[R] surface plot

[Divya Alice Varkey]

Hi,

 

I have been trying to make a surface plot using R - I came across
functions like plot.surface, surface but I could not use these functions
as they seem to be in FOO package which I cannot load. I also want to
make a plane that fits the surface plot.

Can anyone help?

 

divya


[[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
and provide commented, minimal, self-contained, reproducible code.

[R] multiple x-axis labels on plot

[t.d. kaplan]

hi,

how can i set multiple x-axis labels on a plot? in effect, i want
to set 2 x-axis labels and values on the tick marks. is it possible
to have one running on the bottom (as is the default) and another
running across the top of a plot?

like:

xlab-1
-
|   |
|   |
-
xlab-0


thanks.

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] help on determining operating system

[Mihalis Tsoukalos]

On Tue 12 Dec 2006, at 06:40 , LU YING wrote:

> Dear list,
>
> I am an R user and I also write my own package in R(sometime i need to
> write  in C), and right now i am thinking about buying a new
> workstation--and i am trying to decide if i should get
> a mac with OS X or a linux machine (for example Dell).
>
> I have experience using R on linux (but i have been just a user and  
> never
> been a admin) but i am hesitating of managing a linux system on my own
> (btw I would like to have my new workstation to be used as a  
> server), so
> right now I am leaning toward of buying a Mac Pro. But from the  
> website,
> it sounds like R doesnt work quite well with Mac operating system
> yet...so I was wondering if anybody here have any experiences of
> using/developing R package on a Mac machine? Is it smooth enough?
>
> (oh by the way, i am not a Mac user yet, Windows has been the primary
> operating system that i used, but after hearing many good things
> of OS X, I am really interested in switching over.)
>
> any suggestions are appreciated!
>
> Ying

Hi Ying.

I am using R on both a PowerMac and a MacBook. I do not do any  
development but as far as using R I do not have any problems.
Please note that software such as Parallels (http:// 
www.parallels.com), allows you to run Linux on a Mac Intel (such as  
Mac Pro) without problems, in case you need it.

Feel free to ask more questions,
Mihalis.


Mac for Productivity, Unix for Development, and Windows for Solitaire

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] how to define w matrix in my case?

[Xu Yuan]

hello list,

I have N agricultural fields (some of them share borders, some don't)
with ph as the variable of interest. Since I want to test the spatial
autocorrelation, I need to come up with the w matrix. The first and
easy way that came to my brain was the binary relationship, i.e., the
w matrix is all 1s and 0s with 1 meaning two fields sharing border and
0 not. So I checked the distribution of the N fields, and I manually
defined a NxN matrix with 1s and 0s. I list the variable of interest
(ph) as a vector with N elements, and plan to use moran or moran.test
to test the spatial autocorrelation. However, I had difficulty to run
the code. Anyone has suggestions about my case where the areal/lattice
data are irregular?

Please also let me know if moran or moran.test is the correct command to use.

Thanks.
XY

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] help on determining operating system

[LU YING]

Dear list,

I am an R user and I also write my own package in R(sometime i need to 
write  in C), and right now i am thinking about buying a new 
workstation--and i am trying to decide if i should get 
a mac with OS X or a linux machine (for example Dell).

I have experience using R on linux (but i have been just a user and never 
been a admin) but i am hesitating of managing a linux system on my own 
(btw I would like to have my new workstation to be used as a server), so 
right now I am leaning toward of buying a Mac Pro. But from the website, 
it sounds like R doesnt work quite well with Mac operating system 
yet...so I was wondering if anybody here have any experiences of 
using/developing R package on a Mac machine? Is it smooth enough?

(oh by the way, i am not a Mac user yet, Windows has been the primary 
operating system that i used, but after hearing many good things 
of OS X, I am really interested in switching over.)

any suggestions are appreciated!

Ying


Ying Lu
Assistant Professor
Dept. Sociology
U-Colorado at Boulder

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] strings as factors

[Bill.Venables]

Here is a possibility:

> test <- expand.grid(id = 1:2, sex = c('male', 'female'))
> sapply(test, class)
   id   sex 
"integer"  "factor" 
> test <- transform(test, sex = as.character(sex))
> sapply(test, class)
 id sex 
  "integer" "character" 


But I am surprised at the reason you give for needing it as a character
vector, because factors often act as character vectors under matching
anyway.

> sexf <- factor(test[[2]])
> sexf
[1] male   male   female female
Levels: female male

> which(sexf %in% "male")
[1] 1 2
> which(sexf == "male")
[1] 1 2

Bill Venables
 

-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Alexander Nervedi
Sent: Tuesday, 12 December 2006 10:09 AM
To: r-help@stat.math.ethz.ch
Subject: [R] strings as factors

Hi,
To be able to match cases with a benchmark I need to have a data.frame
with 
a character id variable. however, I am surprised why this seems to be so

hard. In fact I was  unable to succeed. Here is what I tried:

>test1 <-expand.grid(ID = 1:2, sex = c("male","female"))
>is(test1[,2])
[1] "factor"   "oldClass"
>test2 <-expand.grid(ID = 1:2, sex = c('male','female'))
>is(test2[,2])
[1] "factor"   "oldClass"
>test3 <-expand.grid(ID = 1:2, sex = I(c("male","female")))
>is(test3[,2])
[1] "factor"   "oldClass"
>test4 <-expand.grid(ID = 1:2, sex = I(c('male','female')))
>is(test4[,2])
[1] "factor"   "oldClass"
>options(stringsAsFactors = FALSE)
>options("stringsAsFactors")
$stringsAsFactors
[1] FALSE

>test5 <-expand.grid(ID = 1:2, sex = I(c('male','female')))
>is(test5[,2])
[1] "factor"   "oldClass"


is there anyway I can get sex to be a character?

Arnab

_
Visit MSN Holiday Challenge for your chance to win up to $50,000 in
Holiday

__
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
and provide commented, minimal, self-contained, reproducible code.

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] implementation of t.test

[Charles C. Berry]

On Mon, 11 Dec 2006, Weiwei Shi wrote:

> Hi, there:
>
> for some reason, I need to look at t.test at coding level. Can anyone
> here suggest a place to start with?

You mean how to read the code??

Like this:

> t.test # print the function
function (x, ...)
UseMethod("t.test")

> # that told me 't.test' has S3 methods
> methods(t.test)
[1] t.test.default* t.test.formula*

Non-visible functions are asterisked
> # that told me what they were
> # and that I need ':::' to see them
> page(stats:::t.test.default,"print")
> page(stats:::t.test.formula,"print")
> # looks like you want to study t.test.default

see
?methods
?":::"

HTH

> [...]

Charles C. Berry(858) 534-2098
  Dept of Family/Preventive Medicine
E mailto:[EMAIL PROTECTED]   UC San Diego
http://biostat.ucsd.edu/~cberry/ La Jolla, San Diego 92093-0717

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Hourly Time Series

[Harshal D Dedhia]

I have hourly data for approximately 21 days in the following format
 
DateIDHourIDMetrics 
200609200xx
200609201xx
 
The hour ids correspond to one hour windows starting 00:00 to 23:59.
 
I have never dealt with TS data before. What is the best way to handle
this data? TS objects or use the Zoo package?
 
Thanks in advance.

[[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
and provide commented, minimal, self-contained, reproducible code.

[R] Combining bitmaps and plots - file too large

[Jared.O'Connell]

Hello,

I wish to draw a bitmap image and a standard plot in a split window,
multiple times, output to a pdf eg.

library(pixmap)
pdf("test.pdf")
for(i in 1:50) {
par(mfrow=c(1,2))
p1 = read.pnm(paste("img",i,".ppm",sep=""))
plot(x,y)
}
dev.off()

The end result is a pdf file > 1GB, obviously not very portable.  The
.ppm's I'm using are around 1MB so they are not some huge resolution.
I've tried several different methods of optimising .pdfs externally (eg.
ps2pdf -dPDFSETTINGs=\screen) without much luck.

Any suggestions?

Regards,

Jared

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] strings as factors

[Alexander Nervedi]

Hi,
To be able to match cases with a benchmark I need to have a data.frame with 
a character id variable. however, I am surprised why this seems to be so 
hard. In fact I was  unable to succeed. Here is what I tried:

>test1 <-expand.grid(ID = 1:2, sex = c("male","female"))
>is(test1[,2])
[1] "factor"   "oldClass"
>test2 <-expand.grid(ID = 1:2, sex = c('male','female'))
>is(test2[,2])
[1] "factor"   "oldClass"
>test3 <-expand.grid(ID = 1:2, sex = I(c("male","female")))
>is(test3[,2])
[1] "factor"   "oldClass"
>test4 <-expand.grid(ID = 1:2, sex = I(c('male','female')))
>is(test4[,2])
[1] "factor"   "oldClass"
>options(stringsAsFactors = FALSE)
>options("stringsAsFactors")
$stringsAsFactors
[1] FALSE

>test5 <-expand.grid(ID = 1:2, sex = I(c('male','female')))
>is(test5[,2])
[1] "factor"   "oldClass"


is there anyway I can get sex to be a character?

Arnab

_
Visit MSN Holiday Challenge for your chance to win up to $50,000 in Holiday

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] implementation of t.test

[Weiwei Shi]

Hi, there:

for some reason, I need to look at t.test at coding level. Can anyone
here suggest a place to start with?

thanks.

-- 
Weiwei Shi, Ph.D
Research Scientist
GeneGO, Inc.

