Dear R People,
I would like to fit an arima model with a seasonal component, but I've
daily data and I consider a montly seasonal ?!
How could I have a daily predict with this kid of time series ?
Thanks in advance for any insight
Lisa
[[alternative HTML version deleted]]
Dear Luca,
I don't think that R has a built-in function for doing
Laplace or inverse Laplace transforms. I remember having to
use an IMSL routine (INLP, I think) to do this many years
ago. When I looked at the article that the algorithm was
based on, I found that as an example the author showed ho
Hi,
I am a new user of R and am building an R add-on package. I followed the
"Writing R Extension" manual from cran website but still met some
problems that I cannot solve. I build it under redhat linux 9.0 R1.7.0.
Say foo is the name of the package.
First, after I wrote the Rd files for each f
On Thursday 04 September 2003 19:52, Ted Harding wrote:
> Thanks, Deepayan!
> However, for me this has deepened the mystery (I don't really
> understand in detail how lattice graphics works anyway!).
>
> To clarify: The variables X,Y,Z,W in DF have some zero values,
> and otherwise are positive. F
A student of mine has 110 similarly structured multivariate time
series, and we're interested in methods that are practical for
thousands of them.
Basically each series describes a series of musical notes, and certain
properties of these notes are recorded. The same set of properties
is recorded
By the way, Dong,
you shouldn't use the term "mean" in Splus to designate the mean of your trait
(mean<-8000). "mean' is an Splus function, and by doing mean<-8000, you may experience
problems when you'll need the argument "mean" to designate the original Splus function
(as in the function mod
Thanks, Deepayan!
However, for me this has deepened the mystery (I don't really
understand in detail how lattice graphics works anyway!).
To clarify: The variables X,Y,Z,W in DF have some zero values,
and otherwise are positive. For U,V in X,Y,Z,W I plot log(1+V)
against log(1+U) for all the point
How about this:
read.table(textConnection(sub("^#","",readLines(myfile))),header=T)
which simply stripts off any # which is first on any line and then
passes the result to read.table .
--- "Vadim Ogranovich" <[EMAIL PROTECTED]> wrote:
>I admit I should have been more clear in my original postin
My thanks to Drs. Armstrong, Bates, Harrell, Liaw, Lumley,
Prager, Schwartz, and Mr. Wang for their replies. I have
pasted my original message and their replies below.
After viewing http://www.itl.nist.gov/div898/strd/ as suggested
by Dr. Schwartz, it occurred to me that it might be educational
On Thu, 4 Sep 2003, Paul, David A wrote:
> I am one of only 5 or 6 people in my organization making the
> effort to include R/Splus as an analysis tool in everyday work -
> the rest of my colleagues use SAS exclusively.
>
> Today, one of them made the assertion that he believes the
> numerical al
Douglas Bates <[EMAIL PROTECTED]> writes:
> McCullough, B. D. (1998), "Assessing the reliability of statistical
> software: Part I", The American Statistician, 52, 149-159.
>
> McCullough, B. D. (1999), "Assessing the reliability of statistical
> software: Part II", The American Statistician,
> A curious difference between SAS and R. I wonder if anyone can explain it.
>
> Basic idea: Split-plot design (Male = whole plot, Trt = Sub plot). Rep is random,
> Rep*Male variance component is 0 and deleted. Heterogeneous variances - each Trt
> has different variance.
>
> The model with o
"Paul, David A" <[EMAIL PROTECTED]> writes:
> I am one of only 5 or 6 people in my organization making the
> effort to include R/Splus as an analysis tool in everyday work -
> the rest of my colleagues use SAS exclusively.
>
> Today, one of them made the assertion that he believes the
> numerica
yes: From "?optim", I get the following:
optim(par, fn, gr = NULL,
method = c("Nelder-Mead", "BFGS", "CG", "L-BFGS-B", "SANN"),
lower = -Inf, upper = Inf,
control = list(), hessian = FALSE, ...)
