 -1248.860 1 vs 2 L.Ratio p-value update(fit5, method = ML) update(fitlme7, method = ML) 19.89766 0.0978 shows that both are ~ equal, although I know about the uncertainty of ML tests with lme(). Both models show that the ^2 and the ^4 terms are important parts of the model. My question is: - Is it legitim to choose a model based on these outputs according to theoretical considerations instead of statistical tests that not really show a superiority of one model over the other one? - Is there another criterium I've overseen to decide which model can be clearly prefered? - The idea behind that is that in the one model (fit5) the second contrast of the factor (gru) is statistically significant, although not the whole factor in the anova output. In the other model, this is not the case. Theoretically interesting is of course the significance of the second contrast of gru, as it shows a tendency of one treatment being slightly superior. I want to choose this model but I am not sure whether this is proper action. Both models shows this trend, but only one model clearly indicates that this trend bears some empirical meaning. Thanks for any suggestions, leo here are the outputs for each model: fitlme7 - lme(nachw ~ I(zeitn-3.5) + I((zeitn-3.5)^2) + I((zeitn-3.5)^3) + I((zeitn-3.5)^4)*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) plot(augPred(fitlme7), layout=c(14,8)) summary(fitlme7); anova(fitlme7); intervals(fitlme7) Linear mixed-effects model fit by REML Data: hlm3 AIC BIClogLik 2582.934 2654.834 -1275.467 Random effects: Formula: ~1 | subgr (Intercept) StdDev: 0.5833797 Formula: ~zeitn | subject %in% subgr Structure: General positive-definite, Log-Cholesky parametrization StdDevCorr (Intercept) 0.6881908 (Intr) zeitn 0.1936087 -0.055 Residual1.3495785 Fixed effects: nachw ~ I(zeitn - 3.5) + I((zeitn - 3.5)^2) + I((zeitn - 3.5)^3) + I((zeitn - 3.5)^4) * gru Value Std.Error DF t-value p-value (Intercept) 4.528757 0.17749012 553 25.515542 0. I(zeitn - 3.5) 0.010602 0.08754449 553 0.121100 0.9037 I((zeitn - 3.5)^2) 0.815693 0.09765075 553 8.353171 0. I((zeitn - 3.5)^3) 0.001336 0.01584169 553 0.084329 0.9328 I((zeitn - 3.5)^4) -0.089655 0.01405811 553 -6.377486 0. gru1 0.187181 0.30805090 24 0.607630 0.5491 gru2 0.532665 0.30805090 24 1.729147 0.0966 gru3-0.046305 0.30805090 24 -0.150317 0.8818 I((zeitn - 3.5)^4):gru1 -0.007860 0.00600928 553 -1.307993 0.1914 I((zeitn - 3.5)^4):gru2 -0.001259 0.00600928 553 -0.209516 0.8341 I((zeitn - 3.5)^4):gru3 -0.000224 0.00600928 553 -0.037225 0.9703 Correlation: (Intr) I(-3.5 I((-3.5)^2 I((-3.5)^3 I((z-3.5)^4) I(zeitn - 3.5) 0.071 I((zeitn - 3.5)^2) -0.465 0.000 I((zeitn - 3.5)^3)
Re: [R] need palette of topographic colors similar to topo.colors ()
I will second Roger's suggestion, colorRampPalette is a great function for
creating your own palettes. For example, Matlab's jet palette (also
available in fields package under peculiar name 'tim.colors') can be defined
by:
jet.colors = colorRampPalette(c(#7F, blue, #007FFF, cyan,
#7FFF7F, yellow, #FF7F00, red, #7F))
Other predefined functions for creating and managing color palettes that I
know of, are:
* R provides functions for creating palettes of continuous colors:
rainbow, topo.colors, heat.colors, terrain.colors.colors, gray
* tim.colors in package fields contains palette similar to Matlab's jet
palette (see examples for simpler implementation)
* rich.colors in package gplots contains two palettes of continuous
colors.
* Functions brewer.pal from RColorBrewer package and colorbrewer.palette
from epitools package contain tools for generating palettes
* rgb and hsv creates palette from RGB or HSV 3-vectors.
Maybe one of those will work for you.
Jarek
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
Sent: Saturday, January 07, 2006 3:10 PM
To: bogdan romocea
Cc: r-help
Subject: Re: [R] need palette of topographic colors similar to topo.colors()
On Sat, 7 Jan 2006, bogdan romocea wrote:
Dear useRs,
I got stuck trying to generate a palette of topographic colors that
would satisfy these two requirements:
- the pallete must be 'anchored' at 0 (just like on a map), with
light blue/lawn green corresponding to data values close to 0 (dark
blue to light blue for negative values, green-yellow-brown for
positive values)
- the brown must get darker for higher positive values.
topo.colors() fails both requirements and AFAICS lacks any options to
control its behavior.
#---unsatisfactory topo.colors() behavior
topoclr - function(tgt)
{
clr - topo.colors(length(tgt))
clr - clr[round(rank(tgt),0)]
plot(tgt,pch=15,col=clr)
}
par(mfrow=c(2,1)) ; topoclr(-50:50) ; topoclr(-20:80)
An acceptable solution would be something like this
grayclr - function(tgt)
{
tgt - sort(tgt) ; neg - which(tgt 0)
clrneg - gray(0:length(tgt[neg])/length(tgt[neg]))
clrpos - gray(length(tgt[-neg]):0/length(tgt[-neg]))
clr - c(clrneg,clrpos)
plot(tgt,pch=15,col=clr)
}
par(mfrow=c(2,1)) ; grayclr(-50:50) ; grayclr(-20:80)
if only I could make gray() use blue/brown instead of black (I tried a
couple of things but got stuck again).
Any suggestions?
Use colorRampPalette() to roll your own, or something better tuned,
perhaps catenating two ramps together.
Thank you,
b.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
--
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: [EMAIL PROTECTED]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Looking for packages to do Feature Selection and Classifi cation
Hi,
You should also check my msc.features.select from caMassClass package. It
has feature selection algorithm that I found useful in case of mass-spectra
data. It performs individual feature selection and/or removes highly
correlated neighbor features.
