Gabor Grothendieck wrote:
> On 8/17/06, Martin Maechler <[EMAIL PROTECTED]> wrote:
>> > "Gregor" == Gregor Gorjanc <[EMAIL PROTECTED]>
>> > on Fri, 11 Aug 2006 00:27:27 + (UTC) writes:
[snip]
>
> There are two problems:
>
> 1. as.POSIXlt is not generic. (This problem may not be
Please read about lattice.par.settings, and not trellis.par.settings. Trellis is
in S/S-plus. Anupam.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-
The parameter names are axis.text$font and axis.text$cex .
Try issuing the command:
trellis.par.get()
to get a complete list.
Here is an example:
histogram(1:10, par.settings = list(axis.text = list(font = 2, cex = 0.5)))
On 8/17/06, Debarchana Ghosh <[EMAIL PROTECTED]> wrote:
> Hi All,
>
> I
Hi All,
I'm trying to modify some of the default graphic parameters in a
conditional histogram. While I was able to change the default grey
background to white, I couldn't change the axis.font or the xlab font.
I used the following code:
/histogram(~V751|V013+V025, finalbase, xlab="Heard of HI
Many useful diagnostic plots can be recreated in the usual plot()
framework, with only a little coding effort. In this case, I would
imagine that
plot(dframe$log2game, fitted(D2C29.nlme))
abline(0,1)
should get pretty close, if the name of the dataframe containing the
variable is 'dframe'.
Andre
Dear List,
I am trying to fit Truncated Lognormal to a data set that is
'truncated' from above a certain value, say, 0.01. Below is what I
was able to come up with. I would appreciate it if you could review
and make any necessary changes.
# This is modified off the code for 'dtnorm' of library(
Dear R listers,
If I try to start the X11 device in Gentoo, I get the following
complaint from R:
---
> X11()
Error in X11() : could not find any X11 fonts
Check that the Font Path is correct.
---
xset -q produces the following output:
---
Keybo
Hi
This is a second call for abstracts.
Please forward and circulate to other interested parties.
[apologies for any cross-posting]
DSC 2007, a conference on systems and environments for statistical
computing, will take place in Auckland, New Zealand on February 15 & 16,
2007.
We invite abstract
There's something that either you have not thought of or neglected to tell
us: If you have k variables in the data frame, you will need a data frame
of k variables and one row to be able to rbind() to the bottom of the
original one. What are you going to put in place for non-numeric variables?
P
Use the first few rows of iris as test data and try this
where isnum is 1 for each numeric column and NA for
others.
irish <- head(iris)
isnum <- ifelse(sapply(iris, class) == "numeric", 1, NA)
iris.data <- data.matrix(iris)
rbind(iris, colMeans(iris.data) * isnum, sd(iris.data) * isnum)
On 8/17
Adrian Dusa gmail.com> writes:
>
> On Thursday 17 August 2006 21:41, Peter Dalgaard wrote:
> > [...]
> > Breaks the feature that you get to www.r-project.org just by typing
> > "r", though...
>
> Oh, this is very simple to fix. I created a bookmark named "R" with the above
> location and assig
getting s-apply to skip columns with non-numeric data?
I have a dataframe x of w columns.
Some columns are numeric, some are not.
I wish to create a function to calculate the mean and
standard deviation of each numeric column, and then
bind the column mean and standard deviation to the
bottom
Iuri:
Here is an example of how a model would be specified using lmer using a couple
of your factors:
fm <- lmer(response.variable ~ chain*sector*resp
+(chain*sector*resp|GroupingID), data)
This will give you a main effect for each factor and all possible interactions.
However, do you have
Dear list,
This is more of a stats question than an R question per se. First, I
realize there has been a lot of discussion about the problems with
estimating P-values from F-ratios for mixed-effects models in lme4.
Using mcmcsamp() seems like a great alternative for evaluating the
significance of
Dear r-helpers,
Can anyone suggest a remedy to the following failure of Rgraphviz to
load?
> library(Rgraphviz)
Loading required package: graph
Loading required package: Ruuid
Error in dyn.load(x, as.logical(local), as.logical(now)) :
unable to load shared library '/Library/Frameworks/
Hi
Take a look at panel.identify() (in the 'lattice' package).
I'm not sure if it will help you because I cannot run your example code.
Paul
Douglas Bates wrote:
> Most plotting functions in the nlme package use lattice graphics
> functions based on the grid package. Identify will not work wi
When I run cut.Date or cut.POSIXt with argument breaks
= "weeks", the function gives the first day of that
week, unless the date is the first day of the week, in
which case it gives an error message as in:
> cut(as.Date("2006-08-16"), "week")
[1] 2006-08-14
Levels: 2006-08-14
> cut(as.Date("2006-0
month.name
class(month.name)
character"
tmp <- data.frame(m=rep(month.name, 2), y=rnorm(24))
bwplot(y ~ m, data=tmp)
tmp <- data.frame(m=ordered(rep(month.name, 2), levels=month.name), y=rnorm(24))
bwplot(y ~ m, data=tmp)
__
R-help@stat.math.ethz.ch mai
On Thu, 2006-08-17 at 11:46 -0700, Pamela Allen wrote:
> I am having a problem using boxlpot with my data. I have my data arranged
> in a data table, and two of my columns are "mass" and "month". I am trying
> to plot the mass of my study animals by month, thus I would like to have it
> in the or
On Thursday 17 August 2006 21:41, Peter Dalgaard wrote:
> [...]
> Breaks the feature that you get to www.r-project.org just by typing
> "r", though...
Oh, this is very simple to fix. I created a bookmark named "R" with the above
location and assigned it a keyword "r".