By "fn", I meant the function you supply for that argument.
spencer
Paul, David A wrote:
I am one of only 5 or 6 people in my organization making the
effort to include R/Splus as an analysis tool in everyday work -
the rest of my colleagues use SAS exclusively.
Today, one of them made the assertion that he believes the
numerical algorithms in SAS are superior to t
I just did a Google search for "lapack error codes" and got several
hits. However, I don't know if a translation of "error code 17" would
really help you.
Have you tried "fn" as a stand-alone function? If yes, have you
tried including a "cat" or "print" statement in it, so it prints the
Dirk Eddelbuettel <[EMAIL PROTECTED]> writes:
> On Thu, Sep 04, 2003 at 05:37:46PM +0200, Brunschwig, Hadassa {PDMM~Basel} wrote:
> > Is there an equivalent in R for the dos() command in S?
>
> help(system)
help(shell) on Windows, actually.
--
O__ Peter Dalgaard Blegdamsv
On Thu, 4 Sep 2003, Paul, David A wrote:
> I am one of only 5 or 6 people in my organization making the
> effort to include R/Splus as an analysis tool in everyday work -
> the rest of my colleagues use SAS exclusively.
>
> Today, one of them made the assertion that he believes the
> numerical a
On Thu, 4 Sep 2003, Spencer Graves wrote:
> Have you considered the two books by Venables and Ripley (2002) Modern
> Applied Statistics in S and (2000) S Programming (both Springer)? If
> yes, I don't know what you mean by "the usually available manuals."
In addition, John Chambers's "Programm
On Thu, 2003-09-04 at 08:34, Frank E Harrell Jr wrote:
> On Thu, 04 Sep 2003 14:50:25 -0400
> "Paul, David A" <[EMAIL PROTECTED]> wrote:
>
> > I am one of only 5 or 6 people in my organization making the
> > effort to include R/Splus as an analysis tool in everyday work -
> > the rest of my colle
Does any of you know where I can find an explanation of lapack errors codes?
I get error code 17 when using optim().
Is there a way to handle errors in R such that depending on the type of
error I can decide what to do next?
Thanks,
Haky
__
[EMAIL PR
On Thu, 04 Sep 2003 14:50:25 -0400
"Paul, David A" <[EMAIL PROTECTED]> wrote:
> I am one of only 5 or 6 people in my organization making the
> effort to include R/Splus as an analysis tool in everyday work -
> the rest of my colleagues use SAS exclusively.
>
> Today, one of them made the asserti
I am one of only 5 or 6 people in my organization making the
effort to include R/Splus as an analysis tool in everyday work -
the rest of my colleagues use SAS exclusively.
Today, one of them made the assertion that he believes the
numerical algorithms in SAS are superior to those in Splus
and R -
You can't do it in that sequence, and whether you can do it at all depends on
exactly what you mean when you say that the data used for the regressions are
not the same as those used for the plots. The typical way would be to do
splom(DF,
panel = function(x, y, ...) {
panel.xy
Have you considered "table"?
spencer graves
Paul Green wrote:
How does one get counts for grouped data
from ungrouped data. For example, how can
I get
X1 X2 Count
1 1 1
1 2 2
2 1 1
2 2 1
from
X1 X2
A
On Thu, 2003-09-04 at 12:00, Vadim Ogranovich wrote:
> I admit I should have been more clear in my original posting. Let me
> try again (and I do know that by deafulat read.table discards
> everything after '#' which is why I use comment.char="", my bad not to
> mention this).
>
>
> Here is a typ
If you have a special need, it probably far more time effective on your
part to write a special function rather than attempt to convince the very
busy R developers that they should add a new feature to a very old function
(is this a better use of their time than, say, fixing long identified bugs
On Thu, 4 Sep 2003, Paul Green wrote:
> How does one get counts for grouped data
> from ungrouped data. For example, how can
> I get
>
> X1 X2 Count
> 1 1 1
> 1 2 2
> 2 1 1
> 2 2 1
>
> from
>
> X1 X2
>
For example (variations are possible),
y <- 100 * runif(400)
a <- gl(4, 100)
x <- gl(3, 7, 400)
library(lattice)
bwplot(y ~ x | a, scales = list(y = "free"),
ylim = list(c(0, 100), c(0, 200), c(0, 100), c(0, 200)))
(Assuming you have up to date versions of R and lattice).
