Re: [R] Puzzled at lm() and time-series

[Ajay Shah]

> > Any idea why? I think both objects are quite conformable (except for
> > an NA, but that should get dropped by lm() by default).
> 
> That's the problem: the row with a NA gets dropped but the tsp atribute
> does not get adjusted.

Thanks! :-)

> BTW, try traceback() when you get an error.
> 
> lm(g.cpi.iw ~ g.wpi, data = na.omit(M))

Will do.

> I think it was a leap to assume that you could fit linear models to time 
> series via lm.  ts objects are not mentioned on the help page for lm, are 
> they?  Another trap is to assume that diff() will be respected by lm.

My general attitude in R is "if it sounds reasonable, then it ought to
work". :-) I did do a toy example (which was there in the previous
post) and that worked fine, so I jumped to the conclusion that the
internals are all conformable.

If OLS regressions involving ts objects is not 'officially' supported,
what is the recommended way of going about them? Is there an "unts()"
operator which will take me back to raw data? I like to call things
ts() because it gives me prettier graphs.

On diff() also, I have an instinctive confidence that you guys will
have touched up everything perfectly, so if
x = ts()
y = ts()
lm(y ~ x)
works, then
dx = diff(x,1)
dy = diff(y,1)
lm(dy ~ dx)
should also work perfectly. :-)

-- 
Ajay Shah   Consultant
[EMAIL PROTECTED]  Department of Economic Affairs
http://www.mayin.org/ajayshah   Ministry of Finance, New Delhi

__
[EMAIL PROTECTED] 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] Puzzled at lm() and time-series

[Prof Brian Ripley]

On Mon, 23 Aug 2004, Ajay Shah wrote:

> > > Any idea why? I think both objects are quite conformable (except for
> > > an NA, but that should get dropped by lm() by default).
> > 
> > That's the problem: the row with a NA gets dropped but the tsp atribute
> > does not get adjusted.
> 
> Thanks! :-)
> 
> > BTW, try traceback() when you get an error.
> > 
> > lm(g.cpi.iw ~ g.wpi, data = na.omit(M))
> 
> Will do.
> 
> > I think it was a leap to assume that you could fit linear models to time 
> > series via lm.  ts objects are not mentioned on the help page for lm, are 
> > they?  Another trap is to assume that diff() will be respected by lm.
> 
> My general attitude in R is "if it sounds reasonable, then it ought to
> work". :-) 

You get what you pay for, don't forget.  Telling the donor what a free
gift `ought' or `should' do is discourteous at best.


If you want to use lm on time series, do a ts.intersect to create a 
suitable data frame first, then call na.omit.

If you get an error you don't understand, R's debugging facilities will 
help you find what you didn't understand.  Please learn to use them.

-- 
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

__
[EMAIL PROTECTED] 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 factor ANOVA with lm()

[Trenkler, Dietrich]

The following is a data frame


> "jjd" <- structure(list(Observations = c(6.8, 6.6, 5.3, 6.1,
  7.5, 7.4, 7.2, 6.5, 7.8, 9.1, 8.8, 9.1), LevelA = structure(c(1,
  1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3), .Label = c("A1", "A2",
  "A3"), class = "factor"), LevelB = structure(c(1, 1, 2, 2,
  1, 1, 2, 2, 1, 1, 2, 2), .Label = c("B1", "B2"), class = "factor")),
  .Names = c("Observations", "LevelA", "LevelB"), row.names = c("1",
  "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12"),
  class = "data.frame")

representing data from


@BOOK{Dobson02,
  author = {Annette J. Dobson},
  year = 2002,
  title = {An Introduction to Generalized Linear Models},
  edition = {2.},
  publisher = {Chapman \& Hall/CRC},
  address = {Boca Raton, Florida, 33431}
}

page 101. To reproduce the estimates c(6.7,0.75,1.75,-1.0,0.4,1.5)
given on page 103 in a two factor ANOVA  entering


> jja1 <- lm(Observations~LevelA*LevelB,data=jjd)
> summary(jja1)

I get


Call:
lm(formula = Observations ~ LevelA * LevelB, data = jjd)

Residuals:
   Min 1Q Median 3QMax
-6.500e-01 -2.000e-01 -3.469e-17  2.000e-01  6.500e-01

Coefficients:
  Estimate Std. Error t value Pr(>|t|)
(Intercept) 6.7000 0.3512  19.078 1.34e-06 ***
LevelAA20.7500 0.4967   1.510   0.1818
LevelAA31.7500 0.4967   3.524   0.0125 *
LevelBB2   -1. 0.4967  -2.013   0.0907 .
LevelAA2:LevelBB2   0.4000 0.7024   0.569   0.5897
LevelAA3:LevelBB2   1.5000 0.7024   2.136   0.0766 .
---
Signif. codes:  0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1

Residual standard error: 0.4967 on 6 degrees of freedom
Multiple R-Squared: 0.9065, Adjusted R-squared: 0.8286
F-statistic: 11.64 on 5 and 6 DF,  p-value: 0.00481


This is fine. But why do I get these estimates?


