HI,
Thank you all for the reply to my nls Q.
after i put a variable at the left hand side of "~", and feed initial
values of coefficients, it works now:)
I have a related Q:
I apply arima() and nls() on the same time series. and try to compare
which one fits better.
the result from nls() provides "
On 17 Jan 2003 at 15:59, Damon Wischik wrote:
It seems like gnlr() in Jim Lindsay's package
gnlm might help you.
Kjetil Halvorsen
>
> I have some data which I am trying to fit with a negative binomial
> distribution. I have found the glm.nb function from MASS.
>
> I have reason to believe that
On Friday 17 January 2003 12:44 pm, [EMAIL PROTECTED] wrote:
> Dear all
>
> I am fighting with contour plot.
>
> I have a continuous response and three factors. The formula argument in
> function contourplot() does not like the factors. What I got is really
> nonsense, loads of squares in the plot
I am running R version (1.6.2-1) on Redhat Linux 8.0.
I am unsuccesfully trying to compile Fortran code and then loading the
created object into R.
The following are the basic commands I have used to do this.
#R CMD SHLIB -o file.f
#R
>dyn.load("file.so")
In the above command I have been explicit
Some other techniques for overdispersed and underdispersed count data
are described in:
COUNT DATA REGRESSION USING SERIES EXPANSIONS: WITH APPLICATIONS
by A. COLIN CAMERON and PER JOHANSSON
in JOURNAL OF APPLIED ECONOMETRICS, VOL 12, 203-223 (1997).
http://www.econ.uiuc.edu/~econ472/
I played around a bit with the ls.objects() code posted by Petr Pikal
yesterday and came up with the following that is a bit faster, shorter,
and adds memory usage information. It combines an object's mode and
class information into a "Type" column that seems more parsimonious,
and adds an argume
Dear Jonathan,
This error appear when the number of censored time is not equal to different
identifier numbers. E.g. It is possible you have not censored times for all
subjects. In this case you have to add another data with the same identitier
time equal to 0 and censored 0. For example:
If you
When you have numerical "x" variables, rather than factors, you can make
sensible contour plot. Short of that, nothing in this world will give you
"beautiful curves".
Andy
> -Original Message-
> From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]
> Sent: Friday, January 17, 2003 1:45 PM
Dear all
I am fighting with contour plot.
I have a continuous response and three factors. The formula argument in
function contourplot() does not like the factors. What I got is really
nonsense, loads of squares in the plot (exactly the same as what the help
page says). I am wondering how I coul
I am trying to analyse recurrent failure times using survfitr
from the survrec package. To do this, I need to "Create a survival
recurrent object" using Survr. But, when I do this, I get an error
"Error in Survr(r1d[, 1], r1d[, 5], r1d[, 6]) : data doesn't match".
Here, r1d[,1] is the identifier
I have some data which I am trying to fit with a negative binomial
distribution. I have found the glm.nb function from MASS.
I have reason to believe that the mean parameter mu depends on
certain factors, and that the shape parameter theta depends on
others.
If, say, the factors are P and Q, it
Timur Elzhov <[EMAIL PROTECTED]> writes:
> Second, who pass the other, `call', `op' and `rho' parameters
> to `do_optim() ?'
You mean "why" I suppose.
op: Some functions are mapped into the same C function (do_math2, for
example) so you need to know which one.
call: The whole call is passed m
Dear R experts,
I looked at the body of, say, `optim' function and found
the call to the `.Internal', C optim function. It looks
like this:
.Internal(optim(par, fn1, gr1, method, con, lower, upper))
On the other hand, the C prototype of optim is:
SEXP do_optim(SEXP call, SEXP op, SEXP args,
Hi,
You may want to take a look at the file "README.client" under the
main ROracle package directory. It describes how to access Oracle
from an Oracle-less linux workstation.
--
David
Luke Whitaker wrote:
>
> Hello,
>
> I have installed the ROracle and DBI packages, and I want to
> access an
Juan Ramon Gonzalez wrote:
Hello R-listers,
I am developing a function which needs to create jpeg files from some plots. To create the jpeg files I use the instruction dev.print(jpeg, file=c://graph.jpg",width=400,height=400).
[won't work anyway]
Until now everything has been fine, but now I ha
Hello,
I have installed the ROracle and DBI packages, and I want to
access an Oracle database that is not on the same machine
as the one I am running R on.
I can access the database remotely with perl DBI and Java JDBC.
Does anyone know if this is possible using R DBI/ROracle ? I
have looked thr
"kjetil brinchmann halvorsen" <[EMAIL PROTECTED]> writes:
> On 16 Jan 2003 at 22:15, Yan Yu wrote:
>
> > HI,
> > i have some prob when i try to use nls().
> > my data is 1D vector, I tried to use a polynomial function(order is 3) to
> > fit it.
> > the data series is stored in x.
> > the a0, a1,
Hello R-listers,
I am developing a function which needs to create jpeg files from some plots. To create
the jpeg files I use the instruction dev.print(jpeg,
file=c://graph.jpg",width=400,height=400). Until now everything has been fine, but now
I have a special plot which is formed by 3 separat
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED]] On Behalf Of Jeremy Butler
> Sent: Thursday, January 16, 2003 11:42 PM
> To: [EMAIL PROTECTED]
> Subject: [R] barplot plotting problem
>
>
> Hi,
> Is there any equivalent of type="n" when constructing
> barplots
Vumani Dlamini wrote:
Dear R-users:
I asked a question on how I can have a universal legend in a plot and
received the following result. I tried using "layout" but I can't seem
to work on the "empty" plot (where I have to have the legend). I tried
"oma" but I couldn't improve the quality of th
http://developer.r-project.org has the background papers.