On Thursday
I have compiled R 1.7.1 with gnome and installed the gtkDevice on a Linux
RH 8 system. This is my first use of this device and I have two
questions about it.
1. After running R --rui="gnome", the console comes up. To open a
graphics window, I open the gtkDevice library [library(gtkDevice)], th
How does one get counts for grouped data
from ungrouped data. For example, how can
I get
X1 X2 Count
1 1 1
1 2 2
2 1 1
2 2 1
from
X1 X2
AA
AB
BB
AB
BA
Hello
When I run
scatter.smooth(jitter(weight), jitter(height2), span = .25, evaluation
= 50, pch = '.')
I get the type of graph I thought I would get, but also a warning.
k-d tree limited by memory. ncmax= 528
I always get concerned when there are warnings I don't understand.
What's a
Would S Poetry be the sort of thing you are looking for?
Patrick Burns
Burns Statistics
[EMAIL PROTECTED]
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of S Poetry and "A Guide for the Unwilling S User")
Rado Bonk wrote:
Hi,
Does anybody know suitable documents (manuals) on writing user f
On Thu, 4 Sep 2003, Marcel Vieira wrote:
> Dear R users,
>
> I am trying to minimise a function using "nlm".
>
> I am getting the following error message: "Error: function is too long to
> keep source"
>
> The function is really very long (about 100 A4 pages).
>
> Is there anything I could do to s
I admit I should have been more clear in my original posting. Let me try again (and I
do know that by deafulat read.table discards everything after '#' which is why I use
comment.char="", my bad not to mention this).
Here is a typical example of my data file:
#keyvalue
foo 1.2
boo
XLSolutions Corporation ([1]www.xlsolutions-corp.com) is pleased to
announce a two-day course, "Splus/R: Complementing and Extending
Statistical Computing for SAS Users"
[2]www.xlsolutions-corp.com/Rsas.htm
Dates/City: October 9-10, 2003 in Washington DC
October 2-3,
Marcel Vieira wrote:
Thanks a lot for your help.
But I am getting that error message when I am trying to
load my function. Then I can't use anything to minimise it.
Is there anything I can do to increase R's
capacity for loading very long functions?
I assume by 'load' you must be somehow using 'so
Sorry Folks,
I'm sure I could suss out the answer myself but I need it
soon ... !
1. Given a set of 4 variables X,Y,Z,W in a dataframe DF, I make
a scatter-plot matrix using splom(DF).
2. I do all regressions of U on V using lm(U~V), where U and V
are all 12 different ordered pairs from X,Y
I have a personal rule that any function I write that is longer than
about one page should be modularized. This rule pushes me to think
carefully about how to structure the problem. It also helps me debug my
code and modify it as appropriate. If I can develop appropriate
"primatives", I g
On Thu, Sep 04, 2003 at 04:10:12PM +0100, Wayne Jones wrote:
> I am using the RODBC functionality to query a database. I am trying to read
> in a columns of strings which have a character field lengths greater than
> 255.
> The data.frame that I recieve back from the RODBC query only contains the
On Thu, Sep 04, 2003 at 05:37:46PM +0200, Brunschwig, Hadassa {PDMM~Basel} wrote:
> Is there an equivalent in R for the dos() command in S?
help(system)
Hth, Dirk
--
Those are my principles, and if you don't like them... well, I have others.
-- Gr
Thanks a lot for your help.
But I am getting that error message when I am trying to
load my function. Then I can't use anything to minimise it.
Is there anything I can do to increase R's
capacity for loading very long functions?
Many thanks.