Entering

> model.matrix(jja1)

delivers


   (Intercept) LevelAA2 LevelAA3 LevelBB2 LevelAA2:LevelBB2
LevelAA3:LevelBB2
11000 0
0
21000 0
0
31001 0
0
41001 0
0
51100 0
0
61100 0
0
71101 1
0
81101 1
0
91010 0
0
10   1010 0
0
11   1011 0
1
12   1011 0
1
attr(,"assign")
[1] 0 1 1 2 3 3
attr(,"contrasts")
attr(,"contrasts")$LevelA
[1] "contr.treatment"

attr(,"contrasts")$LevelB
[1] "contr.treatment"


which shows that internally lm() seems to use corner point constraints
of the form

\[\alpha_1=\beta_1=(\alpha\beta)_{11}=
(\alpha\beta)_{12}=(\alpha\beta)_{12}=(\alpha\beta)_{31}=0\]


in the model $E[Y_{jkl}]=\mu+\alpha_j+\beta_k+(\alpha\beta)_{jk}$
$j=1,2,3$, $k=1,2$, $l=1,2$, Dobson, page 102.


My question is:  how can I incorporate restrictions like
$\alpha_1+\alpha_2+\alpha_3=0$, $\beta_1+\beta_2=0$,
$(\alpha\beta)_{21}+\alpha\beta)_{22}=0$,
$(\alpha\beta)_{31}+(\alpha\beta)_{32}=0$ and
$(\alpha\beta)_{11}+(\alpha\beta)_{21}+(\alpha\beta)_{31}=0$ from the
outset?  Or put another way:  Why is it that lm() uses the corner point
constraints by default?  Where can I find a documentation for this
behavior?

I know that I can use something like lm(y~X) where y <- c(6.8, 6.6,
5.3, 6.1, 7.5, 7.4, 7.2, 6.5, 7.8, 9.1, 8.8, 9.1) and X is an
appropriate design matrix.  But I wonder if there is a more direct way.


Many thanks in advance.

D. Trenkler 


--
Dietrich Trenkler   Universität Osnabrück  
FB Wirtschaftswissenschaften   
Rolandstr.8  D-49069 Osnabrück

[EMAIL PROTECTED]

__
[EMAIL PROTECTED] 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] Installing R on DEC Alpha - problems with dynamic loading

[Firth, Mike A (ALDP)]

I have recently installed R on DEC Alpha OSF 5.1.

The first regression test (reg-test-1.R) failed with an unresolved symbol in
lapack.so:

2246839:/data/h1/bifdev/apps/wga/R-1.9.1/bin/R.bin: /sbin/loader: Fatal
Error: call to unresolved symbol from
/data/h1/bifdev/apps/wga/R-1.9.1/modules/lapack.so (pc=0x3ffbfe22b60)

Further investigation has revealed that there is NO problem with lapack.so.
The problem seems to lie in the use of 'unloadNamespace' earlier in the
script.

On our machine the following line:

unloadNamespace(splines)

seem to really confuse the dynamic linking/symbol resolution. I have a very
small example to demonstrate:

data(iris)
library(splines)
unloadNamespace(splines)
data(iris)

works fine, but:

library(splines)
unloadNamespace(splines)
data(iris)

falls over with:

Error in dyn.load(x, as.logical(local), as.logical(now)) : 
unable to load shared library
"/data/h1/bifdev/apps/wga/R-1.9.1/library/tools/libs/tools.so":
  dlopen: /data/h1/bifdev/apps/wga/R-1.9.1/library/stats/libs/stats.so:
symbol "bdrsplerr_" unresolved
Execution halted

The unloadNamespace has effectively unloaded a symbol from a completely
different shared object.

Can anybody shed any light on this problem?

Thanks.
-
Mike Firth
Senior Technical Specialist
AstraZeneca Pharmaceuticals
Mereside
Alderley Park
Macclesfield
Cheshire
SK10 3LT

Tel: 01625 513919

__
[EMAIL PROTECTED] 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 factor ANOVA with lm()

[Trenkler, Dietrich]

> -Original Message-
> From: Prof Brian Ripley 
> Sent: Monday, August 23, 2004 1:15 PM
> To:   Trenkler, Dietrich
> Subject:  Re: [R] Two factor ANOVA with lm()
> 
> On Mon, 23 Aug 2004, Trenkler, Dietrich wrote:
> 
> [...]
> 
> > outset?  Or put another way:  Why is it that lm() uses the corner point
> > constraints by default?  Where can I find a documentation for this
> > behavior?
> 
> In almost any piece of documentation on linear models in R, including the
> FAQ and `An Introduction to R', which says
> 
>   The main reason for mentioning this is that R and S have different
>   defaults for unordered factors, S using Helmert contrasts.  So if you 
>   need to compare your results to those of a textbook or paper which used
>   S-PLUS, you will need to set
> 
> options(contrasts = c("contr.helmert", "contr.poly"))
> 
>   This is a deliberate difference, as treatment contrasts (R's default)
>   are thought easier for newcomers to interpret.
> 
> Now, what does the posting guide say about doing your homework?
 
[Dietrich Trenkler]  I swear I didn't need it for a homework.
I just overlooked the self-evident... (blush)

Thank you.