Jarek
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
Sent: Friday, January 06, 2006 3:12 PM
To: Weiwei Shi
Cc: Diaz.Ramon; r-help
Subject: Re: [R] Looking for packages to do Feature Selection and
Classification
Thanks. It's indeed an interesting paper. Besides RF (using Ramon's varSelRF
package), I am also testing Guyon et al's (2002) Recursive Feature
Elimination for my feature-selection part.
On 1/5/06, Weiwei Shi [EMAIL PROTECTED] wrote:
FYI:
check the following paper on svm (using libsvm) as well as random
forest in the context of feature selection.
http://www.csie.ntu.edu.tw/~cjlin/papers/features.pdf
HTH
On 1/4/06, Diaz.Ramon [EMAIL PROTECTED] wrote:
Dear Frank,
I expect you'll get many different answers since a wide variety of
approaches have been suggested. So I'll stick to self-advertisment: I've
written an R package, varSelRF (available from R), that uses random forest
together with a simple variable selection approach, and provides also
bootstrap estimates of the error rate of the procedure. Andy Liaw and
collaborators previously developed and published a somewhat similar
procedure. You probably also want to take a look at several packages
available from BioConductor.
Best,
R.
-Original Message-
From: [EMAIL PROTECTED] on behalf of Frank Duan
Sent: Wed 1/4/2006 4:23 AM
To: r-help
Cc:
Subject:[R] Looking for packages to do Feature Selection and
Classification
Hi All,
Sorry if this is a repost (a quick browse didn't give me the answer).
I wonder if there are packages that can do the feature selection and
classification at the same time. For instance, I am using SVM to
classify my
samples, but it's easy to get overfitted if using all of the features.
Thus,
it is necessary to select good features to build an optimum hyperplane
(?). Here is a simple example: Suppose I have 100 useful features and
100
useless features (or noise features), I want the SVM to give me the
same results when 1) using only 100 useful features or 2) using all 200
features.
Any suggestions or point me to a reference?
Thanks in advance!
Frank
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
--
Ramón Díaz-Uriarte
Bioinformatics Unit
Centro Nacional de Investigaciones Oncológicas (CNIO)
(Spanish National Cancer Center)
Melchor Fernández Almagro, 3
28029 Madrid (Spain)
Fax: +-34-91-224-6972
Phone: +-34-91-224-6900
http://ligarto.org/rdiaz
PGP KeyID: 0xE89B3462
(http://ligarto.org/rdiaz/0xE89B3462.asc)
**NOTA DE CONFIDENCIALIDAD** Este correo electrónico, y en
s...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
--
Weiwei Shi, Ph.D
Did you always know?
No, I did not. But I believed...
---Matrix III
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] trouble with extraction/interpretation of variance structure para meters from a model built using gnls and varConstPower
I have been using gnls with the weights argument (and varConstPower) to specify a variance structure for curve fits. In attempting to extract the parameters for the variance model I am seeing results I don't understand. When I simply display the model (or use summary on the model), I get what seem like reasonable values for both power and const. When I actually try to extract the values, I get the same number for the power, but a different (and less sensible) value for const. The simplest example I can come up with that shows the problem is as follows: #Set up data x= c(0,0,0,1,1,1,2,2,2,3,3,3,4,4,4,5,5,5,6,6,6,7,7,7); y0 = c(.1,.1,.1, .5,.5,.5, 1,1,1, 2,2,2, 4,4,4, 7,7,7, 9,9,9, 10,10,10); yp = c(0,.03,.05, 0,.05,.01, 0,.07,.03, .1,0,.2, .2,.1,0, .3,0,.1, 0,.3,.4, .3,.5,0); y= y0 + 4*yp; data = data.frame(x=x,y=y); #Run model library(nlme) model3 = try(gnls(y ~ SSfpl(x,A,B,xmid,scal),data=data,weights=varConstPower(const=1,power=0,form= ~fitted(.; #Examine results model3; #const = .6551298, power = .8913665 summary(model3);#const = .6551298, power = .8913665 coef(model3$modelStruct$varStruct)[power];#power = .8913665 coef(model3$modelStruct$varStruct)[const];#const = -0.4229219 coef.varFunc(model3$modelStruct$varStruct); #R can't seem to find this function, Splus can Any advice on what I am doing wrong would be appreciated. Hugh Rand Senior Scientist Amgen [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
On Mon, 9 Jan 2006, Michael Dewey wrote: Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. Very late last millenium, though. When I were young[er] we didn't have all these fancy yellow books. More seriously, yes, reading books about R and S is very effective and is how most of the R experts learned. In my case it was the Blue Book, the White Book, and the Ripley/Venables/Smith notes on S-plus (which have evolved to the Introduction to R). -thomas Ptolemy once asked [Euclid] if there was in geometry any shorter way that that of the Elements, and he replied that there was no royal road to geometry. Proclus (410-485 CE) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] decide between polynomial vs ordered factor model (lme)
On 1/9/06, Leo Gürtler [EMAIL PROTECTED] wrote: Dear alltogether, two lme's, the data are available at: http://www.anicca-vijja.de/lg/hlm3_nachw.Rdata explanations of the data: nachw = post hox knowledge tests over 6 measure time points (= equally spaced) zeitn = time points (n = 6) subgr = small learning groups (n = 28) gru = 4 different groups = treatment factor levels: time (=zeitn) (n=6) within subject (n=4) within smallgroups (=gru) (n = 28), i.e. n = 4 * 28 = 112 persons and 112 * 6 = 672 data points library(nlme) fitlme7 - lme(nachw ~ I(zeitn-3.5) + I((zeitn-3.5)^2) + I((zeitn-3.5)^3) + I((zeitn-3.5)^4)*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) fit5 - lme(nachw ~ ordered(I(zeitn-3.5))*gru, random = list(subgr = ~ 1, subject = ~ zeitn), data = hlm3) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) anova( update(fit5, method=ML), update(fitlme7, method=ML) ) Model df AIC BIClogLik Test update(fit5, method = ML)1 29 2535.821 2666.619 -1238.911 update(fitlme7, method = ML) 2 16 2529.719 2601.883 -1248.860 1 vs 2 L.Ratio p-value update(fit5, method = ML) update(fitlme7, method = ML) 19.89766 0.0978 shows that both are ~ equal, although I know about the uncertainty