On Fri, 21 Jul 2006, N. Goodacre wrote:
Dear R mailing group,
The second parameter for the function optim()is a function whose
parameters are to be optimized. The description of this function given in
the help file is the following:
fn: A function to be minimized (or maximized),
R does not know that poly(age,2) and poly(age,1) are linearly dependent.
(And indeed they only are for some functions 'poly'.)
I cannot reproduce your example ('l' is missing), but perhaps
glm(deaths ~ poly(age,2) + poly(age,1)*Smoke + offset(l), poisson)
was your intention?
On Fri, 21 Jul
Dear all,
In the search for a command to insert a row between other rows in a data
frame I found that there seems to be no such command in the base R
package. There is however a very simple function insertRow in the
micEcon package, that makes use of rbind. I wondered if it would not be
Hello,
I have two dataframes of the following structures:
str(a)
`data.frame': 1354896 obs. of 14 variables:
$ V1 : int 0 1 2 3 4 5 6 7 8 9 ...
$ V2 : int 0 0 0 0 0 0 0 0 0 0 ...
$ V3 : int 74 12305 103 12337 46 57 12446 90 12097 79 ...
$ V4 : num11.8 1529.2 17.8 1579.46.7
On Thu, 2006-07-20 at 14:38 +, Emanuele Mazzola wrote:
Hello everybody,
i'm having some trouble performing correspondence analysis with R for Mac OS
X. Does anyone know about some useful package?
And also, if i had found coordinates of points representing row and column
profiles, how
Duncan Murdoch [EMAIL PROTECTED] writes:
R tries to use the maximum precision (64 bit mantissa) in the floating
...
Or perhaps your problem has nothing to do with this; I didn't really
look at it in detail.
It hasn't. I was off speculating about sum vs rowSums too, but:
num.v-
On Thu, 2006-07-20 at 16:40 +, Emanuele Mazzola wrote:
Hi all,
thank you for your answers; i've tried both cca from vegan library, and
dudi.coa from ade4 library; one last question: my deal is mainly with
contingency tables, like the one i'm posting here
Dear all,
I have tried installing rgl with the usual command:
R CMD INSTALL rgl_0.67-2.tar.gz
Differently from what happened last time I have succesfully installed this
package, this time there was a failure:
...
...g++ -I/usr/lib/R/include -I/usr/lib/R/include -I -DHAVE_PNG_H
G'day all,
BDR == Prof Brian Ripley [EMAIL PROTECTED] writes:
BDR R does not know that poly(age,2) and poly(age,1) are linearly
BDR dependent.
Indeed, I also thought that this is the reason of the problem.
BDR (And indeed they only are for some functions 'poly'.)
I am surprised
On Fri, Jul 21, 2006 at 09:33:56AM +0200, Gunther Höning wrote:
I have two dataframes of the following structures:
[...]
I want to merge these dataframes by V1 and V2 of a and b. The combination of
V1, V2 is a unique key.
Note that b is smaller than a.
Any suggestions to solve this problem
On Fri, 21 Jul 2006, Berwin A Turlach wrote:
G'day all,
BDR == Prof Brian Ripley [EMAIL PROTECTED] writes:
BDR R does not know that poly(age,2) and poly(age,1) are linearly
BDR dependent.
Indeed, I also thought that this is the reason of the problem.
BDR (And indeed they only
Hi, Hi all,
thank you for your answers; i've tried both cca from vegan library, and
dudi.coa from ade4 library; one last question: my deal is mainly with
contingency tables, like the one i'm posting here
acciaieria-c(.41,.02,.44,.04,.09)
laminatoio-c(.34,.28,.26,.01,.11)
On FC5:
roc% rpm -q --file /usr/include/GL/glu.h
mesa-libGLU-devel-6.4.2-6.FC5.3
Do check what the R-admin manual says about -devel RPMs.
On Thu, 20 Jul 2006, James Foadi wrote:
Dear all,
I have tried installing rgl with the usual command:
R CMD INSTALL rgl_0.67-2.tar.gz
Differently from
Thank you both very much for your help.
Peter Dalgaard is right- i didn't consider the fact that elementwise
multiplication is column-wise rather than row-wise.
Sorry for taking up timespace with such a trivial mistake.