D. Trenkler

__
[EMAIL PROTECTED] 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] convert strings to object names: SUMMARY

[Gudrun Jonasdottir]

Dear R-list,

Apologies for replying late. Thanks to Andy, Dimitris, James, Uwe, Olaf,
Adai, Gardar and Patrick. (Apologies if I forgot someone)

In summary: The quickest way to convert a string to an object name, seems
to be by using get(dat), but it seems to work equally well if you use any
of

eval(parse(text=dat))
do.call("print", list(as.name(dat)))
eval(substitute(print(x), list(x=as.name(dat
assign("dat", get(paste("dat", no, sep="")))

Thanks again,
Gudrun

Gardar Johannessonwrote:
> Use the get() function:
>
>  > dat99 <- matrix(c(1,1,2),3,3)
>  > no <- 99
>  > dat.name <- paste("dat",no,sep="")
>  > get(dat.name)
>   [,1] [,2] [,3]
> [1,]111
> [2,]111
> [3,]222
>  >
>
>
> At 04:15 PM 8/19/2004 +0200, Gudrun Jonasdottir wrote:
>>Dear R-Help list,
>>
>>I have a problem with convertions of strings. I want to use the function
>>"paste()" to create an object name and then use that character string to
>>call on that object. So, for example:
>>
>>dat99 <- matrix(rbind(1,1,2),3,3)
>>no <- 99
>>dat <- paste("dat",no,sep="")
>>dat
>>[1] "dat99"
>>
>>What should I do to get the output
>>
>>dat
>>  [,1] [,2] [,3]
>>[1,]111
>>[2,]111
>>[3,]222
>>
>>Cheers,
>>Gudrun
>>
>>
>>
>>--
>>Gudrun Jonasdottir, M.Sc.
>>Matematiska institutionen
>>Stockholms Universitet
>>SE- 106 91 Stockholm
>>
>>Work: +46 (0)8 16 45 56
>>Mobile: +46 (0)709 779 800
>>
>>__
>>[EMAIL PROTECTED] mailing list
>>https://stat.ethz.ch/mailman/listinfo/r-help
>>PLEASE do read the posting guide!
>> http://www.R-project.org/posting-guide.html
>
>

__
[EMAIL PROTECTED] 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] Statistical help about backets analisys

[Kaminer, Oren]

Hi 

I'm a student in the Technion institute 

I would appreciate if you could help me in question I have encountered
while writing my final project.

 

In the project I am using the buckets analysis in order to find, what
products I should recommend to a person who bought 3 products already.

 

 

My question for you his this 

Is the following lift condition is correct when using the buckets
analysis?

P(A^B^C^D) / (P(A)*P(B^C^D)

 

--> When: A^B equal A and B 

 

 

 


[[alternative HTML version deleted]]

__
[EMAIL PROTECTED] 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] [Job Ad] Position at Merck Research Laboratories, NJ USA

[Pikounis, Bill]

Please accept my apologies for cross-posting to those subscribed to both
R-help and S-news.

Also, please direct *all* inquiries to Vladimir Svetnik, the hiring manager.
His contact information is below.

Thanks,
Bill



Job description:  Computational statistician/biometrician   

The Biometrics Research Department at Merck Research Laboratories, Merck &
Co., Inc. in Rahway, NJ, is seeking a highly motivated statistician/data
analyst to work in its basic research and drug discovery area.  The
applicant should have broad expertise in statistical computing.   Experience
and/or education relevant to signal processing, image processing, pattern
recognition and machine learning are preferred.  The position will involve
providing statistical, mathematical, and software development support for
one or more of following areas: medical imaging, biological signal analysis,
and computational chemistry.   We are looking for a Ph.D. with a background
and/or post-doctoral experience in at least one of the following fields:
Statistics, Electrical/Computer or Biomedical Engineering, Computer Science,
Applied Mathematics, or Physics.   Advanced computer programming skills
(including, but not limited to R, Splus, Matlab, C/C++) and excellent
communication skills are essential. An ability to lead statistical analysis
efforts within a multidisciplinary team is required.   The position may also
involve general statistical consulting and training.

Our dedication to delivering quality medicines in innovative ways and our
commitment to bringing out the best in our people are just some of the
reasons why we're ranked among Fortune magazine's "100 Best Companies to
Work for in America."  We offer a competitive salary, an outstanding
benefits package, and a professional work environment with a company known
for scientific excellence.  To apply, please forward your CV or resume and
cover letter to

ATTENTION: Open Position  
Vladimir Svetnik, Ph.D.  
Biometrics Research Dept.  
Merck Research Laboratories
RY33-300
126 E. Lincoln Avenue
Rahway, NJ 07065-0900 
[EMAIL PROTECTED]

__
[EMAIL PROTECTED] 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] C++ classes as opaque types in R

[Heiko Schaefer]

Dear all,

suppose I would have an abstract class in C++ representing some
complex type. Is it possible to expose a selected C++ interface
to R while retaining all the gory details within C++. Other 
scripting languages have the concept of an opaque pointer and
constructor/destructor hooks, so that the scripting language's
garbage collection can clean up (e.g. Python). Is there anything
like this in R?

Thanks a lot,
Heiko

__
[EMAIL PROTECTED] 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] The "Green" Book?

[Sam Chapman]

Thank you for your responses. I should have mentioned that I am new to R, but
not to programming. Nevertheless, the insights are valued and appreciated!