"Did you always know?"
"No, I did not. But I believed..."
---Matrix III

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] a web interface to identify()

[Jon Stearley]

i have a function like this:
  # show a plot and run a script when the user clicks on a plot,
  # where the script arguments correspond to the user-selected point.
  blah <- function(x, y) {
plot(y~x)
n <- identify(x=x, y=y)
com <- system(command=paste("bleh", names(y)[n]))
  }

i would like to do this via a web page instead of x11() etc.  eg:
  1) a user clicks on an image in their web browser
  2) the i,j coordinate is sent to the server
  3) a single R process determines the nearest data point
  4) the server sends a new page to the client, based on attributes  
of the selected data point

i've browsed the R web interface options and frankly don't know which  
to pick, or maybe they are all overkill for what i am trying to  
accomplish?  perhaps the easiest thing to do is use ismap to capture  
the i,j coords, the receiving cgi script connects to an R process for  
the data lookup, and then responds to the browsing client  
appropriately.  the data set involved is very large, so i'd need a  
single R process sitting there waiting for such queries in order to  
avoid initialize&load time - this is the part i am particularly  
unclear how to do.

any ideas/suggestions/guidance on the best approach would be much  
appreciated.  thank you.

-- 
+--+
| Jon Stearley  (505) 845-7571  (FAX 844-9297) |
| Sandia National Laboratories  Scalable Systems Integration   |
+--+

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] EBimage package for materials science

[İbrahim Mutlay]

Dear R users,

In last R News, a new package was appeared. EBimage image processing package
seems so powerful. But in R News, it is used for the images of cells under
microscope. So, i wonder whether there is anyone who use this package for
materials science applications such as determination of mean diameter of
particles, fibers or pores, estimation of porosity or covering factor.

Sincerely...

-- 
Ýbrahim Mutlay

[[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
and provide commented, minimal, self-contained, reproducible code.

[R] Problem with sas.get function in Hmisc

[Jean Vidal]

Thomas,

As F Harrel in a preceding message told me that you are the maintainer
of Hmisc package,
I write directly to you, with copy to the Rhelp list in case someone
encountered the same problem and find some benefit in the response.

I used quite often the function sas.get in Hmisc library which I is
very, very useful.
But, as trying to reuse it today it seems not to function anymore.
I tried everything I could imagine this afternoon, with no success.

Here is my last test.
'datatest' is a very simple SAS dataset (V9.1) with only 3 variables,
100 obs, no format.
Sas.get produces this ouput :
> bs2m <- sas.get(library="C:/test","datatest")
Syntaxe du nom de fichier, de r‚pertoire ou de volume incorrecte.
Error in sas.get(library = "C:/test", "datatest") :
SAS job failed with status 1
In addition: Warning message:
'cmd' execution failed with error code 1 in: shell(cmd, wait = TRUE,
intern = output)

In the R temp directory there is only one file : SaS678418be.3.sas,
containing the usual SAS
program (macro and  macro call).
I can run it from R with :
> sys("sas -sysin C:/Temp/RtmpuC23qb/SaS678418be.3.sas")
character(0)
and I get two files with dict (SaS678418be.1.sas) and data (SaS678418be.2.sas).
So the SAS step seems to work fine.

Do you have an idea of what went wrong ?
I tried to run old R progs with sas.get which used to work, and have
the same problem.

Thank you in advance.

> version
   _
platform   i386-pc-mingw32
arch   i386
os mingw32
system i386, mingw32
status
major  2
minor  4.0
year   2006
month  10
day03
svn rev39566
language   R
version.string R version 2.4.0 (2006-10-03)

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] hermite and Bezier splines

[Mark Hindell]

Does anyone know how to do hermite or

Bezier splines in R? I can find Matlab routines, but really need to 
implement them in R. Failing that I'd be interested in other 
conformal splines. I need to smooth and interpolate animal tracking data.





Antarctic Wildlife Research Unit
School of Zoology
University of Tasmania
PO Box 252-05
Hobart
TAS, 7001
Australia

Phone:  (0)3 6226 2645
Fax:(0)3 6226 2745


http://www.zoo.utas.edu.au/awru/ 
[[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] global option settings for grid and lattice?

[Paul Murrell]

Hi


Zepu Zhang wrote:
> Hello,
> 
> I'd like to be able to set options for grid and lattice globally, once 
> for all subsequent plots, just like what ps.options() does. I walked 
> through the functions of Grid and didn't find it. The following are 
> related things that are available:
> 
> get.gpar()
> trellis.par.set()
> 
> any ideas? thanks.


ps.options() sets the defaults for a PostScript output device.  It has
no effect, for example, on screen output.

The top-level grid viewport takes most of its default settings from the
device, so it should pick up ps.options() settings (WHEN you are drawing
to a PostScript device).  All grid drawing uses default settings from
the current viewport unless explicitly overridden, so ps.options()
settings should carry through to your drawing (IF you are only using grid).

Lattice decides for itself what the default graphics settings should be
(again, based on the type of device you are drawing to, but using
lattice defaults, NOT ps.options() defaults).  You might want to look at
?trellis.device and read about themes to gain control over default
lattice settings.

Paul
-- 
Dr Paul Murrell
Department of Statistics
The University of Auckland
Private Bag 92019
Auckland
New Zealand
64 9 3737599 x85392
[EMAIL PROTECTED]
http://www.stat.auckland.ac.nz/~paul/

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] I think this modified ewma function works if anyone is interested

[Leeds, Mark \(IED\)]

I think this modified version of ewma works for anyone who is
interested. It gets rid of any NAs, smoothes the
resulting series and then puts the NAs back in at their correct spots.
The only catch is that the input has to be a zoo object. 
Sometimes I shock myself.


ewmab<-function(x,lambda = 1, init = x[1]) {

oldindex<-index(x)

temp<-as.vector(!is.na(x))
x<-x[temp]

rval<-filter(lambda*coredata(x),filter=(1-lambda),method="recursive",ini
t=init)
nonmissingzoo<-zoo(matrix(coredata(rval),nc=1),index(x))
rval<-merge(zoo(,oldindex),nonmissingzoo)

rval

}


This is not an offer (or solicitation of an offer) to buy/se...{{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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] set up directory for R when I start R

[Duncan Murdoch]

On 12/11/2006 2:21 PM, Earl F. Glynn wrote:
> "Dieter Menne" <[EMAIL PROTECTED]> wrote in message 
> news:[EMAIL PROTECTED]
>> Aimin Yan  iastate.edu> writes:
>>
>>>
>>> I want to set default directory for R when I start R.
>>> How to do this?
>>>
>> ?setwd
>>
>> In Windows, I prefer the method described in
>>
>> http://tolstoy.newcastle.edu.au/R/help/00b/2454.html
> 
> I learned a similar trick by using Regedit to set the registry keys 
> directly.  (Years ago someone showed me this trick to start a DOS session). 
> Apparently, either "\Directory\shell" or "\Folder\shell" do the same thing. 
> Do you know if there is a difference?

Folders are shell objects, directories are file system objects. 
Normally the file system is mapped to folders, but there are other 
folders too, e.g. the network neighbourhood, printers, etc.

Duncan Murdoch

> 
> I checked and your suggestion can be modified to even specify a http_proxy, 
> if needed:
> 
> For example, this works for me under Windows XP, including the proxy server, 
> from any directory chosen using Windows Explorer:
> 
> 
> Windows Registry Editor Version 5.00
> 
> [HKEY_CLASSES_ROOT\Folder\shell\R\command]
> @="C:\\Program Files\\R\\R-2.4.0\\bin\\Rgui.exe 
> http_proxy=http://proxy01:8080 http_proxy_user=ask"
> ---
> 
> The above was the exported registry key from what I set manually using 
> RegEdit. I used simply "R" instead of "Run R", like you suggested.
> 
> 
> efg
> 
> Earl F. Glynn
> Bioinformatics
> Stowers Institute for Medical Research
> 
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Cannot scale my map

[Mihalis Tsoukalos]

On Mon 11 Dec 2006, at 22:32 , Ray Brownrigg wrote:

> On Tuesday 12 December 2006 09:07, Mihalis Tsoukalos wrote:
>> Dear list,
>>
>> I have the following problem:
>>
>> I want to plot my data and display a map at the same graph. The
>> problem is that my map is not properly sized (is very small). It
>> appears at the bottom-left side of the output.
>> I am using the following R commands:
>>
>> {
>> plot(Time, col="lightgrey")
>> title("Connections per Minute")
>> map("world", fill=TRUE, lwd=0.25, col="green", add=TRUE)
>> box()
>> }
>>
>> Please note that Time contains data in the following format:
>> 00:00
>> 00:01
>> ...
>> 22:04, etc.
>>
>> Can you please help me?
>
> If you just want the map as a 'background', then you will need to  
> rescale one
> or other of the plots.

Dear Ray,
thanks for answering.

I just want the map as a "background" but I do not know how to  
rescale it.
Can anyone help me?

thanks!
Mihalis.

---
Show me a Mac user, and I 'll show you a creative user.