Original-Nachricht
Datum: 21 Jul 2006 10:07:31 +0200
Subject: Re: [R] failed installing rgl
Date: Friday 21 July 2006 10:08
From: Prof Brian D Ripley [EMAIL PROTECTED]
To: James Foadi [EMAIL PROTECTED]
Cc: r-help@stat.math.ethz.ch
On FC5:
roc% rpm -q --file /usr/include/GL/glu.h
mesa-libGLU-devel-6.4.2-6.FC5.3
Do check what the R-admin manual
Hi All,
I have a data frame of three columns, all of which names. The names in the
three
cols overlap up to a point, so I might have *Harry* in all three columns,
*Tom* in cols 1 and 3 and *Bob* in col 3 only.
harry paulbob
anita harry tom
frank jackharry
tom peteben
Bother! This cold has made me accident-prone. I meant to hit Reply-all.
Clarification below.
Original Message
Subject: Re: [R] Parameterization puzzle
Date: Fri, 21 Jul 2006 19:10:03 +1200
From: Murray Jorgensen [EMAIL PROTECTED]
To: Prof Brian Ripley [EMAIL PROTECTED]
Dear R users,
I've just uploaded 2 packages on CRAN, RTisean and tsDyn, both for time
series analysis (joint research projects with members of the Statistics
Department, University of Udine). Brief descriptions follow.
RTisean is an R interface to TISEAN executables
Are the columns factors or character? I'll try to write code that copes
with both:
nm - unique(c(as.character(col1), as.character(col2), as.character(col3)))
DF[] - lapply(DF, function(x) match(x, nm))
On Fri, 21 Jul 2006, Federico Calboli wrote:
Hi All,
I have a data frame of three
Prof Brian Ripley wrote:
Are the columns factors or character? I'll try to write code that copes
with both:
nm - unique(c(as.character(col1), as.character(col2), as.character(col3)))
DF[] - lapply(DF, function(x) match(x, nm))
Cheers,
it worked.
Federico
--
Federico C. F. Calboli
glm(S ~ -1 + Mdif, family=quasipoisson(link=identity), start=strt, sdat)
gives error:
Error in glm.fit(x = X, y = Y, weights = weights, start = start, etastart
=
etastart, :
cannot find valid starting values: please specify some
strt is set to be the coefficient for a similar fit
Hi,
I'm just learning R and am encountering some unexpected results following a
guide on the internet. If anyone can help that would be great - I think it
is something about the way the data has been read in!
I've read a coma delimited text data file that was saved from excel:
jacs.data -
Hello all,
I am currently working with rpart to classify vegetation types by spectral
characteristics, and am comming up with poor classifications based on the fact
that I have some vegetation types that have only 15 observations, while others
have over 100. I have attempted to supply prior
On Fri, 21 Jul 2006, Dan Bebber wrote:
glm(S ~ -1 + Mdif, family=quasipoisson(link=identity), start=strt, sdat)
gives error:
Error in glm.fit(x = X, y = Y, weights = weights, start = start, etastart
=
etastart, :
cannot find valid starting values: please specify some
strt
Dear Helen,
You may want to have a look at
http://www.togaware.com/datamining/survivor/Predicting_Fraud.html
Greets,
Diego Kuonen
[EMAIL PROTECTED] wrote:
Hello all,
I am currently working with rpart to classify vegetation types by spectral
characteristics, and am comming up with poor
On 7/21/2006 7:36 AM, nathan wrote:
Hi,
I'm just learning R and am encountering some unexpected results following a
guide on the internet. If anyone can help that would be great - I think it
is something about the way the data has been read in!
I've read a coma delimited text data file
On Fri, 2006-07-21 at 04:36 -0700, nathan wrote:
Hi,
I'm just learning R and am encountering some unexpected results following a
guide on the internet. If anyone can help that would be great - I think it
is something about the way the data has been read in!
I've read a coma delimited
Hi
On 21 Jul 2006 at 4:36, nathan wrote:
Date sent: Fri, 21 Jul 2006 04:36:53 -0700 (PDT)
From: nathan [EMAIL PROTECTED]
To: r-help@stat.math.ethz.ch
Subject:[R] unexpected results
Hi,
I'm just learning R and am
Hi,
I have a dataset saved in *.csv format, that contains
13 columns (the first column being the title name and
the rest experiments) and about 2500 rows.