Quoting Prof Brian Ripley <[EMAIL PROTECTED]>:

> On Fri, 20 Aug 2004, Thomas Lumley wrote:
>
> > On Fri, 20 Aug 2004, Sam Chapman wrote:
> >
>
> [A quote from `An Introduction to R' has been excised here]
>
> > > There is no mention of 'Programming with Data: A Guide to the S Language'
> by
> > > John M. Chambers. Is this newest ("Green") book also suitable as a
> reference
> > > for R? Thank you for your time and attention!
> > >
> >
> > Yes. The system implemented in the "methods" package is not identical to
> > that in the Green Book, but it's pretty similar.
>
> Well, it is suitable as reference for programmers using the "methods"
> package in R, not quite the question asked.  At the level of `An
> Introduction to R' it is not really a suitable reference as it has limited
> coverage at that level.  (The Green Book itself recommends other books for
> end users.)
>
> --
> 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
>
>


Sincerely,

Sam Chapman

__
[EMAIL PROTECTED] 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] unsubscribe to R-help

[Betten, Mark]

I would like to unsubscribe to the R help list so that my email box
doesn't get so full.  I've tried several times to unsubscribe at
r-project.org, but I keep getting emails.  How do I successfully
unsubscribe?  Thanks

 

Mark


This email message, including any attachments, is for the so...{{dropped}}

__
[EMAIL PROTECTED] 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] Reading GAL file

[Mihai Nica]

Greetings:

I am trying to work with spdep (everything is "brand new" downloaded this morning). OS 
= Windows 2000 (also up to date). The code I am using follows:

#example

gal.county=read.geoda("lnpilnd.GAL", row.names=NULL, skip=0) 
summary.nb(gal.county)
Error in summary.nb(gal.county) : Not a neighbours list

#end

The gal file works just fine in GeoDa (also up to date). 

Thanks, I am really stuck here.

Mihai Nica
Jackson State University
155 B Parkhurst Dr.
Jackson, MS 39202
601 969 5423
[[alternative HTML version deleted]]

__
[EMAIL PROTECTED] 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] unsubscribe to R-help

[Peter Dalgaard]

"Betten, Mark" <[EMAIL PROTECTED]> writes:

> I would like to unsubscribe to the R help list so that my email box
> doesn't get so full.  I've tried several times to unsubscribe at
> r-project.org, but I keep getting emails.  How do I successfully
> unsubscribe?  Thanks
...
> [EMAIL PROTECTED] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help

Did you visit that page? (not r-project.org...)

Did you receive a confirmation request? And reply to it? (I think you
need that. I don't often unsubscribe myself...)

Did you wait long enough? If you unsubscribe, you will get removed
from the list of recipients for any new messages, but things that are
already in outgoing mail folders will not be actively removed from the
server.

-- 
   O__   Peter Dalgaard Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics 2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark  Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907

__
[EMAIL PROTECTED] 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] Siegel-Tukey test

[Jürgen Hedderich]

Hello R friends,
I am looking for a function to perform the Siegel-Tukey test in R.
Can anyvbody help me? Thanks so much!
J. Hedderich
--
---
Dipl. Inform. J. Hedderich
Institut für Medizinische Informatik und
Statistik im Klinikum S.H. - Campus Kiel -
   Phone : 0431/5973182
Brunswiker Str. 10   Fax : 0431/5973193
24105 KielE-mail: [EMAIL PROTECTED]
__
[EMAIL PROTECTED] 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] unsubscribe to R-help

[Almirall, Daniel]

R-help is a pretty incredible service.  Are you sure you would like to unsubscribe?

If you have concerns about your inbox getting so full, you may want to try a FILTER of 
some sort--Pine, Outlook, Eudora, etc... all of these have this option.  You can have 
all emails with "[R]" in the subject line routed to your very own "R-help Folder" 
(which you can create).  Then visit that folder whenever you want to get in on a good 
convo or learn new tricks.

CheeRs, Danny




-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Behalf Of Peter Dalgaard
Sent: Monday, August 23, 2004 11:01 AM
To: Betten, Mark
Cc: [EMAIL PROTECTED]
Subject: Re: [R] unsubscribe to R-help


"Betten, Mark" <[EMAIL PROTECTED]> writes:

> I would like to unsubscribe to the R help list so that my email box
> doesn't get so full.  I've tried several times to unsubscribe at
> r-project.org, but I keep getting emails.  How do I successfully
> unsubscribe?  Thanks
.
> [EMAIL PROTECTED] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help

Did you visit that page? (not r-project.org...)

Did you receive a confirmation request? And reply to it? (I think you
need that. I don't often unsubscribe myself...)

Did you wait long enough? If you unsubscribe, you will get removed
from the list of recipients for any new messages, but things that are
already in outgoing mail folders will not be actively removed from the
server.