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Cannot scale my map

[Ray Brownrigg]

On Tuesday 12 December 2006 09:07, Mihalis Tsoukalos wrote:
> Dear list,
>
> I have the following problem:
>
> I want to plot my data and display a map at the same graph. The
> problem is that my map is not properly sized (is very small). It
> appears at the bottom-left side of the output.
> I am using the following R commands:
>
> {
> plot(Time, col="lightgrey")
> title("Connections per Minute")
> map("world", fill=TRUE, lwd=0.25, col="green", add=TRUE)
> box()
> }
>
> Please note that Time contains data in the following format:
> 00:00
> 00:01
> ...
> 22:04, etc.
>
> Can you please help me?
>
Well, the only way a map(..., add=TRUE) will work is if the original scale is 
in the order of latitude and longitude in degrees.  It is not clear exactly 
how the data you are plotting relates to the map you want.

If you just want the map as a 'background', then you will need to rescale one 
or other of the plots.

Hope this helps,
Ray Brownrigg

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Multiple Imputation / Non Parametric Models / Combining Results

[Michael Dewey]

At 08:12 08/12/2006, Simon P. Kempf wrote:
>Dear R-Users,
>
>
>
>The following question is more of general nature than a merely technical
>one.  Nevertheless I hope someone get me some answers.
>
>

I am in no sense an expert in this area but since 
it seems that noone else has answered so far; I 
wonder whether the mitools package from CRAN helps?


>I have been using the mice package to perform the multiple imputations. So
>far, everything works fine with the standard regressions analysis.
>
>
>
>However, I am wondering, if it is theoretically correct to perform
>nonparametric models (GAM, spline smoothing etc.) with multiple imputed
>datasets. If yes, how can I combine the results in order to show the
>uncertainty?
>
>
>
>In the research field of real estate economics, the problem of missing data
>is often ignored respectively unmentioned. However, GAM, spline smoothing
>etc. become increasingly popular. In my research, I would like to use
>multiple imputed datasets and GAM, but I am unsure how present single
>results.
>
>
>
>Again I want to apologize that this is a rather theoretical statistical
>question than a technical question on R.
>
>
>
>Thanks in advance for any hints and advices.
>
>
>
>Simon
>
>
>
>
>
>
>
>
>
>
>
>Simon P. Kempf
>
>Dipl.-Kfm. MScRE Immobilienökonom (ebs)
>
>Wissenschaftlicher Assistent
>
>
>
>Büro:
>
>IREBS Immobilienakademie
>
>c/o ebs Immobilienakademie GmbH
>
>Berliner Str. 26a
>
>13507 Berlin
>
>
>
>Privat:
>
>Dunckerstraße 60
>
>10439 Berlin
>
>
>
>Mobil: 0176 7002 6687
>
>Email:   [EMAIL PROTECTED]
>
>
>
>
> [[alternative HTML version deleted]]

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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] behavior of ewma function

[Leeds, Mark \(IED\)]

I just had an idea but I'm not sure how to do it. Create a non NA series
( which I can do ) and smooth
that series ( whh I can do ). Then, after that smoothed series is
created, put the NAs back into the smoothed series
in their appropriate places ( which I don't know how to do ).
 
If anyone does know how to do that, the help would be appreciated.



-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Leeds, Mark (IED)
Sent: Monday, December 11, 2006 3:15 PM
To: r-help@stat.math.ethz.ch
Subject: [R] behavior of ewma function

I have the ewma function as shown below. I think I copied it from an
oldSplus help page on filter and then modified it with a lot of help
from Achim.

ewma<-function(x,lambda = 1, init = x[1]) {

rval<-filter(lambda*coredata(x),filter=(1-lambda),method="recursive",ini
t=init)
rval<-zoo(coredata(rval),index(x))
rval
}

It sort of works but , if there are NA values in the input series such
as

x<-c(NA,2,3,4,5,NA,6,7,8,9,10,11,12,13,14,15)

y<-ewma(x,.01)

y

  1 2 3 4 5 6 7
8 9101112131415
16 

0.000 0.020 0.0498000 0.0893020 0.1384090  NA 0.000
0.070 0.1493000 0.2378070 0.3354289 0.4420746 0.5576539 0.6820774
0.8152566 0.9571040

So, ewma starts off with a zero if there is an NA and this is misleading
in terms of the exponentially weighted moving average numbers calculated
going forward. Maybe this has something to do Woth the fact that I set
init equal x[1] ? The NA in the 6th spot is fine but is there any way to


1) return an NA value when the input into the series is an NA ?

2) start the exponentially weighted moving average at the next non NA
value ?

So, essentually, for the example above, I would prefer the output to be

NA, 2, 2*.01 + .99*3 = 2.99, 2.99*.01 + .99*4 = 3.9899, 3.9899*.01+
0.99*5 = 4.989, 4.989 ( because of the NA ),
4.989*.01 + 0.99* 6 = 5.989 etc.

This might be too complex to get but atleast is it possible to get NA
where the inputs were NA  and not use zeros for smoothing going forward
? Thanks.








 





P.S : The code in ewma may look a little different than one is used to
but that is because it is sometimes run with The inputs being zoo
objects so coredate and index are needed.


This is not an offer (or solicitation of an offer) to
buy/se...{{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
and provide commented, minimal, self-contained, reproducible code.


This is not an offer (or solicitation of an offer) to buy/se...{{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
and provide commented, minimal, self-contained, reproducible code.

[R] behavior of ewma function

[Leeds, Mark \(IED\)]

I have the ewma function as shown below. I think I copied it from an
oldSplus help page on filter and
then modified it with a lot of help from Achim.

ewma<-function(x,lambda = 1, init = x[1]) {

rval<-filter(lambda*coredata(x),filter=(1-lambda),method="recursive",ini
t=init)
rval<-zoo(coredata(rval),index(x))
rval
}

It sort of works but , if there are NA values in the input series such
as

x<-c(NA,2,3,4,5,NA,6,7,8,9,10,11,12,13,14,15)

y<-ewma(x,.01)

y

  1 2 3 4 5 6 7
8 9101112131415
16 

0.000 0.020 0.0498000 0.0893020 0.1384090  NA 0.000
0.070 0.1493000 0.2378070 0.3354289 0.4420746 0.5576539 0.6820774
0.8152566 0.9571040

So, ewma starts off with a zero if there is an NA and this is misleading
in terms of the exponentially weighted
moving average numbers calculated going forward. Maybe this has
something to do
Woth the fact that I set init equal x[1] ? The NA in the 6th spot is
fine but is there any way to 

1) return an NA value when the input into the series is an NA ?

2) start the exponentially weighted moving average at the next non NA
value ?

So, essentually, for the example above, I would prefer the output to be

NA, 2, 2*.01 + .99*3 = 2.99, 2.99*.01 + .99*4 = 3.9899, 3.9899*.01+
0.99*5 = 4.989, 4.989 ( because of the NA ),
4.989*.01 + 0.99* 6 = 5.989 etc.

This might be too complex to get but atleast is it possible to get NA
where the inputs were NA  and not use zeros
for smoothing going forward ? Thanks.








 





P.S : The code in ewma may look a little different than one is used to
but that is because it is sometimes run with
The inputs being zoo objects so coredate and index are needed.


This is not an offer (or solicitation of an offer) to buy/se...{{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
and provide commented, minimal, self-contained, reproducible code.

[R] Cannot scale my map

[Mihalis Tsoukalos]

Dear list,

I have the following problem:

I want to plot my data and display a map at the same graph. The  
problem is that my map is not properly sized (is very small). It  
appears at the bottom-left side of the output.
I am using the following R commands:

{
plot(Time, col="lightgrey")
title("Connections per Minute")
map("world", fill=TRUE, lwd=0.25, col="green", add=TRUE)
box()
}

Please note that Time contains data in the following format:
00:00
00:01
...
22:04, etc.

Can you please help me?

many thanks in advance,
Mihalis.

---
Show me a Mac user, and I 'll show you a creative user.

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] set up directory for R when I start R

[Earl F. Glynn]

"Dieter Menne" <[EMAIL PROTECTED]> wrote in message 
news:[EMAIL PROTECTED]
> Aimin Yan  iastate.edu> writes:
>
>>
>> I want to set default directory for R when I start R.
>> How to do this?
>>
> ?setwd
>
> In Windows, I prefer the method described in
>
> http://tolstoy.newcastle.edu.au/R/help/00b/2454.html

I learned a similar trick by using Regedit to set the registry keys 
directly.  (Years ago someone showed me this trick to start a DOS session). 
Apparently, either "\Directory\shell" or "\Folder\shell" do the same thing. 
Do you know if there is a difference?

I checked and your suggestion can be modified to even specify a http_proxy, 
if needed:

For example, this works for me under Windows XP, including the proxy server, 
from any directory chosen using Windows Explorer:


Windows Registry Editor Version 5.00

[HKEY_CLASSES_ROOT\Folder\shell\R\command]
@="C:\\Program Files\\R\\R-2.4.0\\bin\\Rgui.exe 
http_proxy=http://proxy01:8080 http_proxy_user=ask"
---

The above was the exported registry key from what I set manually using 
RegEdit. I used simply "R" instead of "Run R", like you suggested.


efg

Earl F. Glynn
Bioinformatics
Stowers Institute for Medical Research

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] R and LaTeX

[Mike Prager]

David Kaplan <[EMAIL PROTECTED]> wrote:

> Hi all,
> 
> I have started using LaTeX for writing papers and I have heard that R 
> works well with LaTeX.  I'm specifically interested in how I can have 
> LaTeX read in R generated graphics - for example graphs formed by 
> matplot, or other such  processes.  Does anyone out there use LaTeX and 
> can point me in the right direction?

> David

David--

The basic paradigm is to save the graph from R in encapsulated
Postscript format.  The procedure can vary slightly by the OS
you are using R under.  Under Windows, I usually generate the
graphics in the windows() device, then use savePlot to save it
to eps.