of ML tests with lme(). Both models show that the ^2 and the ^4 terms are important parts of the model. My question is: - Is it legitimate to choose a model based on these outputs according to theoretical considerations instead of statistical tests that not really show a superiority of one model over the other one? - Is there another criterium I've overlooked to decide which model can be clearly preferred? - The idea behind that is that in the one model (fit5) the second contrast of the factor (gru) is statistically significant, although not the whole factor in the anova output. In the other model, this is not the case. Theoretically interesting is of course the significance of the second contrast of gru, as it shows a tendency of one treatment being slightly superior. I want to choose this model but I am not sure whether this is proper action. Both models shows this trend, but only one model clearly indicates that this trend bears some empirical meaning. Thanks for any suggestions, The comparisons may be more clearly shown if you create the ordered factor and a second version of the ordered factor what has the contrasts set so it produces a 4th order polynomial. That is, set hlm3$ozeit - ordered(hlm3$zeitn) hlm3$ozeit4 - C(hlm3$ozeit, contr.poly, 4) then define one model in terms of ozeit and a second model in terms of ozeit4. I would go further and create a new binary factor from gru that contrasted level 2 against the other three levels and use that instead of gru. For a model fit by lme I would use the one-argument form of anova to assess the significance of terms in the fixed effects. (That advice doesn't hold for models fit by lmer - at least at present.) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] How to use filled.contour(x,y,z) data for levelplot(z)?
Jan, libary(lattice) rownames(zz) - xx colnames(zz) - yy levelplot(zz) will not work -- levelplot needs a data frame with zz, xx and yy values next to each other, so read about data.frame(), rep() and as.vector(zz); you will need the each= argument for one of xx or yy. Sounds like you'd be helped by using package sp, see also http://r-spatial.sourceforge.net/ and look for the graph gallery, function spplot. -- Edzer __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
On 1/9/06, Thomas Lumley [EMAIL PROTECTED] wrote: On Mon, 9 Jan 2006, Michael Dewey wrote: Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. Very late last millenium, though. When I were young[er] we didn't have all these fancy yellow books. More seriously, yes, reading books about R and S is very effective and is how most of the R experts learned. In my case it was the Blue Book, the White Book, and the Ripley/Venables/Smith notes on S-plus (which have evolved to the Introduction to R). In addition to books, the various manuals, contributed documents and mailing list archives, all of which one should review, the key thing to do if you want to really learn R is to read source code and lots of it. I think there is no other way. Furthermore, the fact that you can do this is really a key advantage of open source. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] [R-pkgs] sudoku
I replied all to the original message, but since that was to
[EMAIL PROTECTED] it might not have gone out there, did it?
If not, below is my reply again. [You have restrict the
randomization so that you permute within and between block rows/columns.]
/Henrik
Original Message
Subject: Re: [R] [R-pkgs] sudoku
Date: Sat, 07 Jan 2006 09:36:54 +1100
From: Henrik Bengtsson [EMAIL PROTECTED]
To: Brahm, David [EMAIL PROTECTED]
CC: [EMAIL PROTECTED]
References:
[EMAIL PROTECTED]
Brahm, David wrote:
Any doubts about R's big-league status should be put to rest, now that
we have a
Sudoku Puzzle Solver. Take that, SAS! See package sudoku on CRAN.
The package could really use a puzzle generator -- contributors are
welcome!
Last summer I put a quick generator together after discussing with some
friends how these games a generate (and enumerated). I don't know if it
is a correct/complete generator, but consider an empty game with 3x3
grids each with 3x3 cells. Create the initial board by adding 1:9 in
the first row, the c(2:9,1), in the second and so on, to make sure you
have one correct board. From this you can now generate all(?) other
possible boards by permuting rows and columns. You can for instance use
a random seed enumerate all such boards. Finally, you want to remove
some of cells, which you also can by sampling using known random seeds.
See attached code. Example:
source(Sudoku.R)
Sudoku$generate()
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
[1,]1 NA34 NA NA NA8 NA
[2,]4 NA NA NA8 NA NA NA NA
[3,] NA8 NA1 NA3456
[4,]2 NA NA NA NA NA NA NA1
[5,] NA67 NA NA NA2 NA4
[6,]8 NA NA NA NA NA NA6 NA
[7,] NA NA5 NA NA89 NA NA
[8,]6 NA891 NA3 NA NA
[9,] NA1 NA3 NA NA NA78
Sudoku$generate(1)
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
[1,]3 NA25 NA NA NA9 NA
[2,]9 NA NA NA3 NA NA NA NA
[3,] NA4 NA8 NA7231
[4,]2 NA NA NA NA NA NA NA6
[5,] NA34 NA NA NA1 NA9
[6,]8 NA NA NA NA NA NA5 NA
[7,] NA NA9 NA NA26 NA NA
[8,]7 NA691 NA3 NA NA
[9,] NA2 NA6 NA NA NA18
Sudoku$generate(2)
[,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9]
[1,]7 NA61 NA NA NA2 NA
[2,]1 NA NA NA3 NA NA NA NA
[3,] NA2 NA7 NA5981
[4,]8 NA NA NA NA NA NA NA5
[5,] NA91 NA NA NA7 NA8
[6,]5 NA NA NA NA NA NA9 NA
[7,] NA NA5 NA NA72 NA NA
[8,]9 NA832 NA5 NA NA
[9,] NA1 NA6 NA NA NA79
/Henrik
-- David Brahm ([EMAIL PROTECTED])
[[alternative HTML version deleted]]
___
R-packages mailing list
[EMAIL PROTECTED]
https://stat.ethz.ch/mailman/listinfo/r-packages
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
roger bos wrote:
As far as generating a sudoku, it can't be too hard because I have a program
on my cell phone that does it with a size less than 325K. I don't know the
best way to generate these, but one way I was thinking of was starting with
a filled up one then randomize the columns and rows. Then make some of them
blank. The cell-phone version often generates puzzles that have non-unique
solutions. Though I admit this is sometimes annoying, it also can make the
puzzle harder.