Marcel
Have you considered "optim" in library(MASS)? "
Have you considered the two books by Venables and Ripley (2002) Modern
Applied Statistics in S and (2000) S Programming (both Springer)? If
yes, I don't know what you mean by "the usually available manuals."
hope this helps.
Rado Bonk wrote:
Hi,
Does anybody know suitable documents (manuals)
Have you considered "optim" in library(MASS)? "optim" will
optionally output the hessian, which can be used to obtain confidence
intervals in many cases.
hope this helps. spencer graves
Marcel Vieira wrote:
Dear R users,
I am trying to minimise a function using "nlm".
I am getting the fo
Hi,
Does anybody know suitable documents (manuals) on writing user functions
(covering loops, conditions ...) in R? Other than the usually available
manuals.
Thanks,
Rado
--
Radoslav Bonk M.S.
Dept. of Physical Geography and Geoecology
Faculty of Sciences, Comenius University
Mlynska Dolina 8
Dear R users,
I am trying to minimise a function using "nlm".
I am getting the following error message: "Error: function is too long to
keep source"
The function is really very long (about 100 A4 pages).
Is there anything I could do to solve this problem?
At the moment I am using "nlmin" in S
> "Ulrich" == Ulrich Leopold <[EMAIL PROTECTED]>
> on Thu, 04 Sep 2003 14:41:41 +0200 writes:
Ulrich> Dear list, sorry for having bothering you. I found
Ulrich> the problem. It was the a stupid error made by me. R
Ulrich> could not recognise the variable as it is of course
From: "Spencer Graves" <[EMAIL PROTECTED]>
> Your observation that qqnorm "does not appear to be very general" is
> rebutted by Venables and Ripley (2002) Modern Applied Statistics with S,
> 4th ed. (Springer, p.108): "One of the best ways to compare the
> distribution of a sample x with a dist
Hi, ¿How i cant exexute a script in R without the environment of R?, my
script uses the package tcltk, i like view only the interface without tehe
environment of R 1.7.1
Ej
name script---> probe.R
tt<-tktoplevel()
but<-tkbutton()
and execute in win (icon or line command) probe.R and see the int
Hello R-people
Is there an equivalent in R for the dos() command in S?
We are trying to write a function which will initiate the Metropolis algorithm run
with BUGS. That means we have a file containing the commands for BUGS which we usually
type in manually in the command prompt to run BUGS. I
Thanks Marlene, that's exactly what I was hoping for.
Best,
-Francisco
On Thursday, September 4, 2003, at 02:37 AM, Marlene Mueller wrote:
R is very similar to Gauss for this kind of task.
Try:
e1 <- x[,23] == 0
e2 <- x[,12] > 1
e3 <- x[,4] < 15
e <- e1 | e2 | e3 # e1 or e2 or e3
x
Hello there fellow R-users,
I am using the RODBC functionality to query a database. I am trying to read
in a columns of strings which have a character field lengths greater than
255.
The data.frame that I recieve back from the RODBC query only contains the
first 255 characters (the rest having
On Fri, 5 Sep 2003, Philip Rhoades wrote:
> Hi people,
>
> I have made some progress trying to work out how to solve this problem
> but I have got a bit stuck - sorry if this turns out to be a simple
> exercise . .
>
> Allelic Differentiation (AD) in genetics measures the number of
> different all
Yes, that is one scenario and for that we need a better class
(possibly a better data.frame class).
But there are other scenarios for which a special class for the
column is better. Which is why I asked.
> Steve Dutky <[EMAIL PROTECTED]> wrote:
>> I have a function that manipulates a list of num
Hi,
I found the problem, now it is working fine. cheers Martin
On Thursday 04 September 2003 16:20, Martin Wegmann wrote:
> Hello R user,
>
> I have several data frames with >100 columns and I did a linear regression
> over time of each column
>
> df1.lm <- lapply(df1, function(x) lm(x~year)$co
Paul Meagher wrote:
> 2. Does R have a suite of "best-fit" tools for finding the best
> fitting-probability distribution for any observed probability distribution?