In Latex, you can put 

\usepackage{graphicx}

in the document preamble and something like

\begin{figure}[!th]
\includegraphics[height=8in]{figurename.eps}\\
\end{figure}

into the text to put the figure in a float.  To put in exactly
where the statement occurs, omit putting it into a figure
environment.

HTH,

--Mike

-- 
Mike Prager, NOAA, Beaufort, NC
* Opinions expressed are personal and not represented otherwise.
* Any use of tradenames does not constitute a NOAA endorsement.

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Solution of Rcmdr Problem in Quantian OS, Thanks...

[İbrahim Mutlay]

As you know, i have problem about Rcmdr in the 2.4.0 version of R, it can't
be run properly in Quantian due to that Tcl/Tk does not support it. But,
now, with helps from Dirk Eddelbuettel, problem was solved. The solution is
just that reinstallation of R from debian packages not by compiling of
2.4.0 version source code. During the process, i noticed a srange thing,
that is, if i start R in root user mode, result is:


R : Copyright 2005, The R Foundation for Statistical Computing
Version 2.1.0  (2005-04-18), ISBN 3-900051-07-0

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for a HTML browser interface to help.
Type 'q()' to quit R.

Loading Tcl/Tk interface ... Xlib: connection to ":0.0" refused by server
Xlib: No protocol specified

Error in fun(...) : this isn't a Tk applicationcouldn't connect to display
":0.0"
Error: .onLoad failed in 'loadNamespace' for 'tcltk'
Fatal error: unable to restore saved data in .RData

[EMAIL PROTECTED]:/home/mutlay/r#

So, console kick me out of R. But in ordinary user mode, there is no problem
and with "capabilities()" command all of them are TRUE:

R : Copyright 2005, The R Foundation for Statistical Computing
Version 2.1.0  (2005-04-18), ISBN 3-900051-07-0

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for a HTML browser interface to help.
Type 'q()' to quit R.

Loading Tcl/Tk interface ... done
[Previously saved workspace restored]

> capabilities()
jpeg  pngtcltk  X11 http/ftp  sockets   libxml fifo
TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
  cledit  IEEE754iconv
TRUE TRUE TRUE
>

Unfortunately, i can't interpret this case. If it is possible, i expect some
comments on this case.

Thanks to Dirk...
Sincerely
-- 
Ýbrahim Mutlay

[[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] DOE teaching suggestions?

[Spencer Graves]

Hi, Erin:

  Also, have you seen the "BsMD" package ("Bayes Screening and Model 
Discrimination"), also discussed in Box Hunger and Hunter (2005).

  Spencer Graves
##
  Also, have you seen the "BHH2" package, companion to Box, Hunter and
Hunter (2005) Statistics for Experimenters, 2nd ed. (Wiley)?

  Hope this helps.
  Spencer Graves

  Are you planning to have them design and conduct an actual
physical experiment as part of the class?  You may know that Bill Hunter
(the second Hunter of Box, Hunter & Hunter) wrote articles about doing
this, and I found it extremely helpful.   Things happen with real
physical experiments that can't be duplicated with any kind of computer
simulation.

  I think I've gotten good results assigning team projects of their
own choosing.  I found it necessary to have "design review"
presentations in the middle of the class.  These presentations give you
feedback on their understanding of the class material to that date.
They also give you an opportunity to suggest improvements before they
actually do the experiment.

  This is not what you asked, but I hope you find it useful, anyway.
  Best Wishes,
  Spencer Graves

Erin Hodgess wrote:
> Dear R People:
>
> I will be teaching an undergraduate Design of Experiments class
> in the Spring Semester.  It will be very much an applied course.
>
> My question, please:  has anyone used R for a course like this, please?
>
> I've tried Rcmdr for a regression course and just plain command
> line for a time series course.
>
> Should I use Rcmdr, or teach them to use the command line, OR is there
> something else, please?
>
> Thanks in advance!
>
> 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
> and provide commented, minimal, self-contained, reproducible code.
>

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] lmer message

[Marc Bernard]

Dear All,
   
  I am using lmer to fit a glmm model using the PQL approximation.
  My data is not a  Bernoulli (0/1) but a binomial one. The first thing I 
noticed is that the method gives me the approximated covariance matrix for the 
random effects but nothing about the residuals. In addition, I have the 
following estimation that I do not know what  deos it mean: 
  Estimated scale (compare to  1 )  75043946. 
   
  However, when I use  the glmmPQL method to fit this model then the  problem 
doesn't arise, i.e. I have the estimated covariance matrix for the random 
effects as well as the standard deviation of the residuals. I would be very 
grateful for any comments and/or explanation.
   
  Thank you in advance,
   
  Bernard
   
   


-

[[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Getting DataFrame Name from Text String

[Carlos Ortega]

Hello,

I think assign() makes a better job

Regards,
Carlos.

On 12/11/06, Vladimir Eremeev <[EMAIL PROTECTED]> wrote:
>
> consider get or as.name
>
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.
>

[[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] similarity test with R

[Chuck Cleland]

Ethan Johnsons wrote:
>> x=c(3.05176E-05,0.000457764,0.003204346,0.0138855,0.04165649,0.09164429,0.1527405,0.1963806,0.1963806,0.1527405,0.09164429,0.04165649,0.0138855,0.003204346,0.000457764,3.05176E-05)
>> y=c(0.306,0.0004566,0.0031985,0.0139083,0.0415539,0.0917678,0.1528134,0.1962831,0.1962994,0.1527996,0.0917336,0.0415497,0.0139308,0.0031917,0.0004529,0.301)
> 
> I tried chisq.test, t-test, prop.test, etc, but the p-value is very
> high, which is not 'statistically significant'.  With these data sets,
> I want to compare the similarity, which it is very close to identical
> if you plot them.I am wondering if there is any test that can
> verify the similarity of the two data sets.
> 
> thx much

http://finzi.psych.upenn.edu/R/Rhelp02a/archive/82001.html

library(equivalence)

> ej
> 
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.

-- 
Chuck Cleland, Ph.D.
NDRI, Inc.
71 West 23rd Street, 8th floor
New York, NY 10010
tel: (212) 845-4495 (Tu, Th)
tel: (732) 512-0171 (M, W, F)
fax: (917) 438-0894

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] similarity test with R

[Ethan Johnsons]

>x=c(3.05176E-05,0.000457764,0.003204346,0.0138855,0.04165649,0.09164429,0.1527405,0.1963806,0.1963806,0.1527405,0.09164429,0.04165649,0.0138855,0.003204346,0.000457764,3.05176E-05)
>y=c(0.306,0.0004566,0.0031985,0.0139083,0.0415539,0.0917678,0.1528134,0.1962831,0.1962994,0.1527996,0.0917336,0.0415497,0.0139308,0.0031917,0.0004529,0.301)

I tried chisq.test, t-test, prop.test, etc, but the p-value is very
high, which is not 'statistically significant'.  With these data sets,
I want to compare the similarity, which it is very close to identical
if you plot them.I am wondering if there is any test that can
verify the similarity of the two data sets.

thx much

ej

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Difference in outputs of random mixed effect models (lmer function)

[Syed M. Jamal]

Dear all,
   
  I  am using lme4 library (lmer function) for random mixed effect model. I 
 came across different outputs using R versions 2.2.1 and 2.4.0. I am  not sure 
whether it is due to new version of R or that of lme4 library.  I am looking 
forward to know which version of R and lme4 library will  give me the correct 
outputs.

  Best wishes,
  Syed M. Jamal
Utrecht University

-

[[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
and provide commented, minimal, self-contained, reproducible code.

[R] How to write a two-way interaction as a random effect in a lmer model?

[Fucikova, Eva]

Dear All,

 

I am working with linear mixed-effects models using the lme4 package in
R. I created a model with the lmer function including some main effects,
a two-way interaction and a random effect. Now I am searching how I
could incorporate an interaction between the random effect and one of
the fixed effects.

 

I tried to express the interaction in:

recap_random3<-lmer(breath~handling+stress+stress:handling+(1|rnr)+(0|rn
r:stress))

however R gives me the following error message

:

Error in eval(expr, envir, enclos) : fl[[2]] must be a factor of length
1744

In addition: Warning messages:

1: numerical expression has 1744 elements: only the first used in:
rnr:stress 

2: numerical expression has 1744 elements: only the first used in:
rnr:stress

 

If I fit this model in SPSS, this gives me output, but I don't know
whether I can trust that.

 

 

Therefore I went to look for an alternative:

After looking at the help function in R for lmer I deduced these models.


Examples from R

(fm1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy))
(fm2 <- lmer(Reaction ~ Days + (1|Subject) + (0+Days|Subject),
sleepstudy))
anova(fm1, fm2)

 

 

My models would then look like this:

 

recap_random0<-lmer(breath~handling+stress (1|rnr))

recap_random1<-lmer(breath~handling+stress (1|rnr)+(0+stress|rnr))

 

However, I do not know how to interpret the results. Does the model see
stress|rnr as an interaction between stress and rnr, or did it take
stress nested in rnr.

 

> summary(recap_random1)

Linear mixed-effects model fit by REML 

Formula: breath ~ handling + stress + stress:handling + (1 | rnr) + (0 +
stress | rnr) 

  AIC  BIC logLik MLdeviance REMLdeviance

 9748 9781  -4868   9719 9736

Random effects:

 Groups   NameVariance Std.Dev.

 rnr  (Intercept) 55.6711  7.4613   # BUT

 rnr  stress  15.2805  3.9090   # Does this
output line express the interaction??? 