Thanks,
Roger
On 1/9/06, Martin Maechler [EMAIL PROTECTED] wrote:
First, thanks a lot! to David Brahms for finally tackling this
important problem, and keeping the R language major league !
;-) :-) {but the thanks! is meant seriously!}
Detlef == Detlef Steuer [EMAIL PROTECTED]
on Sun, 8 Jan 2006 12:21:52 +0100 writes:
Detlef Hey, you spoiled my course! :-)
Detlef I planned using this as an excersise. Alternative
Detlef ideas anyone ...
Well, you could *add* to it:
1) When I have been thinking about doing this myself (occasionally
in the past weeks), I had always thought that finding *ALL*
solutions was a very important property of the algorithm I would
want to design.
(since this is slightly more general and useful than proofing
uniqueness which the current algorithm does not yet do anyway).
2) The current sudoku() prints the result itself and returns a
matrix; improved, it should return an object of class sudoku,
with a print() and a plot()
Re: [R] Missing value representation in Excel before extraction to R with RODBC
Dear list, Well, those columns in Excel that starts with NA (actually 8 NA's in my case) is imported as all NA in R but if the columns starts with at least 3 cells with values (i.e not NA) the are imported correctly to R. When as.is=TRUE is used a simular conversion takes place but now as all NA and dates are represented as date-and-time. Is there any way to get this correct even when the Excel columns start with several NA's? Sincerely Fredrik - Original Message - From: Prof Brian Ripley [EMAIL PROTECTED] To: Petr Pikal [EMAIL PROTECTED] Cc: Fredrik Lundgren [EMAIL PROTECTED]; R-help r-help@stat.math.ethz.ch Sent: Monday, January 09, 2006 9:36 AM Subject: Re: [R] Missing value representation in Excel before extraction to R with RODBC On Mon, 9 Jan 2006, Petr Pikal wrote: Hi I believe it has something to do with the column identification decision. When R decides what is in a column it uses only some values from the beginning of a file. Not R, Excel. Excel tells ODBC what the column types are. I do not use RODBC as read.delim(clipboard, ...) is usually more convenient but probably there is a way how to tell RODBC what is in the column instead of let R decide from the top of the file. Using as.is=TRUE stops RODBC doing any conversion. But I may be completely mistaken. HTH Petr On 6 Jan 2006 at 20:47, Fredrik Lundgren wrote: From: Fredrik Lundgren [EMAIL PROTECTED] To: R-help r-help@stat.math.ethz.ch Date sent: Fri, 6 Jan 2006 20:47:29 +0100 Subject:[R] Missing value representation in Excel before extraction to R with RODBC Dear list, How should missing values be expressed in Excel before extraction to R via RODBC. I'm bewildered. Sometimes the representation with NA in Excel appears to work and shows up in R as NA but sometimes the use of NA in Excel changes the whole vector to NA's. Blank or nothing or NA as representation for missing values in Excel with dateformat gives NA's of the whole vector in R but with general format in Excel gives blanks for missing values in R. How should I represent missing values in Excel? Best wishes and thanks for any help Fredrik Lundgren -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] two y-axis in xy-plot
On 1/9/06, Antje Schüle [EMAIL PROTECTED] wrote: Hi there, I am wondering if it is possible to do an xyplot with two y-axes. I'd like to print two parameters in a time series but they both have different scales. Which parameter in xyplot can I add to achieve this result? The answer depends on the details of what you are doing, so please provide us with a reproducible example. Deepayan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] warning message from nlme
Hi all, I tried to do a variance components using nlme, but I got the following warning mesage # not meaningful for factors in: Ops.factor(y[revOrder], Fitted) ## Can someone point out what is the meaning of this warning message? I tried to look at Ops.factor, but I don't understand it since I'm relatively new to R. Thanks. Yen Lin [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] warning message from nlme
Hi all, Sorry for the sloppy description of problem. I have a dataset called dense. I want to decompose the variability/variation into different components such as wafer, axis, orientation and data. These variables are all categorical data. I converted axis, orientation and location into factors before I ran the analysis: lme(Data~1,random=~1|Wafer/axi/ori/loc,data=Dense) The algorithm returns the standard deviation of each random effect, but also gives the warning message: Warning message: - not meaningful for factors in: Ops.factor(y[revOrder], Fitted) I wonder what does this warning message mean? If the factors are not meaningful, how can I find out which factors the warning message is referring to? Thanks. Yen Lin -Original Message- From: Berton Gunter [mailto:[EMAIL PROTECTED] Sent: Monday, January 09, 2006 9:34 AM To: Chia, Yen Lin Subject: RE: [R] warning message from nlme Can someone point out what is the meaning of this warning message? I tried to look at Ops.factor, but I don't understand it since I'm relatively new to R. Thanks. No. **Read the posting guide** and provide sufficient details in your post so that an answer can be given. -- Bert __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
To avoid spam on the R wikis pages: If we assume that anyone who we would want to be empowered to modify the R wiki pages is an R-user, would it be possible to somehow incorporate a function into the next R release which provides a user with a key/password? A new R function would generate a day-of-the year dependent key: if you want to modify an R wiki page you need to enter the key for that day (This is not a proposal to make keys user specific: every R user worldwide would have the same key each day). Then only a person who has installed R would be able to run the function to get a key to modify R wiki pages. Of course anyone could read the wikis. I supposed that if we wanted, that the key provided could somehow encode the O/S and R version being run, and then the wiki page modified would note which O/S and version the annotator is running, however for ease of use I suggest that the key generated each day be short for simplicy in typing it in. I suppose a more complex solution would be for an R function to make a call to open a web-browser with a cookie or something set which thus allows the user to modify R wiki pages. Leif Kirschenbaum Senior Yield Engineer Reflectivity, Inc. (408) 737-8100 x307 [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