Not all columns in the row have data in it
i.e for eg
Use
x - count.fields('datafile.csv',sep=',')
on your file. This will tell you the number of columns that R thinks is one
each line. Then do:
table(x)
to see if all the lines have the same number of columns. If not, then find
the lines which don't:
which(x != legal.length)
and then look at
See if this works:
read.csv(datafile.csv, row.names = 1, fill = TRUE)
On 7/21/06, Ahamarshan jn [EMAIL PROTECTED] wrote:
Hi,
I have a dataset saved in *.csv format, that contains
13 columns (the first column being the title name and
the rest experiments) and about 2500 rows.
Not all
I have a covariance matrix that is not positive semi-definite matrix and I
need it to be via some sort of adjustment. Is there any R routine or
package to help me do this?
Thanks, Roger
[[alternative HTML version deleted]]
__
Brian Ripley wrote:
BTW, your example cannot be pasted in as 'sdat' self-references. It could
be fixed, but I gave up at that point.
Oh dear, I'm very sorry. I forgot to run rm(list=ls(all=TRUE)) before
testing.
The corrected code is:
#Data:
S - c(0, 0, 0, 0, 28, 0, 1, 7, 0, 0, 39, 2, 0, 0,
Hi!
On Fri, Jul 21, 2006 at 05:43:03AM -0700, Ahamarshan jn wrote:
I have a dataset saved in *.csv format, that contains
[...]
BS00,-0.084,0.0136,-0.1569,-0.6484,1.103,1.7859,0.40287,0.5368,0.08461,-0.1935,-0.147974,0.30685
BS01,0.491270283,0.875826172,,
On 7/21/2006 8:59 AM, roger bos wrote:
I have a covariance matrix that is not positive semi-definite matrix and I
need it to be via some sort of adjustment. Is there any R routine or
package to help me do this?
I think you need to be more specific about what have and what you want,
but if
Hi,
I am having problems when trying to apply factor analysis in a covariance
matrix,
factanal(covmat=strip1cmcd, factors=5, control=list(lower=0.0264))
Error in optim(start, FAfn, FAgr, method = L-BFGS-B, lower = lower, :
non-finite value supplied by optim
In addition: Warning
Duncan == Duncan Murdoch [EMAIL PROTECTED]
on Fri, 21 Jul 2006 09:44:42 -0400 writes:
Duncan On 7/21/2006 8:59 AM, roger bos wrote:
I have a covariance matrix that is not positive semi-definite matrix and
I
need it to be via some sort of adjustment. Is there any R routine
Hi,
I have been asked by a publisher to change the font style of a lattice
plot in my manuscript. I have consulted documentation on trellis
graphics and the excellent book R graphics, but am still not sure how
I could create plots with Arial as the font style for text in the plot.
I am
Dear Leaf,
I modified your code as follows:
gamma.fun - function(mu,sd,start=100)
{
f.fn - function(alpha)
{abs(sd^2-mu^2/(gamma(1+1/alpha))^2*(gamma(1+2/alpha)-(gamma(1+1/alpha))^2))}
alpha - optim(start, f.fn)
beta - mu/gamma(1+1/alpha$par)
return(list=c(a=alpha$par,b=beta));
}
Now it
On Thu, 20 Jul 2006, Bruno L. Giordano wrote:
If R packages are not found for my purpose, can somebody please point me to
some recent monographs on order-restricted inference?
One more recent book is:
Robertson, T., Wright, F., Dykstra, R. (1988). Order restricted
statistical
Take a look at make.positive.definite in the corpcor package. The
implementation is very similar to what Duncan suggested.
Regards,
Francisco
Dr. Francisco J. Zagmutt
College of Veterinary Medicine and Biomedical Sciences
Colorado State University
From: Duncan Murdoch [EMAIL PROTECTED]
There is a paper by N.J. Higham (SIAM J Matrix Anal, 1998) on a modified
cholesky decomposition of symmetric and not necessarily positive definite
matrix (say, A), with an important goal of producing a small-normed
perturbation of A (say, delA), that makes (A + delA) positive definite.
On Fri, 21 Jul 2006, Valentin Dimitrov wrote:
Dear Leaf,
I modified your code as follows:
gamma.fun - function(mu,sd,start=100)
{
f.fn - function(alpha)
{abs(sd^2-mu^2/(gamma(1+1/alpha))^2*(gamma(1+2/alpha)-(gamma(1+1/alpha))^2))}
alpha - optim(start, f.fn)
beta -
This problem was posted a couple years ago here:
http://tolstoy.newcastle.edu.au/R/help/04/01/0231.html
Using Windows XP with R 2.3.1, I am now experiencing the same problem again:
when a plot is saved and/or copied as a WMF, the labels do not have the
correct character spacing. I am trying to
This is a question about devices, not lattice per se, so applies to all
forms of plotting.