 Residual  7.4567  2.7307# If not, how
should the interaction output look like?

number of obs: 1744, groups: rnr, 217; rnr, 217

 

Fixed effects:

 Estimate Std. Error t value

(Intercept) 28.164471   0.716359   39.32

handling 0.012477   0.0123301.01

stress   0.636979   0.4160111.53

 

Correlation of Fixed Effects:

(Intr) hndlng stress

handling-0.645  

stress  -0.517  0.667   

 

 

Could anybody please give me an advice how to solve this problem? Which
way is correct to express interaction in the random factors? How should
the output look like?

 

Thank you in advance,

Eva Fucikova

 



Msc. Eva Fucikova 
Netherlands Institute of Ecology (NIOO-KNAW) 
PO Box 40 
 ZG Heteren 
The Netherlands 
tel.: +31 (0)26 4791248 
Email:[EMAIL PROTECTED] 

***

 


[[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
and provide commented, minimal, self-contained, reproducible code.

[R] double boostrap with clusterApplyLB

[Michela Cameletti]

Dear R-Users,
we are using a linux-cluster with RMPI and the snow package.
We would like to do a double boostrap.
We have a general function that implements the first boostrap (the outer) and
we are wondering if we can include another bootstrap (the inner) in the
same general function including another clusterApplyLB.

For example:

general function = function(...) {
  clusterApplyLB(cl, fun,...) }
where "fun" is the function for the inner boostrap

outer bootstrap = clusterApplyLB(cl,general function,...)

Does R accept this kind of expression?
Thank you very much in advance,
Michela and Marco

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] DOE teaching suggestions?

[Spencer Graves]

Hi, Erin:

  Also, have you seen the "BHH2" package, companion to Box, Hunter and 
Hunter (2005) Statistics for Experimenters, 2nd ed. (Wiley)?

  Hope this helps.
  Spencer Graves

  Are you planning to have them design and conduct an actual
physical experiment as part of the class?  You may know that Bill Hunter
(the second Hunter of Box, Hunter & Hunter) wrote articles about doing
this, and I found it extremely helpful.   Things happen with real
physical experiments that can't be duplicated with any kind of computer
simulation.

  I think I've gotten good results assigning team projects of their
own choosing.  I found it necessary to have "design review"
presentations in the middle of the class.  These presentations give you
feedback on their understanding of the class material to that date.
They also give you an opportunity to suggest improvements before they
actually do the experiment.

  This is not what you asked, but I hope you find it useful, anyway.
  Best Wishes,
  Spencer Graves

Erin Hodgess wrote:
> Dear R People:
>
> I will be teaching an undergraduate Design of Experiments class
> in the Spring Semester.  It will be very much an applied course.
>
> My question, please:  has anyone used R for a course like this, please?
>
> I've tried Rcmdr for a regression course and just plain command
> line for a time series course.
>
> Should I use Rcmdr, or teach them to use the command line, OR is there
> something else, please?
>
> Thanks in advance!
>
> 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
> and provide commented, minimal, self-contained, reproducible code.
>

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Getting DataFrame Name from Text String

[Vladimir Eremeev]

consider get or as.name

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Weighted averaging partial least squares regression

[ucfagls]

Quoting Andreas Plank <[EMAIL PROTECTED]>:

> Hello,
>
> is it possible in R to calculate a Weighted averaging partial least
> squares regression? I'm not firm in statistics and didn't found anything
> about weighted averaging in combination with PLS in the help archives.
> Or is it possible to develop a workaround with the pls-package?

Nothing in R that is publicly available. It is certainly possible to 
modify the
pls package (I did so for package cocorresp, but that does something slightly
different to what you want).

Steve Juggins is writing an R package that includes WA-PLS, you might wish to
contact him to see if there is an early version available that you might use.
His University web pages are here:

http://www.campus.ncl.ac.uk/staff/Stephen.Juggins/

And you'll find his email address on them.

HTH

Gavin Simpson

>
> thanks for help in advance
> Andreas Plank
>
>
> --
> _
> Dipl. Biol. Andreas Plank
> FU Berlin
> Institute of Geological Science
> Department Palaeontology
> Malteserstr. 74-100, House D
> 12249 Berlin
> Germany
> phone.: +49(0)30-83870-271
> fax.:   +49(0)30-83870-745
> http://userpage.fu-berlin.de/~jevers/plank_a.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
> and provide commented, minimal, self-contained, reproducible code.
>

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] organizing stats from a list of models

[hadley wickham]

>   I have a list of models (about 600 glm models) and I included the prefix 
> "mod_" on their name. Now I would like retrieve the list from the R 
> environment and save their AICs (and other info) on a table. I´m trying 
> something like:

I have some (rather un)tested code:

findmodels <- function(modeltype = "lm", dataset, pattern) {
ls <- ls(".GlobalEnv", pattern=pattern)
mods <- ls[sapply(ls, function(x) inherits(get(x), modeltype))]
if (!missing(dataset)) {
data.name <- function(x) as.character(x$call[["data"]])
mods <- mods[sapply(mods, function(x) data.name == dataset)]
}

models <- lapply(mods, get)
class(models) <- c("ensemble", class(models))
models
}

summary.ensemble <- function(object, ...) {
fits <- data.frame(t(sapply(object, function(mod) {
sum <- summary(mod)
c(
df = .df(mod),
logL = logLik(mod),
AIC = -AIC(mod),
BIC = -AIC(mod, k=log(length(fitted(mod,
R2 = sum$r.squared,
adjR2 = sum$adj.r.squared
)
})))
fits$model <- factor(names(object))
rownames(fits) <- paste("m", fits$model, sep="")
fits
}

Hopefully that should give you an idea on how to proceed.

Regards,

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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] two ggplot and colour=x question

[Rainer M Krug]

Thanks a lot for your help - I'll try it out and let you know if I still 
have problems.

Rainer

hadley wickham wrote:
>> I am using ggplot with the aesthetic=list(..., colour=x, ...)
>>
>> ggplot()
>> ggline()
>>
>> I have four different values in x ("ren", "cyn", "mixed", "bare") and I
>> have two questions
>>
>> 1) I would like to assign specific colours to the values, i.e. green,
>> red, blue and brown. How can I do this? I did not understand
>> map_colour_brewer.
> 
> There's not really an easy way to do this at the moment.  However, you
> can create a new variable containing the colours you want to use and
> then use a manual scale so they aren't converted automatically:
> 
> df$colour <- c("red","blue","yellow","orange)[df$myvar]
> p <- ggplot(data=df, aes=list(x=x,y=y,colour=colour)
> scmanual(p, "colour")
> 
>> 2) I don't want the legend top be plot. How can I disable the legend to
>> be plotted?
> 
> If you use a manual scale (as above) there won't be a legend, or more
> generally you can do:
> 
> p$legend.position <- "none"
> to turn of the legend (see ?ggopt for other options)
> 
> Hadley


-- 
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation
Biology (UCT)

Department of Conservation Ecology and Entomology
University of Stellenbosch
Matieland 7602
South Africa

Tel:+27 - (0)72 808 2975 (w)
Fax:+27 - (0)86 516 2782
Fax:+27 - (0)21 808 3304 (w)
Cell:   +27 - (0)83 9479 042

email:  [EMAIL PROTECTED]
[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] filled.contour and NA's

[hadley wickham]

> I'm trying to do a filled.contour plot where some points are labelled as
> NA. How do I could plot this kind of graphics, so NA points are coloured
> black,  keeping the levels of remaining points. NA's values represent
> land points (meaningless), and what I want to plot is the levels of a
> variable over the sea.

You can also do this using ggplot, although you don't have quite as
much control over the appearance of the contours (you do get more
control over other things)

install.packages("ggplot", dep=T)
library(ggplot)

# Set up appropriate data structure
dimnames(ene) <- list(y, x)
names(dimnames(ene)) <- c("y", "x")
enem <- melt(ene)

p <- ggplot(na.omit(enem), aes=list(x=x, y=y, z=value, fill=value))
p <- ggtile(p)
p <- ggcontour(p)
scfillgradient(p)
scfillgradient(p, low="white", high="blue")

Regards,

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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] two ggplot and colour=x question

[hadley wickham]

> I am using ggplot with the aesthetic=list(..., colour=x, ...)
>
> ggplot()
> ggline()
>
> I have four different values in x ("ren", "cyn", "mixed", "bare") and I
> have two questions
>
> 1) I would like to assign specific colours to the values, i.e. green,
> red, blue and brown. How can I do this? I did not understand
> map_colour_brewer.

There's not really an easy way to do this at the moment.  However, you
can create a new variable containing the colours you want to use and
then use a manual scale so they aren't converted automatically:

df$colour <- c("red","blue","yellow","orange)[df$myvar]
p <- ggplot(data=df, aes=list(x=x,y=y,colour=colour)
scmanual(p, "colour")

> 2) I don't want the legend top be plot. How can I disable the legend to
> be plotted?

If you use a manual scale (as above) there won't be a legend, or more
generally you can do:

p$legend.position <- "none"
to turn of the legend (see ?ggopt for other options)

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
and provide commented, minimal, self-contained, reproducible code.