I think that the best-fitting probability distribution for an observed
probability distribution is the empirical distribution of your
Your observation that qqnorm "does not appear to be very general" is
rebutted by Venables and Ripley (2002) Modern Applied Statistics with S,
4th ed. (Springer, p.108): "One of the best ways to compare the
distribution of a sample x with a distribution is to use a Q-Q plot. ...
This idea ca
Hi there,
I have four panels in a lattice bwplot. I want to have
two different ylim for the panels, for example panels
[1,1] and [1,2] with ylim=c(0,200) and panels [2,1]
and [2,2] with ylim=c(0,100).
Thanks for help in advance.
Mahbub.
__
[EMAIL PRO
Dear users,
is anybody of you aware of a R command to perform laplace transform or
even its inversion?
Thank you very much.
Luca
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Hello R user,
I have several data frames with >100 columns and I did a linear regression
over time of each column
df1.lm <- lapply(df1, function(x) lm(x~year)$coeff[2])
that worked fine and I get slope of each column oder time - until I divided
df1 by df2
df3 <- df1/df2
> df3.lm <- lapply(
Please note Student-Newman-Keuls is NOT a recommended multiple comparison procedure.
In the language of Hsu (1996), Student-Newman-Keuls is not even a "confident
inequalities" method. In other words, it does not control the probability of making at
least one incorrect assertion of inequality (wh
Hi people,
I have made some progress trying to work out how to solve this problem
but I have got a bit stuck - sorry if this turns out to be a simple
exercise . .
Allelic Differentiation (AD) in genetics measures the number of
different alleles between (say) two populations eg:
Organisms i
On Thu, 4 Sep 2003, Roger Koenker wrote:
> The officially sanctioned way to put the expression "lambda_1 = x" in a title
> is something like this:
>
> title(substitute(lambda[1] == lamb, list(lamb = x)))
>
> but suppose I have two lambdas and would like something like
>
> "lambda_1 = x
My apologies for the last email that only contained the message and not my
reply. Here is what I meant to send.
- Original Message -
From: "Richard A. O'Keefe" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Thursday, September 04, 2003 2:56 AM
Subject: Re: [R] Overlaying graphs
> I d
- Original Message -
From: "Richard A. O'Keefe" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Thursday, September 04, 2003 2:56 AM
Subject: Re: [R] Overlaying graphs
> I do not know how to overlay the curve graphic on top of hist graphic.
>
> Do you know about the "add=TRUE" option
The officially sanctioned way to put the expression "lambda_1 = x" in a title
is something like this:
title(substitute(lambda[1] == lamb, list(lamb = x)))
but suppose I have two lambdas and would like something like
"lambda_1 = x_1 , lambda_2 = x_2"
to appear. What then? Undou
Hi
On 4 Sep 2003 at 14:35, Ulrich Leopold wrote:
> > E.g.,
> >
> > mydata$difference <- mydata$x - mydata$y
> >
>
> That's what I thought, but I get the following message:
>
> > propLSK.STONE.Pox0t30$Pox0t30STONE-propLSK.STONE.Pox0t30$Pox0t30
> numeric(0
Ulrich Leopold <[EMAIL PROTECTED]> writes:
> > E.g.,
> > mydata$difference <- mydata$x - mydata$y
> >
>
> That's what I thought, but I get the following message:
>
> > propLSK.STONE.Pox0t30$Pox0t30STONE-propLSK.STONE.Pox0t30$Pox0t30
> numeric(0)
>
> Does it mean the resulting vector is empty?
Dear list,
sorry for having bothering you. I found the problem. It was the a stupid
error made by me. R could not recognise the variable as it is of course case
sensitive for names. So I specified the wrong variable name and R did
complain about it with "numeric(0)".
Ulrich
Peter Dalgaard BSA
2*log(likelihood ratio) is approximately chi-square for nested
models. AIC = (-2)*(log(likelihood)-k), where k = number of parameters
in the model.