On Mon, 9 Jan 2006, Gabor Grothendieck wrote: On 1/9/06, Thomas Lumley [EMAIL PROTECTED] wrote: On Mon, 9 Jan 2006, Michael Dewey wrote: Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. Very late last millenium, though. When I were young[er] we didn't have all these fancy yellow books. More seriously, yes, reading books about R and S is very effective and is how most of the R experts learned. In my case it was the Blue Book, the White Book, and the Ripley/Venables/Smith notes on S-plus (which have evolved to the Introduction to R). In addition to books, the various manuals, contributed documents and mailing list archives, all of which one should review, the key thing to do if you want to really learn R is to read source code and lots of it. I think there is no other way. Furthermore, the fact that you can do this is really a key advantage of open source. There has to be some reason to dig into the source code. Just starting at line 1 and reading until you are enlightened would be frustrating, repetetive, and nearly pointless. The great benefits of the R books is that they have interesting results (a fancy graph, analysis, or report) that you can trace back to the constituent parts and (with open source code) learn everything you want to and be confident that the rest is there if you need it. Books using R do an excellent job of showing what is possible and, through recursive study of the open source code, how to do it. Books connect high-level tasks to low-level functions. R has plenty of documentation, but if the measure of excellence is simply number of pages or weight, SAS's documentation might still win even if we include the pages of R source code. Both packages have lots of detailed documentation, where if you understood everything that was written, you'd know how to do what you want. The authors of neither R nor SAS have failed to document their functions. Where I think the R (and SAS) documentation is lacking is in the connections between the documentation elements. RTFM isn't helpful if you can't find TFM. For instance, there is more than one way to make a graph, (see http://addictedtor.free.fr/graphiques/thumbs.php?sort=package for 135 of them) how does a novice know which function to use? How do you find out the alternate ways to do things? The hateful MS Excel solves this by registering the alternate graphic capabilities under a hierarchical GUI menu. We solve it with an email list and several fuzzy searches. Since R has such an extensive set of extensions, maybe we need a section in the R-intro documentation near http://cran.r-project.org/doc/manuals/R-intro.html#Writing-your-own-functions titled Finding existing functions. It could explain the difference between base and recommended, installed, CRAN, and how someone can find and use things in these areas using help(), '?', help.search(), help.start(), RSiteSearch(), and the mailing lists. Dave -- Dr. David Forrest [EMAIL PROTECTED](804)684-7900w [EMAIL PROTECTED] (804)642-0662h http://maplepark.com/~drf5n/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] R newbie example code question
Sometimes I print out a package
and read about it and there
are sometimes nice examples
that I would like to run myself.
Is there a way to bring them
into R from the package or
are they only meant to be typed
in manually ? If manual is the
only way, that's fine. I was
just checking whether there was
a quicker way. Thanks.
Mark
**
This email and any files transmitted with it are confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
Michael Dewey wrote: At 20:12 08/01/06, Jack Tanner wrote: My hypothesis is that the basic reason that people ask questions on R-help rather than first looking elsewhere is that looking elsewhere doesn't get them the info they need. People think in terms of the tasks they have to do. The documentation for R, which can be very good, is organized in terms of the structure of R, its functions. This mismatch -- people think of tasks, the documentation thinks in functions -- causes people to turn to the mailing list. Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. I certainly agree about the value of books. After struggling with lme/glmmPQL documentation for a while, I found a copy of MASS, and it's been nothing short of illuminating. Gabor Grothendieck ggrothendieck at gmail.com wrote: In addition to books, the various manuals, contributed documents and mailing list archives, all of which one should review, I do not wish to disparage all these valuable resources. But it is apparent that they do not answer the (real or perceived) needs of those who ask the same more or less basic questions over and over on R-help. It doesn't help if one, or ten, or hundreds of newbies are told -- go thee and RTFM, because, by definition, there will be other newbies (presumably, until the entire human race consists of R experts). the key thing to do if you want to really learn R is to read source code and lots of it. I think there is no other way. Furthermore, the fact that you can do this is really a key advantage of open source. Absolutely, the R sources are the highest fidelity representation of the knowledge on R. But there's also knowledge about the sources, e.g., why a particular function was coded that way, and why one would want to use that function over others that seem similar. The wiki proposal is thus twofold: first, to take the key advantage of open source, and apply it not only to the code, but to the knowledge about the code as well. Second, to structure the experience of learning and using R such that the wiki is very prominent. Unfortunately, the site is down at the moment, but there's a really good example of how wikified, task-oriented documentation can help an open source project: http://codex.wordpress.org/Main_Page . __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R newbie example code question
Mark Leeds wrote:
Sometimes I print out a package
and read about it and there
are sometimes nice examples
that I would like to run myself.
Is there a way to bring them
into R from the package or
are they only meant to be typed
in manually ? If manual is the
only way, that's fine. I was
just checking whether there was
a quicker way. Thanks.
See (you won't believe it): ?example
Uwe Ligges
Mark
**
This email and any files transmitted with it are confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R newbie example code question
wow. example() was exactly what
I wanted. you all have made all these
incredible facilities
for a new person. thanks.
mark
-Original Message-
From: Uwe Ligges [mailto:[EMAIL PROTECTED]
Sent: Monday, January 09, 2006 1:30 PM
To: Mark Leeds
Cc: R-Stat Help
Subject: Re: [R] R newbie example code question
Mark Leeds wrote:
Sometimes I print out a package
and read about it and there
are sometimes nice examples
that I would like to run myself.
Is there a way to bring them
into R from the package or
are they only meant to be typed
in manually ? If manual is the
only way, that's fine. I was
just checking whether there was
a quicker way. Thanks.
See (you won't believe it): ?example
Uwe Ligges
Mark
**
This email and any files transmitted with it are
confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
**
This email and any files transmitted with it are confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R newbie example code question
Mark,
I am not user where you find your reading material, but if it is online,
perhaps you can copy and paste it into an R session.