For jpeg, you can specify the fonts via the 'fonts' argument: see ?X11.
For postscript, you can convert the fonts to Type 1 via e.g. ttf2pt1, or
you can use ttf2afm to make .afm files and a postscript
On Fri, 2006-07-21 at 05:43 -0700, Ahamarshan jn wrote:
Hi,
I have a dataset saved in *.csv format, that contains
13 columns (the first column being the title name and
the rest experiments) and about 2500 rows.
Not all columns in the row have data in it
i.e for eg
I am using the multcomp package for doing multiple comparisons. Since the data
I am handling is huge the number of comparisons are also large. I am interested
in:
1 Breaking down my plots to get rid of the clutter that happens when plotting
the entire data set. How do I pass only part of the
Hello R community,
I am looking for a robust test for equality of variances that can take
observation weights.
I realize I can do the F-test with weighted variances, but I've read that
this test is not very robust.
So I thought about maybe adding a weights argument to John Fox's code for
the
I am using the multcomp package for doing multiple comparisons. Since
the data I am handling is huge the number of comparisons are also large.
I am interested in:
1 Breaking down my plots to get rid of the clutter that happens when
plotting the entire data set. How do I pass only part of the
Dear Users,
I have two particular problems that I need to solve.
I do an analysis of a survey about sexuality.
(Don't read any further if you don't like the subject.)
Problem (1)
In the survey there a two questions about monogamy.
(1) Are you monogamous? (At this moment.)
(2) Have you been
Ravi == Ravi Varadhan [EMAIL PROTECTED]
on Fri, 21 Jul 2006 11:33:23 -0400 writes:
Ravi There is a paper by N.J. Higham (SIAM J Matrix Anal,
Ravi 1998) on a modified cholesky decomposition of
Ravi symmetric and not necessarily positive definite matrix
Ravi (say, A), with an
I found this other more recent monograph:
Silvapulle and Sen (October 2004), Constrained Statistical Inference: Order,
Inequality, and Shape Constraints, Wiley-Interscience.
http://ca.wiley.com/WileyCDA/WileyTitle/productCd-0471208272,descCd-reviews.html
Thanks for the tip,
Bruno
-
You can always bootstrap any robust spread measure (e.g. mad or higher
efficiency versions from robustbase or other packages).
-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
The business of the statistician is to catalyze the scientific learning
process. - George E.
Hi,
i have a list of several vectors, for example:
vectorlist
$vector.a.1
[1] a b c
$vector.a.2
[1] a b d
$vector.b.1
[1] e f g
I can use intersect to find elements that appear in $vector.a.1 and
$vector.a.2:
intersect(vectorlist[[1]], vectorlist[[2]])
[1] a b
I would like to use grep
FAQ 7.21.
But there are perhaps slicker ways.
-- Bert Gunter
Genentech Non-Clinical Statistics
South San Francisco, CA
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Georg Otto
Sent: Friday, July 21, 2006 10:39 AM
To: r-help@stat.math.ethz.ch
Georg Otto wrote:
Hi,
i have a list of several vectors, for example:
vectorlist
$vector.a.1
[1] a b c
$vector.a.2
[1] a b d
$vector.b.1
[1] e f g
I can use intersect to find elements that appear in $vector.a.1 and
$vector.a.2:
intersect(vectorlist[[1]],
The following assumes that within each component of vectorlist
the vector elements are unique. In that case the first two lines
define vectorlist and perform the grep, as in your post. Elements
of the intersection must occur n times where n is the number
of components of vectorlist that match the
Dear List,
I am a new Mac user and I am having problem generating png (or jpeg)
using the GUI version of R. I installed R-2.3.1.dmg (custom install with
everything selected) and X11User.pkg but I am still getting the
following X11 connection error when I try to generate a png (or a jpeg):
Error
I finally determined the problem, but not the specific cause.
For some reason, the WMF is resized when saved or copied from R. If you
compare the same plot pasted into PowerPoint as both a bitmap and a WMF, the
WMF has its height increased ~14% and its width decreased ~5% consistently.