-- 
   O__   Peter Dalgaard Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics 2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark  Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907

__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

__
[EMAIL PROTECTED] 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] unsubscribe to R-help

[Roger D. Peng]

There is also a digest option which is only mailed once daily.
-roger
Almirall, Daniel wrote:
R-help is a pretty incredible service.  Are you sure you would like to unsubscribe?
If you have concerns about your inbox getting so full, you may want to try a FILTER of some sort--Pine, 
Outlook, Eudora, etc... all of these have this option.  You can have all emails with "[R]" in 
the subject line routed to your very own "R-help Folder" (which you can create).  Then visit 
that folder whenever you want to get in on a good convo or learn new tricks.
CheeRs, Danny

-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Behalf Of Peter Dalgaard
Sent: Monday, August 23, 2004 11:01 AM
To: Betten, Mark
Cc: [EMAIL PROTECTED]
Subject: Re: [R] unsubscribe to R-help
"Betten, Mark" <[EMAIL PROTECTED]> writes:

I would like to unsubscribe to the R help list so that my email box
doesn't get so full.  I've tried several times to unsubscribe at
r-project.org, but I keep getting emails.  How do I successfully
unsubscribe?  Thanks
.
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help

Did you visit that page? (not r-project.org...)
Did you receive a confirmation request? And reply to it? (I think you
need that. I don't often unsubscribe myself...)
Did you wait long enough? If you unsubscribe, you will get removed
from the list of recipients for any new messages, but things that are
already in outgoing mail folders will not be actively removed from the
server.
__
[EMAIL PROTECTED] 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] unsubscribe to R-help

[Martin Maechler]

> "Roger" == Roger D Peng <[EMAIL PROTECTED]>
> on Mon, 23 Aug 2004 11:37:57 -0400 writes:

Roger> There is also a digest option which is only mailed once daily.
Roger> -roger

and there's an option to 
"don't get mail for the time being"
which I really recommend for people going away for a while who
don't even want to receive daily digests.

You can unset that option when you come back
(more easily than subscribe anew) and it gives a bit better
statistics about the number of R-help subscribers ;-)

-- and BTW: messages like the original shouldn't even make it to
   be posted the list; I do try trashing them before they waste everyone's
   time. At least subscribers should find out where to send such
   mails.  But this one slipped through my filters ...

Martin Maechler {Mailing list maintainer}


Roger> Almirall, Daniel wrote:

>> R-help is a pretty incredible service.  Are you sure you
>> would like to unsubscribe?

>> If you have concerns about your inbox getting so full, you may want to try a 
FILTER of some sort--Pine, Outlook, Eudora, etc... all of these have this option.  You 
can have all emails with "[R]" in the subject line routed to your very own "R-help 
Folder" (which you can create).  Then visit that folder whenever you want to get in on 
a good convo or learn new tricks.
>> 
>> CheeRs, Danny
>> 
>> 
>> 
>> 
>> -Original Message-
>> From: [EMAIL PROTECTED]
>> [mailto:[EMAIL PROTECTED] Behalf Of Peter Dalgaard
>> Sent: Monday, August 23, 2004 11:01 AM
>> To: Betten, Mark
>> Cc: [EMAIL PROTECTED]
>> Subject: Re: [R] unsubscribe to R-help
>> 
>> 
>> "Betten, Mark" <[EMAIL PROTECTED]> writes:
>> 
>> 
>>> I would like to unsubscribe to the R help list so that my email box
>>> doesn't get so full.  I've tried several times to unsubscribe at
>>> r-project.org, but I keep getting emails.  How do I successfully
>>> unsubscribe?  Thanks
>> 
>> .
>> 
>>> [EMAIL PROTECTED] mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-help
>> 
>> 
>> Did you visit that page? (not r-project.org...)
>> 
>> Did you receive a confirmation request? And reply to it? (I think you
>> need that. I don't often unsubscribe myself...)
>> 
>> Did you wait long enough? If you unsubscribe, you will get removed
>> from the list of recipients for any new messages, but things that are
>> already in outgoing mail folders will not be actively removed from the
>> server.

__
[EMAIL PROTECTED] 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] sample selection problem, inverse mills ratio (Heckman, Lewbel, ...)

[Arne Henningsen]

Hi,

I think you have to do these estimations "by hand". However, this shouldn't be 
too difficult. For instance the first step of the 2-step Heckman estimation 
is a probit estimation that can by done in R by 
   glm(  ... , family=binomial(link=probit))
(see ?glm). And the second step is a simple OLS regression.

All the best,
Arne


On Thursday 19 August 2004 11:45, Wildi Marc, wia wrote:
>  -Ursprüngliche Nachricht-
>  Von: Wildi Marc, wia
>  Gesendet: Mittwoch, 18. August 2004 10:11
>  An: [EMAIL PROTECTED]
>  Betreff:
>
>
>  Hi
>
>  Does anybody know from an R-package devoted to sample selection problems
> (Heckman's lambda, Lewbel, ...)?
>
>  Thanks and best regards
>
>  Marc Wildi
>
>
>
>
>  [[alternative HTML version deleted]]
>
> __
> [EMAIL PROTECTED] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html

-- 
Arne Henningsen
Department of Agricultural Economics
University of Kiel
Olshausenstr. 40
D-24098 Kiel (Germany)
Tel: +49-431-880 4445
Fax: +49-431-880 1397
[EMAIL PROTECTED]
http://www.uni-kiel.de/agrarpol/ahenningsen/

__
[EMAIL PROTECTED] 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] Reading GAL file

[Roger Bivand]

On Mon, 23 Aug 2004, Mihai Nica wrote:

> Greetings:
> 
> I am trying to work with spdep (everything is "brand new" downloaded
> this morning). OS = Windows 2000 (also up to date). The code I am using
> follows:
> 
> #example
> 
> gal.county=read.geoda("lnpilnd.GAL", row.names=NULL, skip=0) 

Well, if you look at the help page for read.geoda() and read.gal(), you 
may see that read.gal() is what you use for reading the GAL file, and 
read.geoda() is just there as an easy way of using read.csv() for data 
files on the CSISS server. I can see that the help page could be clearer, 
it will be in the next release.