John
John Sorkin M.D., Ph.D.
Chief, Biostatistics and Informatics
Baltimore VA Medical Center GRECC and
University of Maryland School of Medicine Claude Pepper OAIC
University of Maryland School of Medicine
Division of Gerontology
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
410-605-7119
- NOTE NEW EMAIL ADDRESS:
[EMAIL PROTECTED]
Mark Leeds [EMAIL PROTECTED] 1/9/2006 1:20 PM
Sometimes I print out a package
and read about it and there
are sometimes nice examples
that I would like to run myself.
Is there a way to bring them
into R from the package or
are they only meant to be typed
in manually ? If manual is the
only way, that's fine. I was
just checking whether there was
a quicker way. Thanks.
Mark
**
This email and any files transmitted with it are confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] repeat { readline() }
Use tryCatch; try behaves the way it does with respect to interrupts
for historical compatibility.
luke
On Sun, 8 Jan 2006, hadley wickham wrote:
On a related note, does anyone know how to exit:
repeat { try( readline() ) }
The try block captures Ctrl-C.
Hadley
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
--
Luke Tierney
Chair, Statistics and Actuarial Science
Ralph E. Wareham Professor of Mathematical Sciences
University of Iowa Phone: 319-335-3386
Department of Statistics andFax: 319-335-3017
Actuarial Science
241 Schaeffer Hall email: [EMAIL PROTECTED]
Iowa City, IA 52242 WWW: http://www.stat.uiowa.edu
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] warning message from nlme
Yen Lin: I'd like to try and offer a little help, but I'm still unclear on your data structure and problem. You say, they are all categorical variables. But, does this apply also to your dependent variable? If so, lme is the wrong function to use. You also say you want to decompose tha variation into wafer, axis, orientation and data. But then, what is loc. Do you mean you want to decompose the variation in data, your DV, into multiple components including wafer, axis, orientation and loc? Maybe if you can take some time to clarify your data structure in more detail and why your lme call is structured as it is it might be easier to help. Harold -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Chia, Yen Lin Sent: Monday, January 09, 2006 12:42 PM To: Berton Gunter Cc: r-help@stat.math.ethz.ch Subject: Re: [R] warning message from nlme Hi all, Sorry for the sloppy description of problem. I have a dataset called dense. I want to decompose the variability/variation into different components such as wafer, axis, orientation and data. These variables are all categorical data. I converted axis, orientation and location into factors before I ran the analysis: lme(Data~1,random=~1|Wafer/axi/ori/loc,data=Dense) The algorithm returns the standard deviation of each random effect, but also gives the warning message: Warning message: - not meaningful for factors in: Ops.factor(y[revOrder], Fitted) I wonder what does this warning message mean? If the factors are not meaningful, how can I find out which factors the warning message is referring to? Thanks. Yen Lin -Original Message- From: Berton Gunter [mailto:[EMAIL PROTECTED] Sent: Monday, January 09, 2006 9:34 AM To: Chia, Yen Lin Subject: RE: [R] warning message from nlme Can someone point out what is the meaning of this warning message? I tried to look at Ops.factor, but I don't understand it since I'm relatively new to R. Thanks. No. **Read the posting guide** and provide sufficient details in your post so that an answer can be given. -- Bert __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
On 1/9/06, Jack Tanner [EMAIL PROTECTED] wrote: Michael Dewey wrote: At 20:12 08/01/06, Jack Tanner wrote: My hypothesis is that the basic reason that people ask questions on R-help rather than first looking elsewhere is that looking elsewhere doesn't get them the info they need. People think in terms of the tasks they have to do. The documentation for R, which can be very good, is organized in terms of the structure of R, its functions. This mismatch -- people think of tasks, the documentation thinks in functions -- causes people to turn to the mailing list. Further to that I feel that (perhaps because they do not like to blow their own trumpet too much) the authors of books on R do not stress how much most questioners could gain by buying and reading at least one of the many books on R. When I started I found the free documents useful but I made most progress when I bought MASS. I do realise that liking books is a bit last millennium. I certainly agree about the value of books. After struggling with lme/glmmPQL documentation for a while, I found a copy of MASS, and it's been nothing short of illuminating. Gabor Grothendieck ggrothendieck at gmail.com wrote: In addition to books, the various manuals, contributed documents and mailing list archives, all of which one should review, I do not wish to disparage all these valuable resources. But it is apparent that they do not answer the (real or perceived) needs of those who ask the same more or less basic questions over and over on R-help. It doesn't help if one, or ten, or hundreds of newbies are told -- go thee and RTFM, because, by definition, there will be other newbies (presumably, until the entire human race consists of R experts). I certainly was not disparaging books. I said _in addition to_ books, not _insted of_. The reason I pointed this out is that I think most people already read the books. What many people don't do as far as can tell is read the code. Obviously if you are just starting out you are going to be relying on the documentation, books, etc. but once you get past the intro stage you need to get into code. One repeatedly sees questions on this list where just a minute or two spent with the code would have answered the question. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] product of multidimensional tables
Hi, I am trying to carry out the product between two multi dimensional tables, e.g. A with dim = c(2,2,3,4) and B with dim = c(2,3,4). So, I want to outer multiply each 3x4 table in A[i,j,,] with B[k,,] to get a table C of dim = c(2,2,3,4,3,4). This arises in scenario of conditional probability tables. A could be a table taking probability values for different values of variables s,t,u,v and B taking values for different values of variables t,p,q. I want to get a table of factor (different from the factor in R) got by multiplying these two CPTs. The new table C will have dimensions (variables) s,t,u,v,p,q as a result of product of these two. I am looking at the apply() method as an aid to get this done. But, it seems that I can't get a multidimensional output by applying any FUN funtion in apply(X, MARGIN, FUN, ...). for instance a outer product of two vectors gives back another vector and not a 2 dimensional array. So, any thoughts on this? Any other place I should be looking at? Thanks, Nachi [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] kein Betreff
Hallo, I´m trying to find out how I can start WinEdt always directly when R is started. Does anybody know how to do so? I tried to find it out by myself but had no fortune. Maybe you have to compile (?) a certain file. (I am usind R in the latest version on Win XP) Thank You Stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] automatic start of RWinEdt
stefan semmelring [EMAIL PROTECTED] schrieb am 09.01.06 21:31:01: Hallo, I´m trying to find out how I can start WinEdt always directly when R is started. Does anybody know how to do so? I tried to find it out by myself but had no fortune. Maybe you have to compile (?) a certain file. (I am usind R in the latest version on Win XP) Thank You Stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] brown, durbin , evans ( 1975 )
Does anyone know where
I can get R code for plotting
the Brown , Durbin
and Evans cumsum
procedure ( 1975 ) ?