Thus, del(AIC) = 2*(log(likelihood ratio)-del(k)). If the trend is
strictly linear, then it involves only 1 parameter, so del(k) = 1. Then
E.g.,
mydata$difference <- mydata$x - mydata$y
That's what I thought, but I get the following message:
> propLSK.STONE.Pox0t30$Pox0t30STONE-propLSK.STONE.Pox0t30$Pox0t30
numeric(0)
Does it mean the resulting vector is empty? If yes, what could be the reason
for it? Both columns are available:
Hi
I have two geostatistical models from geoR. An ordinary kriging model with
AIC=-148.6 and a universal kriging model with AIC=-156.7, there are 345
data points. The improvement shown by the AIC by adding a trend component
to the model seems quite small given the number of data points, is the
I think the Mozilla plugin site explicitly says that you cannot copy the
Java plugin into the Mozilla plugin directory. You have to make a symbolic
link to it in the plugin directory. Please try that.
Jason Turner <[EMAIL PROTECTED]>
Sent by: [EMAIL PROTECTED]
09/03/2003 07:32 PM
On 4 Sep 2003, Ulrich Leopold wrote:
> could someone point me to the right command to subtract 2 columns in a
> data.frame. Might be a bit embarrassing question. But I cannot figure
> out how to do this simple command in R.
Suppose your data frame is called foo, and you want the first column minu
Hi,
I'm using the boot package to bootstrap a linear model. The boot command
is:
> blm01 <- boot(mat, boot.fishpower, 1000, strata=boot.strata)
I'm having several problems with the linear model so I decided to check
the stratification. The first thing I did was checking the number of
observation
Is the following what you want?
> DF <- data.frame(a=1:2, b=3:4)
> DF$a-DF$b
[1] -2 -2
> DF[,"a"]-DF[,"b"]
[1] -2 -2
hope this helps. spencer graves
Ulrich Leopold wrote:
Dear list,
could someone point me to the right command to subtract 2 columns in a
data.frame. Might be a bit embarrassing qu
Ulrich Leopold <[EMAIL PROTECTED]> writes:
> Dear list,
>
> could someone point me to the right command to subtract 2 columns in a
> data.frame. Might be a bit embarrassing question. But I cannot figure
> out how to do this simple command in R.
E.g.,
mydata$difference <- mydata$x - mydata$y
--
Dear list,
could someone point me to the right command to subtract 2 columns in a
data.frame. Might be a bit embarrassing question. But I cannot figure
out how to do this simple command in R.
Thanks, Ulrich
--
__
Ulrich Leopold MSc.
Department of
On Thu, 4 Sep 2003, Britta Lintfert wrote:
> I have to do an ANOVA (or is it a MANOVA) with 6 Variables (called HsL,
> LsH, Hp, Lp, G, and) and 6 categories (OQ, Go, RC, AV, CC, Sk), the
> examples in the literature couldn't help me so far. Who can help me??
Perhaps the documentation of aov()
Hello,
I have to do an ANOVA (or is it a MANOVA) with 6 Variables (called HsL,
LsH, Hp, Lp, G, and) and 6 categories (OQ, Go, RC, AV, CC, Sk), the
examples in the literature couldn't help me so far. Who can help me??
Thank
Britta
__
[EMAIL PROTECTE
> "Vadim" == Vadim Ogranovich <[EMAIL PROTECTED]>
> on Wed, 3 Sep 2003 14:29:25 -0700 writes:
Vadim> Hi, I thought it would be convenient if the
Vadim> check.names argument to read.table, which currently
Vadim> can only be TRUE/FALSE, could take a function value
Vadim>
R is very similar to Gauss for this kind of task.
Try:
e1 <- x[,23] == 0
e2 <- x[,12] > 1
e3 <- x[,4] < 15
e <- e1 | e2 | e3 # e1 or e2 or e3
x <- x[!e,] # keep if NOT e
Hope that helps,
Marlene
Francisco J. Bido wrote:
Hi,
I am translating some Gauss code to R. Gauss has
82 matches
Mail list logo