> summary.nb(gal.county)
> Error in summary.nb(gal.county) : Not a neighbours list
> 
> #end
> 
> The gal file works just fine in GeoDa (also up to date). 
> 
> Thanks, I am really stuck here.
> 
> Mihai Nica
> Jackson State University
> 155 B Parkhurst Dr.
> Jackson, MS 39202
> 601 969 5423
>   [[alternative HTML version deleted]]
> 
> __
> [EMAIL PROTECTED] 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, Breiviksveien 40, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93
e-mail: [EMAIL PROTECTED]

__
[EMAIL PROTECTED] 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] Reading GAL file

[Mihai Nica]

Oh, that was easy, THANKS!

Mihai Nica
Jackson State University
155 B Parkhurst Dr.
Jackson, MS 39202
601 969 5423
- Original Message - 
From: "Roger Bivand" <[EMAIL PROTECTED]>
To: "Mihai Nica" <[EMAIL PROTECTED]>
Cc: <[EMAIL PROTECTED]>
Sent: Monday, August 23, 2004 11:19 AM
Subject: Re: [R] Reading GAL file


> On Mon, 23 Aug 2004, Mihai Nica wrote:
>
> > Greetings:
> >
> > I am trying to work with spdep (everything is "brand new" downloaded
> > this morning). OS = Windows 2000 (also up to date). The code I am using
> > follows:
> >
> > #example
> >
> > gal.county=read.geoda("lnpilnd.GAL", row.names=NULL, skip=0)
>
> Well, if you look at the help page for read.geoda() and read.gal(), you
> may see that read.gal() is what you use for reading the GAL file, and
> read.geoda() is just there as an easy way of using read.csv() for data
> files on the CSISS server. I can see that the help page could be clearer,
> it will be in the next release.
>
> > summary.nb(gal.county)
> > Error in summary.nb(gal.county) : Not a neighbours list
> >
> > #end
> >
> > The gal file works just fine in GeoDa (also up to date).
> >
> > Thanks, I am really stuck here.
> >
> > Mihai Nica
> > Jackson State University
> > 155 B Parkhurst Dr.
> > Jackson, MS 39202
> > 601 969 5423
> > [[alternative HTML version deleted]]
> >
> > __
> > [EMAIL PROTECTED] 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, Breiviksveien 40, N-5045 Bergen,
> Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93
> e-mail: [EMAIL PROTECTED]
>
>
>

__
[EMAIL PROTECTED] 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] More precision problems in testing with Intel compilers

[Samuelson, Frank*]

I've put up the test problems I had with 'alternate' compilers at
http://www.merrill-samuelson.com/tmp

One is the d-p-q-r test output, and one is the complete print-tests.Rout
file.

I also put up a couple of failures from the reg-tests-1 file.
Even if you don't change anything else, one of these _needs_ changing.
There's a == comparison from the output of 2 different glm calls that
fails because the operands differ by
1/2 unit of machine precision.  (I added some digits to the print 
statements for more info.)  I'd recommend an all.equal() here.

And last, all the < 100*.Machine$double.eps comparisons in nafns.R appear to
fail by a factor of about 2.5.  There are some examples with extra prints.

-Frank


-Original Message-
From: Martin Maechler [mailto:[EMAIL PROTECTED] 
Sent: Friday, August 20, 2004 6:39 PM
To: Samuelson, Frank*
Cc: '[EMAIL PROTECTED] '
Subject: RE: [R] More precision problems in testing with Intel compilers


> "FrankSa" == Samuelson, Frank* 
> on Thu, 19 Aug 2004 16:22:11 -0400 writes:

FrankSa> The Intel compiled version also fails the below test:

here you give the desired output.
What does your 'Intel compiled R' return instead?

>> ### Very big and very small
>> umach <- unlist(.Machine)[paste("double.x", c("min","max"), sep='')]
>> xmin <- umach[1]
>> xmax <- umach[2]
>> tx <- unique(outer(-1:1,c(.1,1e-3,1e-7)))# 7 values  (out of 9)
>> tx <- unique(sort(c(outer(umach,1+tx# 11 values  (out of 14)
>> tx <- tx[is.finite(tx)] #-- all kept
>> (txp <- tx[tx >= 1])#-- Positive exponent -- 4 values
 [1] 1.617924e+308 1.795895e+308 1.797693e+308 1.797693e+308
>> (txn <- tx[tx <1])#-- Negative exponent -- 7 values
[1] 2.002566e-308 2.222849e-308 2.225074e-308 2.225074e-308
2.225074e-308 2.227299e-308 2.447581e-308

FrankSa> Does anyone really care about being correct to 1
FrankSa> unit of machine precision?  If you do, you have a
FrankSa> bad algorithm.  ??

We have had these tests there for a long time now and haven't
heard of failures before..  so this is interesting.
DIG(7) makes us only look at 7 digits which is less than half machine
precision, but then there's cancellation of another 7 digits in
some of those above which gets in the region of machine precision,
(but still leaves a factor of ~= 45).

Can you upload the full print-test.Rout file somewhere?