I wrote my own code but
I am a little worried
that my confiodence bands
may not be correct ( I find the formula
in the original paper confusing and S+Finmetrics
has a formula but that formula implies that
there should be 4 lines as far as I can tell ) so
I would like to see someone
else's code also if it's out
there ? Thanks.
Mark
P.S : Strucchange looks like a great package but
it would take me way longer than I
have to only partially understand the theory behind
what is going on there.
**
This email and any files transmitted with it are confidentia...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] paste tab and print
Prof Brian Ripley a écrit : cat(info, \n) Thank you very much. It works. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] bug in either glmmPQL or lme/lmer
I know it's conventional to report bugs to the maintainer, but I'm not sure
which package actually contains this bug(s), so I apologize for sending this
to the list at large. I see the bug under both R 2.1.1, and R 2.2.1. (I sent
a related message a while ago, but this one has more detail.)
library(MASS)
library(nlme)
fit.model - function(il, model.family) {
cs - Initialize(corSymm(form=~1|id), data=il)
glmmPQL(score~test+coder, random=~1|id, family=model.family, data=il,
correlation=cs)
}
score -
c(1,8,1,3,4,4,2,5,3,6,0,3,1,5,0,5,1,11,1,2,4,5,2,4,1,6,1,2,8,16,5,16,3,15,3,12,4,9,2,4,1,8,2,6,4,11,2,9,3,17,2,6)
id - rep(1:13, rep(4, 13))
test - gl(2, 1, length(score), labels=c(pre, post))
coder - gl(2, 2, length(score), labels=c(two, three))
original - data.frame(id, score, test, coder)
sorted.ok - original[order(original$id, original$score, original$test,
original$coder),]
sorted2.ok - original[order(original$id, original$test, original$score,
original$coder),]
sorted3.not.ok - original[order(original$score, original$id, original$test,
original$coder),]
print(summary(fit.model(original, poisson)))
print(summary(fit.model(sorted.ok, poisson)))
print(summary(fit.model(sorted2.ok, poisson)))
print(summary(fit.model(sorted3.not.ok, poisson)))
That last line produces, under R version 2.1.1, 2005-06-20, i386-pc-mingw32
attached base packages:
[1] methods stats graphics grDevices utils datasets
[7] base
other attached packages:
MASS nlme
7.2-20 3.1-65
iteration 1
Error in logLik.reStruct(object, conLin) :
NA/NaN/Inf in foreign function call (arg 3)
That same last line produces, under R version 2.2.1, 2005-12-20,
i386-pc-mingw32
attached base packages:
[1] methods stats graphics grDevices utils datasets
[7] base
other attached packages:
MASS nlme
7.2-24 3.1-68.1
iteration 1
Error in lme.formula(fixed = zz ~ test + coder, random = ~1 | id, data =
list( :
false convergence (8)
Moreover, summary(fit.model(original, poisson)) produces a different output
than either
summary(fit.model(sorted.ok, poisson)) or summary(fit.model(sorted2.ok,
poisson)), but the latter two do equal each other.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Wikis etc.
On Monday 09 January 2006 11:31, Gabor Grothendieck wrote: . . . I certainly was not disparaging books. I said _in addition to_ books, not _insted of_. The reason I pointed this out is that I think most people already read the books. What many people don't do as far as can tell is read the code. Obviously if you are just starting out you are going to be relying on the documentation, books, etc. but once you get past the intro stage you need to get into code. One repeatedly sees questions on this list where just a minute or two spent with the code would have answered the question. Gabor, The issue IS the INTRO stage though, in fact well beyond the intro stage. Reading the code is well and good for a programmer, but many are not and never will be coders, and this group is going to continue to expand. Even an advanced statistician migrating from a proprietary system like SPSS to R is going to need documentation. They would not even know where in the code to look! Code is cool, but it really isn't expository. John __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] wicked wikis for R
On Monday 09 January 2006 05:16, Jean-Christophe BOUETTE wrote: From: Arin Basu [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Date: 8 Jan 2006 19:18:17 - Subject: [R] wicked wikis for R Message: 41 Date: Sun, 08 Jan 2006 13:52:33 +1100 From: paul sorenson [EMAIL PROTECTED] Subject: Re: [R] Wikis etc. To: Frank E Harrell Jr [EMAIL PROTECTED], r-help r-help@stat.math.ethz.ch -snip- Among others, here's one long-term benefit for the newbies. Instead of people getting admonished/thrashed with harsh expressions/advices like go see the mailing list publishing etiquettes, or you should search the archives and help files, and read all manuals, and ask others first before posting here... (which can turn away many a newcomer from posting or using the mailing list or using R for that matter), wiki could make life a little easy for newbies/less experienced who could then receive more polite one liners like, please check the wikipages..., or solution #xyz in the wikipages for the solution. Sorry, I don't get the point here. Some people will keep feeling offensed when they're just told to read the man/wiki pages, and others will simply change their answers from RTFM to RTFW. Nobody can force people into reading the manuals, or reading the posting guide. This is definitely one problem that the wiki will not solve. The real issue is indexing and cross-referencing. Quite often requestors HAVE tried the manuals, but without a real clue about where to look, that can be unproductive. On the other hand, being pulled up short and Ripleyed can have a salutary effect on analyzing the problem first and researching carefully before posting a clueless query. You could see as a useful part of the learning process. JD __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] automatic start of RWinEdt