[R] Getting DataFrame Name from Text String

[Bert Jacobs]

Hi,

I have the following simple function

Testfunc = function(x)
{
Test = subset(x, var1 <= 1000)
}

Suppose I have a dataframe «dat1» then the command Testfunc(dat1) gives a
correct result.

The problem is that the name of dataframe to be used in the function can be
found in a vector (Dfname). The value of the vector can change in eg.

Dfname = « dat1 »
Or
Dfname = « dat2 »
Or
...

How can I pass this string into the function so that the correct database is
used. Thx for helping me out.

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
and provide commented, minimal, self-contained, reproducible code.

[R] organizing stats from a list of models

[Milton Cezar Ribeiro]

Hi there,
   
  I have a list of models (about 600 glm models) and I included the prefix 
"mod_" on their name. Now I would like retrieve the list from the R environment 
and save their AICs (and other info) on a table. I´m trying something like:
   
  -
  y<-runif(20,min=0,max=1)
  x1<-runif(20,min=0,max=1)
  x2<-runif(20,min=0,max=1)
   
  mymod_1 <-glm(y~x1)
  mymod_2<-glm(y~x2)
  mymod_3<-glm(y~x1+x2)
   
  model.list<-ls(pat="mymod_")
  model.list
  [1] "mymod_1" "mymod_2" "mymod_3"
-
  Now I would like have something like
   
  model_name call AIC
  mymod_1 glm(y~x1) 13.11942
mymod_2 glm(y~x2) 13.11942
mymod_3 glm(y~x1+x2) 13.11942

  How can I do that?
   
  All the best,
   
  Miltinho
   


-

[[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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Small Rcmdr issue

[Peter Dalgaard]

John Fox wrote:
> Dear Alan,
>
> I've noticed that problem too, and have no idea why it happens. The function
> that's executed when you select "Exit -> From Commander and R" is pretty
> simple:
>
> closeCommanderAndR <- function(){
> response <- closeCommander()
> if (response == "cancel") return()
> cat("\n")
> quit(save="no")
> }
>
> If anyone knows how I can fix the problem, I'd be happy to so do.
>   
I think I've seen this outside Rcmdr too, possibly with "R-g tk" but I 
can't seem to reproduce it now.
I don't think it's your problem, but if you get a handle on where the 
issue lies, please let us know. (Of course, you can always just reset 
the terminal or blind-type "stty sane", but it would be nicer to get rid 
of the issue altogether).

 -p

> Regards,
>  John
>
> 
> John Fox
> Department of Sociology
> McMaster University
> Hamilton, Ontario
> Canada L8S 4M4
> 905-525-9140x23604
> http://socserv.mcmaster.ca/jfox 
>  
>
>   
>> -Original Message-
>> From: [EMAIL PROTECTED] 
>> [mailto:[EMAIL PROTECTED] On Behalf Of Alan Jackson
>> Sent: Sunday, December 10, 2006 11:21 PM
>> To: r-help@stat.math.ethz.ch
>> Subject: [R] Small Rcmdr issue
>>
>> Just installed Rcmdr on a Linux box.
>>
>> When I exit from both Rcmdr and R together from the regular 
>> Rcmdr exit menu, it leaves my xterm with "stty -echo", so 
>> that nothing that is typed appears.
>> If I exit only Rcmdr, and then exit R normally, everything is 
>> okay (stty echo).
>>
>> Other than that minor irritant, everything seems to work just fine.
>>
>> Linux 2.6.16-gentoo-r3
>> Athlon 64 X2 3800+
>> R version 2.4.0 (2006-10-03)
>> Rcmdr Version 1.2-5
>>

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Small Rcmdr issue

[John Fox]

Dear Alan,

I've noticed that problem too, and have no idea why it happens. The function
that's executed when you select "Exit -> From Commander and R" is pretty
simple:

closeCommanderAndR <- function(){
response <- closeCommander()
if (response == "cancel") return()
cat("\n")
quit(save="no")
}

If anyone knows how I can fix the problem, I'd be happy to so do.

Regards,
 John


John Fox
Department of Sociology
McMaster University
Hamilton, Ontario
Canada L8S 4M4
905-525-9140x23604
http://socserv.mcmaster.ca/jfox 
 

> -Original Message-
> From: [EMAIL PROTECTED] 
> [mailto:[EMAIL PROTECTED] On Behalf Of Alan Jackson
> Sent: Sunday, December 10, 2006 11:21 PM
> To: r-help@stat.math.ethz.ch
> Subject: [R] Small Rcmdr issue
> 
> Just installed Rcmdr on a Linux box.
> 
> When I exit from both Rcmdr and R together from the regular 
> Rcmdr exit menu, it leaves my xterm with "stty -echo", so 
> that nothing that is typed appears.
> If I exit only Rcmdr, and then exit R normally, everything is 
> okay (stty echo).
> 
> Other than that minor irritant, everything seems to work just fine.
> 
> Linux 2.6.16-gentoo-r3
> Athlon 64 X2 3800+
> R version 2.4.0 (2006-10-03)
> Rcmdr Version 1.2-5
> 
> --
> --
> -
> | Alan K. Jackson| To see a World in a Grain of 
> Sand  |
> | [EMAIL PROTECTED]  | And a Heaven in a Wild Flower, 
> |
> | www.ajackson.org   | Hold Infinity in the palm of 
> your hand |
> | Houston, Texas | And Eternity in an hour. - 
> Blake   |
> 
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] upside down image/data

[Jenny Barnes]

Dear R-community,

I am looking for some simple advice - I have a matrix (therefore 2 dimensional) 
of global temperature. 

Having read R-help I think that when I ask R to image() or levelplot() my 
matrix 
will it actually appear upside down - I think I therefore need to use the line:
> levelplot(temperature.matrix[,ncol(output.temp):1], )
to get it looking like it was on the globe due to the matrix rows increasing in 
number down the matrix in its dimensions on longitude and latitude but the 
y-axis coordinates increase up the axis.

Can anyone simply tell me whether this is correct as I find it very hard to 
know 
which way up my data should be and I cannot tell which is correct simply by 
looking at it!

Many thanks for your time in reading this problem,

Jenny Barnes

~~
Jennifer Barnes
PhD student - long range drought prediction
Climate Extremes
Department of Space and Climate Physics
University College London
Holmbury St Mary, Dorking
Surrey
RH5 6NT
01483 204149
07916 139187
Web: http://climate.mssl.ucl.ac.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
and provide commented, minimal, self-contained, reproducible code.

[R] monte carlo simulation in R

[Dedy Angsana]

i want to learn about monte carlo simulation in R,
also about variance reduction techniques in monte
carlo, especialy antithetic variates and control
variates. can you give me an example of the code? or
where i can find the journal or article or guide?

thx for the answers...

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Switch and integer

[Knut Krueger]

David Barron schrieb:
>
> If the value of EXPR is an integer between 1 and nargs()-1 then the
> corresponding element of ... is evaluated and the result returned.
>
Thank you, I wondered about the
> integer between 1 and nargs()-1
and the example from the help file for(i in c(-1:3,9))  print(switch(i,
1,2,3,4))
No see I  that the 1,2,3,4 is the output not the value, but it's not
very clear for me ho it works.
I will try to find it out ...
The switch for Integer is very different from C++ or Pascal .. maybe
this was the reason for the problem.

Regards Knut

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] (no subject)

[Dedy Angsana]

 
 


 

Want to start your own business?

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] FW: R

[Peter Dalgaard]