Regards,
Martin


FrankSa> -Original Message-
FrankSa> From: Samuelson, Frank* [mailto:[EMAIL PROTECTED] 
FrankSa> Sent: Thursday, August 19, 2004 12:11 PM
FrankSa> To: '[EMAIL PROTECTED] '
FrankSa> Subject: [R] precision problems in testing with Intel compilers


FrankSa> I compiled the 1.9.1 src.rpm with the standard gnu tools and it
works.
FrankSa> I tried compiling the 1.9.1 src.rpm with the Intel 8 C and
FORTRAN
FrankSa> compilers and it bombs out during the testing phase:

FrankSa> comparing 'd-p-q-r-tests.Rout' to './d-p-q-r-tests.Rout.save'
...267c267
FrankSa> < df = 0.5[1] "Mean relative  difference: 5.001647e-10"
FrankSa> ---
>> df = 0.5[1] TRUE
FrankSa> make[3]: *** [d-p-q-r-tests.Rout] Error 1
FrankSa> make[3]: Leaving directory
`/usr/src/redhat/BUILD/R-1.9.1/tests'
FrankSa> make[2]: *** [test-Specific] Error 2
FrankSa> make[2]: Leaving directory
`/usr/src/redhat/BUILD/R-1.9.1/tests'
FrankSa> make[1]: *** [test-all-basics] Error 1
FrankSa> make[1]: Leaving directory
`/usr/src/redhat/BUILD/R-1.9.1/tests'
FrankSa> make: *** [check-all] Error 2
FrankSa> error: Bad exit status from /var/tmp/rpm-tmp.63044 (%build)
FrankSa> ...

__
[EMAIL PROTECTED] 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] Re: Giving a first good impression of R to Social Scientists

[John Fox]

I apologize for joining this discussion late, but I was out of town and just
reviewed postings to R-help. I noticed that there were a couple of other
threads that also touched on similar issues.

Bob Andersen and I have written a paper on using R to teach social
statistics; a copy is at
. It would be
tedious to rehash the paper in detail here, but I'll make a few brief
points:

(1) I believe that, except in special circumstances, GUIs to statistical
software are best for casual or infrequent use. Even users of SPSS who
intend to use the software seriously would be well advised to learn to write
commands. 

(2) The GUI in the Rcmdr package covers what's typically taught in first and
second social-statistics classes.

(3) The difficulty of moving from one statistical package (or computing
environment) to another shouldn't be confused with learning to use a
particular package (or environment) as a novice. I don't believe that it's
any more difficult to write R commands than, say, SAS or SPSS commands.

(4) As others have pointed out, the principal advantage of R (or another
statistical computing environment, as opposed to a statistical package) is
its programmability. Nevertheless, R is not difficult to teach and learn
even to those who will not (initially) be writing programs.

John


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

__
[EMAIL PROTECTED] 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 on windows problem

[Andrew Harrison]

Hi,

I've installed several versions of R on a number of Window 
systems. I get the following error message (which I don't get on linux)

> dev2bitmap(file="test.jpeg",type="jpeg")
Error in system(paste(gsexe, "-help"), intern = TRUE, invisible = TRUE) : 
gswin32c.exe not found

Any idea how to fix this? It seems common to all windows systems I've 
tried. Is there a package I can install that will correct this?

Best wishes,
Harry


-- 
~
Dr Andrew Harrison   Tel: 44 (0) 207 679 3890   
Biomolecular Structure and Modelling UnitFax: 44 (0) 207 679 7193
Biochemistry and Molecular Biology Dept. 
University College London
Gower Street   Email: [EMAIL PROTECTED]
London, WC1E 6BT, UK  http://www.biochem.ucl.ac.uk/~harry
~

__
[EMAIL PROTECTED] 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 on windows problem

[Berton Gunter]

Please read the Help file for dev2bitmap where it will it tell you to install and
how to set the required GhostScript path!


--

Bert Gunter

Non-Clinical Biostatistics
Genentech
MS: 240B
Phone: 650-467-7374


"The business of the statistician is to catalyze the scientific learning
process."

 -- George E.P. Box


Andrew Harrison wrote:

> Hi,
>
> I've installed several versions of R on a number of Window
> systems. I get the following error message (which I don't get on linux)
>
> > dev2bitmap(file="test.jpeg",type="jpeg")
> Error in system(paste(gsexe, "-help"), intern = TRUE, invisible = TRUE) :
> gswin32c.exe not found
>
> Any idea how to fix this? It seems common to all windows systems I've
> tried. Is there a package I can install that will correct this?
>
> Best wishes,
> Harry
>
> --
> ~
> Dr Andrew Harrison   Tel: 44 (0) 207 679 3890
> Biomolecular Structure and Modelling UnitFax: 44 (0) 207 679 7193
> Biochemistry and Molecular Biology Dept.
> University College London
> Gower Street   Email: [EMAIL PROTECTED]
> London, WC1E 6BT, UK  http://www.biochem.ucl.ac.uk/~harry
> ~
>
> __
> [EMAIL PROTECTED] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html

__
[EMAIL PROTECTED] 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 on windows problem

[Prof Brian Ripley]

Please do as the posting guide asks and use a sensible subject line.