On Fri, 17 Jan 2003, Vanguelov, Krassimir wrote:
> Could you tell me where can I read more about the difference between
> "external pointer"(EXTPTRSXP) and "weak reference"(WEAKREFSXP) in R and what
> were they intended for?
--
Brian D.
R's and S-PLUS's write.table functions have different arguments with
different defaults: discussed in MASS4, for example. You appear to need
sep = "," (and FLASE appears to be a typo). It would be better to use
col.names=FALSE and omit the skip=1.
Three other comments:
_ is deprecated in bot
"Vumani Dlamini" <[EMAIL PROTECTED]> writes:
> Dear R-users:
>
> I asked a question on how I can have a universal legend in a plot and
> received the following result. I tried using "layout" but I can't seem
> to work on the "empty" plot (where I have to have the legend). I tried
> "oma" but I co
Dear R-help,
Could you tell me where can I read more about the difference between
"external pointer"(EXTPTRSXP) and "weak reference"(WEAKREFSXP) in R and what
were they intended for?
Regards,
Krassimir Vanguelov
**
This is
Is your data such that it can be restructured into a form amenable to a
lattice plot, such as xyplot()? In that case, the legend (key in lattice)
can be placed pretty much anywhere.
Regards,
Andrew C. Ward
CAPE Centre
Department of Chemical Engineering
The University of Queensland
Brisbane Ql
[EMAIL PROTECTED] writes:
> > [Pet peeve] However, contr.poly *also* treats the factor as a numeric
> > variable, it just assumes that the levels are equidistant. What other
> > sense would a (say) linear term make?
>
> Not quite, it allocates scores to the factor levels, equally spaced
> score
Dear all,
Thanks to those of you who have replied, the majority of the
comments pointed out that the error caused by scan may originate
from another function, and closer inspection of the output from
traceback() reveals that it is in fact the read.table function where
the error is originating
Dear R-users:
I asked a question on how I can have a universal legend in a plot and
received the following result. I tried using "layout" but I can't seem to
work on the "empty" plot (where I have to have the legend). I tried "oma"
but I couldn't improve the quality of the plot, and that I didn
On 16 Jan 2003 at 22:15, Yan Yu wrote:
> HI,
> i have some prob when i try to use nls().
> my data is 1D vector, I tried to use a polynomial function(order is 3) to
> fit it.
> the data series is stored in x.
> the a0, a1, a2, a3 below is coefficient, which i hope i can get from
> calls "nls"
>
On Thu, 16 Jan 2003 08:40:14 -0500, you wrote:
>All:
>
>The select.list() command brings up a "modal dialog box with a (scrollable)
>list of items ..." etc. -- i.e., a GUI control. I also know about winDialog,
>file.choose and the winMenu commands. What other such GUIisms are built into
>** base *
On 17 Jan 2003, Peter Dalgaard BSA wrote:
> [EMAIL PROTECTED] writes:
>
> > I don't think you are describing contrasts for an ordered factor, but
> > orthogonal polynomials in a numeric variable. The latter are computed by
> > the function poly() in both R and S-PLUS. You could set them up to
[EMAIL PROTECTED] writes:
> I don't think you are describing contrasts for an ordered factor, but
> orthogonal polynomials in a numeric variable. The latter are computed by
> the function poly() in both R and S-PLUS. You could set them up to give a
> contrasts matrix if you want, but not a co
> "Deepayan" == Deepayan Sarkar <[EMAIL PROTECTED]>
> on Thu, 16 Jan 2003 15:20:20 -0600 writes:
Deepayan> On Thursday 16 January 2003 02:10 pm, Patrick Connolly wrote:
>> On Wed, 15-Jan-2003 at 10:47PM -0600, Deepayan Sarkar wrote:
>> |> On Wednesday 15 January 2003 07:35
Hi,
I have a large number of high performance liquid chromatography (HPLC)
datafiles that I was hoping to process using R. I couldn't find
anything in the mailing list archives or the packages list but before I
go around reinventing the wheel, has anyone on the list got any
pointers or code th
Hi
I'm working with geostatistics and I use geoR package, which I find very
good. However it doesn't implement the classic geostatistics but a
"model based geostatistics" as proposed by Peter Diggle and team.
R news of June 2001 has an article about geoR by Paulo Ribeiro, the main
developer, that
On 16-Jan-03 Ted Harding wrote:
> Hence the multivariate regression model for the data could be
> written in matrix form as
>
> Y = X*B + w1*W1 + w2*W2 + w3*W3 + e
>
[ Y Nxp ; X Nxk ; W1 W2 W3 Nxp matices of factor level indicators;
B kxp ; w1, w2, w3 scalars ]
> where e is 3-dim N(0,S), and
On Thu, 16 Jan 2003, Yan Yu wrote:
> Hi, all,
>Have anyone used kringing included in R? How is it?
> Does it handle anisotropy data well?
> How does it compare with Kriging in Arc/Info? or other geostatistics
> software customized to do kriging or other geostatistics functions?
Maybe help.se
Lots of questions! Kriging in geostatistics software often uses rather
peculiar approximations to the exact theory, and `data' cannot be
anisotropic (but models can).
There is kriging in packages spatial, sgeostat and fields, at least, as a
quick look at the FAQ would have shown you.
It is unl
On Thu, 16 Jan 2003, graham lawrence wrote:
> Why does the second grep reject when the first grep accepts?
> Why does regexpr accept what grep rejects?
It's the if() that is different. grep returns an integer vector of
matching indices, and numeric(0) == 1 is logical(0), which gives nothing
to
You are wrong about S-PLUS! contr.poly only takes as argument the number
of levels required (and uses pre-computed sets for up to 12 levels).
You get orthogonal polynomials for equally-space values from contr.poly in
both systems, as documented.
I don't think you are describing contrasts for an
40 matches
Mail list logo