[EMAIL PROTECTED] wrote:
> Hi Ricky / AJ
>
> Progress of sorts. I got passed the last problem by looking at the makefiles
> but run in to the next one, see below. 
>
> It has created files in /contrib/R-2.4.0. there is an " R " under 
> /contrib/R-2.4.0/bin/R.
>
> Running it gives :-
>
>
> /contrib/R-2.4.0/bin/R
>
> R version 2.4.0 (2006-10-03)
> Copyright (C) 2006 The R Foundation for Statistical Computing
> ISBN 3-900051-07-0
>
> R is free software and comes with ABSOLUTELY NO WARRANTY.
> You are welcome to redistribute it under certain conditions.
> Type 'license()' or 'licence()' for distribution details.
>
> R is a collaborative project with many contributors.
> Type 'contributors()' for more information and
> 'citation()' on how to cite R or R packages in publications.
>
> Type 'demo()' for some demos, 'help()' for on-line help, or
> 'help.start()' for an HTML browser interface to help.
> Type 'q()' to quit R.
>
>
>  *** caught segfault ***
> address 40b843f0, cause 'memory not mapped'
>
> Traceback:
>  1: .Call("La_dgesv", a, b, tol, PACKAGE = "base")
>  2: solve.default(rgb)
>  3: solve(rgb)
>  4: drop(whitexyz %*% solve(rgb))
>  5: make.rgb(red = c(0.625, 0.34), green = c(0.28, 0.595), blue = c(0.155, 
> 0.07), gamma = 1.8, white = "D65", name = "Apple RGB")
>  6: eval(expr, envir, enclos)
>  7: eval(i, envir)
>  8: sys.source(codeFile, env, keep.source = keep.source)
>  9: try(sys.source(codeFile, env, keep.source = keep.source)) 10: 
> loadNamespace(package, c(which.lib.loc, lib.loc), keep.source = 
> keep.source) 11: try({ ns <- loadNamespace(package, c(which.lib.loc, 
> lib.loc), keep.source = keep.source) dataPath <- file.path(which.lib.loc, 
> package, "data") env <- attachNamespace(ns, pos = pos, dataPath = 
> dataPath)}) 12: library(package, lib.loc = lib.loc, character.only = TRUE, 
> logical = TRUE, warn.conflicts = warn.conflicts, keep.source = keep.source, 
> version = version) 13: require(pkg, quietly = TRUE, warn.conflicts = FALSE, 
> character.only = TRUE, save = FALSE) 14: .First.sys()
>
> Possible actions:
> 1: abort (with core dump)
> 2: normal R exit
> 3: exit R without saving workspace
> 4: exit R saving workspace
> Selection: 14
> aborting ...
> Segmentation fault (core dumped)
>
> The make command fails with :-
>
> make[4]: Leaving directory `/contrib/R-2.4.0/src/library/grDevices/src'
>
>  *** caught segfault ***
> address 4084b2f0, cause 'memory not mapped'
>
> Traceback:
>  1: .Call("La_dgesv", a, b, tol, PACKAGE = "base")
>  2: solve.default(rgb)
>  3: solve(rgb)
>  4: drop(whitexyz %*% solve(rgb))
>  5: make.rgb(red = c(0.625, 0.34), green = c(0.28, 0.595), blue = c(0.155, 
> 0.07), gamma = 1.8, white = "D65", name = "Apple RGB")
>  6: eval(expr, envir, enclos)
>  7: eval(i, envir)
>  8: sys.source(codeFile, env, keep.source = keep.source)
>  9: try(sys.source(codeFile, env, keep.source = keep.source)) 10: 
> loadNamespace(package, lib.loc, keep.source, TRUE, TRUE) 11: 
> code2LazyLoadDB(package, lib.loc = lib.loc, keep.source = keep.source, 
> compress = compress) 12: tools:::makeLazyLoading("grDevices") aborting ... 
> /bin/sh: 18508 Memory fault(coredump) make[3]: *** [all] Error 139 make[3]: 
> Leaving directory `/contrib/R-2.4.0/src/library/grDevices' make[2]: *** [R] 
> Error 1 make[2]: Leaving directory `/contrib/R-2.4.0/src/library' make[1]: 
> *** [R] Error 1 make[1]: Leaving directory `/contrib/R-2.4.0/src' make: *** 
> [R] Error 1
>
> Do not hold out much hope from mailing list, as they did not answer my last
> email, but have included it anyway.
>
>   
"They" might not have had enough information to go on (and r-devel had 
been a better target). Things like OS and computer versions. (I can't 
seem to find the earlier report though).

Looks like you have broken lapack libraries, so you may want to upgrade 
them or override the selection made during the configure phase.

Make sure to read
http://cran.r-project.org/doc/manuals/R-admin.html
and in particular Appendix A3 which discusses some of these issues.

> Cheers
>
> Derek
>
>
> 
>
> Derek McPhee
> Information Services
> Queen's University Belfast
> e-mail [EMAIL PROTECTED]
> Tel 028 90973840
> Fax 028 90975066
>
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.
>

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Weighted averaging partial least squares regression

[Andreas Plank]

Hello, 

is it possible in R to calculate a Weighted averaging partial least
squares regression? I'm not firm in statistics and didn't found anything
about weighted averaging in combination with PLS in the help archives.
Or is it possible to develop a workaround with the pls-package?

thanks for help in advance
Andreas Plank


-- 
_
Dipl. Biol. Andreas Plank 
FU Berlin 
Institute of Geological Science
Department Palaeontology
Malteserstr. 74-100, House D 
12249 Berlin 
Germany 
phone.: +49(0)30-83870-271
fax.:   +49(0)30-83870-745
http://userpage.fu-berlin.de/~jevers/plank_a.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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] FW: R

[Da . McPhee]

Hi Ricky / AJ

Progress of sorts. I got passed the last problem by looking at the makefiles
but run in to the next one, see below. 

It has created files in /contrib/R-2.4.0. there is an " R " under 
/contrib/R-2.4.0/bin/R.

Running it gives :-


/contrib/R-2.4.0/bin/R

R version 2.4.0 (2006-10-03)
Copyright (C) 2006 The R Foundation for Statistical Computing
ISBN 3-900051-07-0

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.


 *** caught segfault ***
address 40b843f0, cause 'memory not mapped'

Traceback:
 1: .Call("La_dgesv", a, b, tol, PACKAGE = "base")
 2: solve.default(rgb)
 3: solve(rgb)
 4: drop(whitexyz %*% solve(rgb))
 5: make.rgb(red = c(0.625, 0.34), green = c(0.28, 0.595), blue = c(0.155, 
0.07), gamma = 1.8, white = "D65", name = "Apple RGB")
 6: eval(expr, envir, enclos)
 7: eval(i, envir)
 8: sys.source(codeFile, env, keep.source = keep.source)
 9: try(sys.source(codeFile, env, keep.source = keep.source)) 10: 
loadNamespace(package, c(which.lib.loc, lib.loc), keep.source = 
keep.source) 11: try({ ns <- loadNamespace(package, c(which.lib.loc, 
lib.loc), keep.source = keep.source) dataPath <- file.path(which.lib.loc, 
package, "data") env <- attachNamespace(ns, pos = pos, dataPath = 
dataPath)}) 12: library(package, lib.loc = lib.loc, character.only = TRUE, 
logical = TRUE, warn.conflicts = warn.conflicts, keep.source = keep.source, 
version = version) 13: require(pkg, quietly = TRUE, warn.conflicts = FALSE, 
character.only = TRUE, save = FALSE) 14: .First.sys()

Possible actions:
1: abort (with core dump)
2: normal R exit
3: exit R without saving workspace
4: exit R saving workspace
Selection: 14
aborting ...
Segmentation fault (core dumped)

The make command fails with :-

make[4]: Leaving directory `/contrib/R-2.4.0/src/library/grDevices/src'

 *** caught segfault ***
address 4084b2f0, cause 'memory not mapped'

Traceback:
 1: .Call("La_dgesv", a, b, tol, PACKAGE = "base")
 2: solve.default(rgb)
 3: solve(rgb)
 4: drop(whitexyz %*% solve(rgb))
 5: make.rgb(red = c(0.625, 0.34), green = c(0.28, 0.595), blue = c(0.155, 
0.07), gamma = 1.8, white = "D65", name = "Apple RGB")
 6: eval(expr, envir, enclos)
 7: eval(i, envir)
 8: sys.source(codeFile, env, keep.source = keep.source)
 9: try(sys.source(codeFile, env, keep.source = keep.source)) 10: 
loadNamespace(package, lib.loc, keep.source, TRUE, TRUE) 11: 
code2LazyLoadDB(package, lib.loc = lib.loc, keep.source = keep.source, 
compress = compress) 12: tools:::makeLazyLoading("grDevices") aborting ... 
/bin/sh: 18508 Memory fault(coredump) make[3]: *** [all] Error 139 make[3]: 
Leaving directory `/contrib/R-2.4.0/src/library/grDevices' make[2]: *** [R] 
Error 1 make[2]: Leaving directory `/contrib/R-2.4.0/src/library' make[1]: 
*** [R] Error 1 make[1]: Leaving directory `/contrib/R-2.4.0/src' make: *** 
[R] Error 1

Do not hold out much hope from mailing list, as they did not answer my last
email, but have included it anyway.

Cheers

Derek




Derek McPhee
Information Services
Queen's University Belfast
e-mail [EMAIL PROTECTED]
Tel 028 90973840
Fax 028 90975066

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] solving non linear system of eq

[Dieter Menne]

Paulino Perez Rodriguez  colpos.mx> writes:

> How can I solve a non linear system of equations using R?

Have your tried to enter "nonlinear equations" into http://search.r-project.org?

Dieter

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Experimental Design with R

[Eric Rexstad]

Erin:

You may want to examine this PDF in the contributed documentation area 
of R-project:

http://cran.r-project.org/doc/contrib/Vikneswaran-ED_companion.pdf

-- 
Eric Rexstad
Research Unit for Wildlife Population Assessment
Centre for Research into Ecological and Environmental Modelling
University of St. Andrews
St. Andrews Scotland KY16 9LZ
+44 (0)1334 461833

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Switch and integer

[Dieter Menne]

Knut Krueger  einthal.de> writes:

> 
> Switch is working with character , with integer, but not in the third 
> example
... 
> #  not working
test = c(3,9,3,9,3,9,8,9,8,9,8,9,3,9,3,9,5,9,3,9,1,2,7,9,3,9,1,1,
2,2,3,9,2,1,2,5, 9,8,9,1,2)
> count1 <- 0
> for (i in 1:length(test))
>   switch (EXPR=test[i],
>   4 = count1 <- count1 +1,
>   5 = count1 <- count1 +1,
>   6 = count1 <- count1 +1,
>   7 = count1 <- count1 +1,
>   8 = count1 <- count1 +1
>   )
>   count1
> 

switch has a different behavior when an integer is use, which is a bit hidden 
in the term "corresponding". 

"If the value of EXPR is an integer between 1 and nargs()-1 then the
corresponding element of ... is evaluated and the result returned."

So something like the example below might come close to what you want. 
In each case you have to add the default last item to avoid a NULL.

"In the case of no match, if there's a further argument in switch that one 
is returned, otherwise NULL."