On Mon, 23 Aug 2004, Andrew Harrison wrote:

>   I've installed several versions of R on a number of Window 
> systems. I get the following error message (which I don't get on linux)
> 
> > dev2bitmap(file="test.jpeg",type="jpeg")
> Error in system(paste(gsexe, "-help"), intern = TRUE, invisible = TRUE) : 
> gswin32c.exe not found
> 
> Any idea how to fix this? It seems common to all windows systems I've 
> tried. Is there a package I can install that will correct this?

You:

1) Read the help page, on Windows.

 You will need a version of 'ghostscript' (5.10 and later have been
 tested): the full path to the executable can be set by the
 environment variable 'R_GSCMD'.

2) Install 'ghostscript' as it says.  If googling for that is beyond you,
http://www.cs.wisc.edu/~ghost/ should get you started.

-- 
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

__
[EMAIL PROTECTED] 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] do linux-version r has gui?

[ronggui wong]

it seems only has command line interface,is not it?
and i only have konqure as my browser, when i use help.start(),the help file 
does not appear.so waht should i do as to make it work ?

thank you!

__
[EMAIL PROTECTED] 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] Boxplot across levels of a factor

[Paul Boutros]

Hello,

I have a data-frame in which one-column is a factor:

> str(data);
`data.frame':   194 obs. of  8 variables:
 $ Type : Factor w/ 3 levels "Nuclear-Rec..",..: 1 2 2 2 2 2 2 2 2 2
...
 $ Locus: num  0.000571 0.004000 0.001429 0.004857 0.007429 ...

And I'd like to make a boxplot of the data$Locus values, where each level of
the factor gets its own box-and-whiskers plot.  I'm weak in R, but I thought
there might be some shortcut to automating this instead of just creating a
new data-structure with all the separate values?

Any suggestions much appreciated!
Paul

__
[EMAIL PROTECTED] 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] Boxplot across levels of a factor

[Prof Brian Ripley]

On Tue, 24 Aug 2004, Paul Boutros wrote:

> Hello,
> 
> I have a data-frame in which one-column is a factor:
> 
> > str(data);
> `data.frame':   194 obs. of  8 variables:
>  $ Type : Factor w/ 3 levels "Nuclear-Rec..",..: 1 2 2 2 2 2 2 2 2 2
> ...
>  $ Locus: num  0.000571 0.004000 0.001429 0.004857 0.007429 ...
> 
> And I'd like to make a boxplot of the data$Locus values, where each level of
> the factor gets its own box-and-whiskers plot.  I'm weak in R, but I thought
> there might be some shortcut to automating this instead of just creating a
> new data-structure with all the separate values?

There are two.  The simpler is

boxplot(Locus ~ Type, data=data)

and you can also use

with(data, boxplot(split(Locus, Type)))

(split() does automate the construction of a suitable data structure.)

-- 
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

__
[EMAIL PROTECTED] 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] Boxplot across levels of a factor

[Ivar Herfindal]

I think Paul wanted one plot for each box, not all boxes in one plot (sorry 
if I misunderstand).

One way to solve this can be like this:
par(mfrow=c(1,3))
with(data, by(1:nrow(data), Type, function(x) boxplot(Locus[x]~data[x]))
Hope this works for you.
Ivar
On Tue, 24 Aug 2004 07:27:57 +0100 (BST), Prof Brian Ripley 
<[EMAIL PROTECTED]> wrote:

On Tue, 24 Aug 2004, Paul Boutros wrote:
Hello,
I have a data-frame in which one-column is a factor:
> str(data);
`data.frame':   194 obs. of  8 variables:
$ Type : Factor w/ 3 levels "Nuclear-Rec..",..: 1 2 2 2 2 2 2 2 
2 2
...
$ Locus: num  0.000571 0.004000 0.001429 0.004857 0.007429 ...

And I'd like to make a boxplot of the data$Locus values, where each 
level of
the factor gets its own box-and-whiskers plot.  I'm weak in R, but I 
thought
there might be some shortcut to automating this instead of just creating 
a
new data-structure with all the separate values?
There are two.  The simpler is
boxplot(Locus ~ Type, data=data)
and you can also use
with(data, boxplot(split(Locus, Type)))
(split() does automate the construction of a suitable data structure.)
__
[EMAIL PROTECTED] 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] Boxplot across levels of a factor

[Petr Pikal]

On 24 Aug 2004 at 2:12, Paul Boutros wrote:

> Hello,
> 
> I have a data-frame in which one-column is a factor:
> 
> > str(data);
> `data.frame':   194 obs. of  8 variables:
>  $ Type : Factor w/ 3 levels "Nuclear-Rec..",..: 1 2 2 2 2 2 2
>  2 2 2
> ...
>  $ Locus: num  0.000571 0.004000 0.001429 0.004857 0.007429
>  ...
> 
> And I'd like to make a boxplot of the data$Locus values, where each
> level of the factor gets its own box-and-whiskers plot.  I'm weak in
> R, but I thought there might be some shortcut to automating this
> instead of just creating a new data-structure with all the separate
> values?
Hi

You have at least 2 options:

boxplot(data$Locus~data$Type)
boxplot(split(data$Locus,data$Type))

See ?boxplot for further options.

Cheers
Petr




> 
> Any suggestions much appreciated!
> Paul
> 
> __
> [EMAIL PROTECTED] 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]

__
[EMAIL PROTECTED] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html