This is
On Fri, 2006-07-21 at 11:47 -0700, Paquet, Agnes wrote:
Dear List,
I am a new Mac user and I am having problem generating png (or jpeg)
using the GUI version of R. I installed R-2.3.1.dmg (custom install with
everything selected) and X11User.pkg but I am still getting the
following X11
Martin,
You are most welcome. I apologize for my faux pas. I really did mean to
say Matrix package, but got sloppy!
There is also another (more recent) article by Higham:
http://www.maths.man.ac.uk/~nareports/narep369.pdf
Best,
Ravi.
I am using the multcomp package for doing multiple comparisons. Since
the data I am handling is huge the number of comparisons are also large.
I am interested in:
1 Breaking down my plots to get rid of the clutter that happens when
plotting the entire data set. How do I pass only part of the
I have an object of mode character that contains a long sequence of letters.
How can I convert this object into a vector with each element of the vector
containing a single letter? Essentially, I want to break the long string of
letters into many individual letters.
Thanks for the help.
Alex
Hi everybody,
i'm dealing with some percentage tables, of which i should test rowwise if
the entries are sgnificantly equal or not. Namely, on row 1, test H0:
element 1= element2, H0: element 1= element3...H0: element 2= element3...H0:
element n-1= element n. The same on the other rows.
On Fri, 2006-07-21 at 15:15 -0500, [EMAIL PROTECTED] wrote:
I have an object of mode character that contains a long sequence of letters.
How can I convert this object into a vector with each element of the vector
containing a single letter? Essentially, I want to break the long string of
Does anyone know of a function that computes the necessary sample size
to reject a null median survival in favor of a given alternative median
survival in a one arm trial?
Cody Hamilton, Ph.D
Institute for Health Care Research and Improvement
Baylor Health Care System
(214) 265-3618
Thanks for the suggestion! I switched to optimize(), al - optimize(f.fn, lower
= 0.1, upper =100,tol=0.001);
the warnings were gone and it works stably.
But when I tried al - uniroot(f.fn, lower = 0.1, upper =100,tol=0.001);
error occured: f() values at end points not of opposite sign. The
Dear Spencer,
Thank you very much for your helpful reply. I was trying to reproduce a
table in one paper. After I modified my code according to your suggestion, I
was able to get the results that are very close to those in the paper. It
seems the starting values of the parameters to be optimized
On 21-Jul-06 Paquet, Agnes wrote:
Dear List,
I am a new Mac user and I am having problem generating png (or jpeg)
using the GUI version of R. I installed R-2.3.1.dmg (custom install
with
everything selected) and X11User.pkg but I am still getting the
following X11 connection error when I
Thanks to Brian and Berwin with there help. I faced a double problem in
that I not only wanted to fit the model but I also wanted to do so in
such a way that it would seem natural for a classroom example.
The moral seems to be that I should do the orthogonal polynomial stuff
outside the model
Hi,
I finally managed to make it work (I just needed to have a X11 window
open).
Thank you very much for your help.
Agnes
-Original Message-
From: Ted Harding [mailto:[EMAIL PROTECTED]
Sent: Friday, July 21, 2006 3:34 PM
To: Paquet, Agnes
Cc: r-help@stat.math.ethz.ch
Subject: RE: [R]
Thanks,
You are right about it being a tab delimited file - I should have spotted
that.
I am now getting an error saying that line 4 did not have 27 elements but
will fiddle around and try to work it out - I'm guessing because I have some
empty feild its causing problems.
Anyway thanks for
Dear all,
I'm sorry I have to bother you with this newbie stuff.
Within a loop I obtain pairs of values x - c(a, b). An empty set M is
defined before the loop (as a list or whatever). Now I want to do the
following: if there is a vector y in M that contains at least one of
the values of x, then
It seems to me that not for all values of mu and sd
there is a Weibull distribution with mean=mu and
variance=sd^2.
the programm with optimize(f.fn) finds always a
solution, but this is not necessarily what we need,
because the minimum of (abs(f(x)) is not always 0.
Suppose f(x)=2+x^2, then
R help,
How would I input data, verify assumptions, and run a nested repeated
measures ANOVA using R? I have STATION nested in SITE nested in BLOCK with
measurements repeated for five YEARs. All are random variables and it's only
slightly unbalanced. I'm trying to characterize spatiotemporal
1. I'd be worried any time the answer depended very much on the
starting values. It suggests that the objective function is not well
behaved, and I must be very careful to make sure I get an appropriate
answer, and I'm not being misled by round-off, etc.
2. I would NOT
76 matches
Mail list logo