Dieter

test =c(4,5,8,1,13)
count1 <- 0
for (i in 1:length(test)) {
  count1 <- switch (EXPR=as.character(test[i]),
  "4" = count1 +1,
  "5" = count1 +1,
  "6" = count1 +1,
  "7" = count1 +1,
  "8" = count1 +1,
  count1
  )
}
count1

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] Switch and integer

[David Barron]

>From the help entry for switch:

If the value of EXPR is an integer between 1 and nargs()-1 then the
corresponding element of ... is evaluated and the result returned.

So, for integers you don't give names to the elements in ...  This should work:

test=c(3,9,3,9,3,9,8,9,8,9,8,9,3,9,3,9,5,9,3,9,1,2,7,9,3,9,1,1,2,2,3,9,2,1,2,5,9,8,9,1,2)
count1 <- 0
for (i in 1:length(test))
 switch(EXPR=test[i],
 NULL,
 NULL,
 NULL,
 count1 <- count1 +1,
 count1 <- count1 +1,
 count1 <- count1 +1,
 count1 <- count1 +1,
 count1 <- count1 +1,
 NULL
 )
 count1


On 11/12/06, Knut Krueger <[EMAIL PROTECTED]> wrote:
> I searched the help list and the manual, but I do not find my mistake.
> Switch is working with character , with integer, but not in the third
> example
>
> Regards Knut
>
>
> count1 <- 0
> test
> =c("3","9","3","9","3","9","8","9","8","9","8","9","3","9","3","9","5","9","3","9","1","2","7","9","3","9","1","1","2","2","3","9","2","1","2","5","9","8","9","1","2")
> count1 <- "0"
> for (i in 1:length(test))
>   switch (EXPR=test[i],
>   "5" = print(test[i]),
>   "6" = print(test[i]),
>   "7" = print(test[i]),
>   "8" = print(test[i]),
>   "9" = print(test[i])
>   )
>   count1
> # example from helpfile
> for(i in c(-1:3,9))  print(switch(i, 1,2,3,4))
>
> #  not working
> test
> =c(3,9,3,9,3,9,8,9,8,9,8,9,3,9,3,9,5,9,3,9,1,2,7,9,3,9,1,1,2,2,3,9,2,1,2,5,9,8,9,1,2)
> count1 <- 0
> for (i in 1:length(test))
>   switch (EXPR=test[i],
>   4 = count1 <- count1 +1,
>   5 = count1 <- count1 +1,
>   6 = count1 <- count1 +1,
>   7 = count1 <- count1 +1,
>   8 = count1 <- count1 +1
>   )
>   count1
>
> __
> 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
> and provide commented, minimal, self-contained, reproducible code.
>


-- 
=
David Barron
Said Business School
University of Oxford
Park End Street
Oxford OX1 1HP

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] barplot - how to force vertical axis to cover entire plot area

[Ricardo Rodríguez - Your XEN ICT Team]

Hi, Etienne,
 
I've seen this while working with barplot and never been able to understand the 
general rule, but by setting ylim high enough, I've always been able to draw a 
y axis covering the biggest values.
 
Could you send a data subset to reproduce the issue? Thanks.
 
Best,
 
Ricardo
 
--
Ricardo Rodríguez
Your XEN ICT Team

>>> Etienne<[EMAIL PROTECTED]> 7/12/2006 01:43 >>>

I'm using barplot with the following call:
  
barplot(stat_data[[5]][,],axes=TRUE,axisnames=TRUE,axis.lty=1,xlab=xlab,ylab=ylab,beside=TRUE,las=1,font.lab=2,font.axis=1,legend.text=TRUE)

On some data, the vertical axis does not cover the
whole plot area and the last tick mark is smaller than
the maximum value.

I tried setting the ylim values but even with that,
some plots are still not OK, it just shrinks the
length of the bars.

Attached is a png example of the problem.  I hope it
gets through.

Thanks,
Etienne

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] Switch and integer

[Knut Krueger]

I searched the help list and the manual, but I do not find my mistake.
Switch is working with character , with integer, but not in the third 
example

Regards Knut


count1 <- 0
test 
=c("3","9","3","9","3","9","8","9","8","9","8","9","3","9","3","9","5","9","3","9","1","2","7","9","3","9","1","1","2","2","3","9","2","1","2","5","9","8","9","1","2")
count1 <- "0"
for (i in 1:length(test))
  switch (EXPR=test[i],
  "5" = print(test[i]),
  "6" = print(test[i]),
  "7" = print(test[i]),
  "8" = print(test[i]),
  "9" = print(test[i])
  )
  count1
# example from helpfile
for(i in c(-1:3,9))  print(switch(i, 1,2,3,4))

#  not working
test 
=c(3,9,3,9,3,9,8,9,8,9,8,9,3,9,3,9,5,9,3,9,1,2,7,9,3,9,1,1,2,2,3,9,2,1,2,5,9,8,9,1,2)
count1 <- 0
for (i in 1:length(test))
  switch (EXPR=test[i],
  4 = count1 <- count1 +1,
  5 = count1 <- count1 +1,
  6 = count1 <- count1 +1,
  7 = count1 <- count1 +1,
  8 = count1 <- count1 +1
  )
  count1

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] R2WinBUGS and calling WinBUGS in Crossover MAC BETA

[Kenneth Benoit]

Ben Bolker wrote:
> Kenneth Benoit  tcd.ie> writes:
> 
>> Hi there - I have a question for any of you who use R2WinBUGS to call 
>> WinBUGS using the useWINE option in that package.
>>
>> I have Codeweaver's Crossover emulator installed on my Intel Mac with 
>> WinBUGS working fine if I start it from Crossover.  But there is 
>> supposed to be a way to start it directly from a command line, which I 
>> could pass to the R2WinBUGS using the bugs(..., useWINE="something") 
>> argument.
>>
>> Has anyone tried this yet?  Thanks!
>>
> 
>useWINE=TRUE.  You may have to set some environment
> variables (e.g. WINE is the path to your WINE executable).
> It's supposed to just work out of the box.  I have some
> fixes that I've been meaning to upload to complement
> the existing stuff, but haven't.  If you run into
> trouble drop me a line.
> 
>  Ben Bolker

Many thanks for that quick reply.  I have tried useWINE=TRUE but this 
does not work on the Mac.  I am using CrossOver for Mac Beta (6.0.0b2). 
  When I call:

bugs(..., useWINE=TRUE, newWINE=TRUE)

then I get this message:
Error in if (!nchar(WINEPATH)) { : argument is of length zero

I think the problem is that the command line call for cxoffice (similar 
to "wine") is different on the Mac from the Linux version.  For instance 
I have the following application bundles:

/Applications/CrossOver.app/
~/Applications/CrossOver/WinBUGS14.app

but I cannot figure out how to start WinBUGS14.app from the command 
line.  If I did then I could supply this command to bugs(..., WINE="").

Best,

Ken

__
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
and provide commented, minimal, self-contained, reproducible code.

Re: [R] cohen kappa for two-way table

[Jim Lemon]

Dylan Beaudette wrote:
> Greetings,
> 
> I am a bit confused by the results returned by the functions:
> cohen.kappa {concord}
> classAgreement {e1071}
> 
> when using a two-way table.
> 
> 
> for example, if I have an matrix A, and a similar matrix B (same
> dimensions), then:
> 
> matrix A and B can be found:
> http://casoilresource.lawr.ucdavis.edu/drupal/files/a_40.txt
> http://casoilresource.lawr.ucdavis.edu/drupal/files/b_40.txt
> 
> A <- matrix(unlist( read.table('a_40.txt'), use.names=FALSE), ncol=14)
> B <- matrix(unlist( read.table('b_40.txt'), use.names=FALSE), ncol=14)
> 
If I interpret this correctly, you are considering the numbers in A and 
B to be nominal variables representing levels of some data attribute.
What cohen.kappa wants is:

1(type=counts) a matrix of counts where each cell represents the number 
of methods (rows are different methods) that classified the data objects 
into levels (columns are different levels).
2(type=scores) a matrix of scores where each cell represents the level 
assigned by a method (rows again) to a data object (columns are data 
objects here).

If your numbers are counts, you can get a sensible kappa for _each_ matrix.
If your numbers are scores, you can get a sensible kappa by specifying 
type=scores for _each_ matrix
As far as I can see, you are computing a sparsely populated table of the 
two matrices and passing that, and I don't see how that can give a 
meaningful result. I suspect that the numbers might be counts in the 
first place, but they are being used as scores.

> Secondly, when using the classAgreements() function I get different numbers:
> 
I'll let someone who knows more about the classAgreement function deal 
with this.

Jim

__
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
and provide commented, minimal, self-contained, reproducible code.

[R] two ggplot and colour=x question

[Rainer M Krug]

Hi

I am using ggplot with the aesthetic=list(..., colour=x, ...)

ggplot()
ggline()

I have four different values in x ("ren", "cyn", "mixed", "bare") and I 
have two questions

1) I would like to assign specific colours to the values, i.e. green, 
red, blue and brown. How can I do this? I did not understand 
map_colour_brewer.

2) I don't want the legend top be plot. How can I disable the legend to 
be plotted?

Thanks

Rainer

-- 
Rainer M. Krug, Dipl. Phys. (Germany), MSc Conservation
Biology (UCT)

Department of Conservation Ecology and Entomology
University of Stellenbosch
Matieland 7602
South Africa

Tel:+27 - (0)72 808 2975 (w)
Fax:+27 - (0)86 516 2782
Fax:+27 - (0)21 808 3304 (w)
Cell:   +27 - (0)83 9479 042

email:  [EMAIL PROTECTED]
[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
and provide commented, minimal, self-contained, reproducible code.