the readme file tells what you should do: - In R use something like (for example in your .Rprofile): options(editor=\c:/program files/winedt team/winedt/winedt\ -c=\R-WinEdt-edit\ -e=r.ini -V) options(pager=\c:/program files/winedt team/winedt/winedt\ -C=\R-WinEdt\ -e=r.ini -V) Used WinEdt parameters (Remark: There is a difference between -c and -C !): -c=name: New instance of WinEdt called name will be started. -C=name: If an instance name of WinEdt is already running, it will be used. So you can run WinEdt as LaTeX and R editor at the same time. -e=name: Using name as initialization-file. -V : Running in virgin-mode Examples: ## Recommended procedure: ## Open WinEdt with something like: c:\program files\winedt team\winedt\winedt -C=R-WinEdt -e=r.ini ## i.e. ideally the shortcut you have already created. ## ## Then create a new document and write an R function. ## Click on the symbol R source or press ALT+S. ## You will be asked to specify a filename (e.g. R-prog1.R). ## If RGui is running, it will be focussed and source(.) will be called. ## options(pager=\c:/program files/winedt team/winedt/winedt\ -C=\R-WinEdt\ -e=r.ini -V) file.show(.Rhistory) ## Mark some lines, click the R paste button or use Alt+P as shortcut: ## Marked lines will be executed in RGui. ## ## The following way to edit function is possible, but *not* recommended: options(editor=\c:/program files/winedt team/winedt/winedt\ -c=\R-WinEdt-edit\ -e=r.ini -V) my.legend - legend fix(my.legend) 2006/1/10, stefan semmelring [EMAIL PROTECTED]: stefan semmelring [EMAIL PROTECTED] schrieb am 09.01.06 21:31:01: Hallo, I´m trying to find out how I can start WinEdt always directly when R is started. Does anybody know how to do so? I tried to find it out by myself but had no fortune. Maybe you have to compile (?) a certain file. (I am usind R in the latest version on Win XP) Thank You Stefan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- 黄荣贵 Deparment of Sociology Fudan University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] How to plot legend to the margin area of the graph?
Dear R-helpers, When plotting a graph, what command should I use to mark legend to the margin area of that graph? __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] lmer with nested/nonnested groupings?
I'm trying to figure out how to use lmer to fit models with factors that have some nesting and some non-nested groupings. For example, in this paper: http://www.stat.columbia.edu/~gelman/research/published/parkgelmanbafumi.pdf we have a logistic regression of survey respondents' political preferences (1=Republican, 0=Democrat), regressing on sex, ethnicity, state (51 states within 5 regions), 4 age categories, and 4 education categories. I'd like to include states (nested within regions), and also age, education, and age x education. (That is, 5 batches of varying coefs: 50 states, 5 regions, 4 age categories, 4 education categories, and 16 age x education categories.) The age x education factor is kinda tricky because it's connected both to age and to education. I'm thinking of a model like this: lmer (y ~ black*female + (1 | state) + (1 | region) + (1 | age) + (1 | edu) + (1 | age.edu), family=binomial(link=logit)) (Here, I'm thinking of age.edu as a variable with 16 levels.) Anyway, it blows up when i try to put in these nested things. I read Doug Bates's article in R-news and there seems to be a way of doing nested groupings (unfortunately, I can't quite figure out how to do it), but I don't see any references to situations such as age, edu, and age*edu . For the article, we used Bugs, which is fine, but I'd like to see how far I can take it using lmer. I could kludge it by, for example, including age, edu, and region as unmodeled factors: lmer (y ~ black*female + (1 | state) + factor(region) + factor(age) + factor(edu) + (1 | age.edu), family=binomial(link=logit)) but I'd like to do the full multilevel version. Thanks! Andrew -- Andrew Gelman Professor, Department of Statistics Professor, Department of Political Science [EMAIL PROTECTED] www.stat.columbia.edu/~gelman Tues, Wed, Thurs: Social Work Bldg (Amsterdam Ave at 122 St), Room 1016 212-851-2142 Mon, Fri: International Affairs Bldg (Amsterdam Ave at 118 St), Room 711 212-854-7075 Mailing address: 1255 Amsterdam Ave, Room 1016 Columbia University New York, NY 10027-5904 212-851-2142 (fax) 212-851-2164 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] wiki in Hamburg set read-only
Hi, to clear up the situation regarding wikis a bit and since, whatever happens, Philippe's wiki is superior, I decided to set the old wiki read-only. A visitor will be asked to visit the new wiki and add contents there. Good luck Philippe! Your plans sound very nice! The new wiki should get visibly mentioned on the R frontpage, so that especially beginners have a good chance to find it. Let's add content! Detlef __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] brown, durbin , evans ( 1975 )
Mark: Does anyone know where I can get R code for plotting the Brown , Durbin and Evans cumsum procedure ( 1975 ) ? Via library(strucchange) P.S : Strucchange looks like a great package but it would take me way longer than I have to only partially understand the theory behind what is going on there. Come on, it's not that difficult, e.g., for detecting the mean shift in plot(Nile) you can apply BDE's Recursive CUSUM test via rcus - efp(Nile ~ 1, type = Rec-CUSUM) plot(rcus) which shows quite clearly the structural change that occured in 1898 after the Ashwan dam was built. You can get test statistic and p-value via sctest(rcus) See the package vignette and the man pages for more examples. As I already told you privately, a lot of research was done after BDE 1975 and the test is not the most suitable in various situations. For example, it can perform quite badly in the presence of multiple shifts or shifts that occur late in the sample period. Best, Z __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to plot legend to the margin area of the graph?
Vincent Deng wrote: Dear R-helpers, When plotting a graph, what command should I use to mark legend to the margin area of that graph? Example: plot(1:10) par(xpd=TRUE) legend(8,11.5,Hello World) Uwe Ligges __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