Now, everytime I type "r" in
I am having a problem using boxlpot with my data. I have my data arranged
in a data table, and two of my columns are "mass" and "month". I am trying
to plot the mass of my study animals by month, thus I would like to have it
in the order of January to December. The problem is that R orders each
Adrian Dusa <[EMAIL PROTECTED]> writes:
> Dear list,
>
> For all those interested who use Firefox as the main browser, here is a quick
> way to make R related searches:
>
> type "about:config" in the address bar
> search for "keyword.url"
> and modify it
> to
> "http://finzi.psych.upenn.edu/c
On 8/17/06, Martin Maechler <[EMAIL PROTECTED]> wrote:
> > "Gregor" == Gregor Gorjanc <[EMAIL PROTECTED]>
> > on Fri, 11 Aug 2006 00:27:27 + (UTC) writes:
>
>Gregor> Gabor Grothendieck gmail.com> writes:
>>>
>>> Here are three ways:
>>>
>>> xx <- as.Date("2006-0
"Kuhn, Max" <[EMAIL PROTECTED]> writes:
> I was hoping that someone could try to reproduce an error that I am
> getting. The R Site Search keeps timing out on me, so apologies of this
> has already come up.
>
> I'm using
>
> > R.version
>
> When I use unlink as below, the help system is disa
Dear list,
For all those interested who use Firefox as the main browser, here is a quick
way to make R related searches:
type "about:config" in the address bar
search for "keyword.url"
and modify it
to
"http://finzi.psych.upenn.edu/cgi-bin/namazu.cgi?idxname=functions&idxname=docs&idxname=Rhe
## initial example
a = list(1:5, 5:9)
b = lapply(a,"*",2)
library(abind) ## you may need to download abind from CRAN
abind(data.frame(a), data.frame(b), along=.5)
## data.frames with column names
a = data.frame(first=1:5, second=5:9)
b = a^2
abind(a, b, along=.5, new.names=c("a","b"))
_
I was hoping that someone could try to reproduce an error that I am
getting. The R Site Search keeps timing out on me, so apologies of this
has already come up.
I'm using
> R.version
_
platform i386-pc-mingw32
arch i386
Try:
mapply(rbind, a, b, SIMPLIFY = FALSE)
On 8/17/06, Domenico Vistocco <[EMAIL PROTECTED]> wrote:
> Dear helpeRs,
>
> suppose I have two lists as follows:
>
> a = list(1:5,5:9)
> b = lapply(a,"*",2)
>
>
> I would like to rbind-ing the two lists, that is I would like to use
> something as rbind
Dear helpeRs,
suppose I have two lists as follows:
a = list(1:5,5:9)
b = lapply(a,"*",2)
I would like to rbind-ing the two lists, that is I would like to use
something as rbind applied
component to component for the two list.
I have used the following solution:
fun.tile.wt = function(list1,
Burt Gunter just reminded me that the completion time could also
be affected by the numbers of levels of each of the factors, especially
random effects: With N records, any variance components / mixed model
software using MLE or REML will have to invert repeatedly an N x N
matrix for the
Yours truly menne-biomed.de> writes:
...
> Recently, a colleague fitted gastric emptying
> curves using GraphPad, with 100% success, and
> nls failed for one third of these. When we
> checked GraphPads output more closely, some of
> the coefficients looked like 2.1 with a confidence
> interval i
I am trying to replicate Finn and Kayandé (1997) study on G-theory
application on Marketing. The idea is to have people evaluate some aspects
of service quality for chains on different economy sectors. Then, conduct a
G-study to identify the generalizability coefficient estimates for different
D-st
We have tried on many machines, from my laptop to a dual core Intel
processor with 1GB of RAM.
On 8/17/06, Spencer Graves <[EMAIL PROTECTED]> wrote:
>
> Hi, Iuri:
>
> How much RAM and how fast a microprocessor (and what version of
> Windows) do you have? You might still try it in R under Wi
Hi, Iuri:
How much RAM and how fast a microprocessor (and what version of
Windows) do you have? You might still try it in R under Windows. The
results might be comparable or dramatically better in R than in SPSS or
SAS.
hope this helps.
Spencer Graves
Iuri Gavronski wrot
Hi, Iuri:
If you've got an 8086 AND a huge data set, compute time might be a
problem with 'lmer'. However, if you a reasonably modern computer and
only a a few thousand observations, 'lmer' should complete almost in the
blink of an eye -- or at least in less time than it would talk for
> Yes, you can do that for lattice-based plots. The functions in the lattice
> package produce objects of class "trellis" which can be stored in a list and
> processed or updated at a later time:
Or for ggplot based plots:
install.packages("ggplot")
library(ggplot)
> plotList <- list(length=3)
sem() handles only equality constraints among parameters, and this model
> requires linear inequality constraints.
>
> I'm aware of SEM software that handles inequality constraints, but I'm not
> aware of anything in R that will do it "out of the box." One possibility is
> to write out the likeli
9500 records. It didn`t run in SPSS or SAS on Windows machines, so I am
trying to convert the SPSS script to R to run in a RISC station at the
university.
On 8/17/06, Doran, Harold <[EMAIL PROTECTED]> wrote:
>
> Iuri:
>
> The lmer function is optimal for large data with crossed random effects.
> H
This will (should) be a piece of cake for lmer. But, I don't speak SPSS.
Can you write your model out as a linear model and give a brief
description of the data and your problem?
In addition to what Spencer noted as help below, you should also check
out the vignette in the mlmRev package. This wi
Iuri:
The lmer function is optimal for large data with crossed random effects.
How large are your data?
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Iuri Gavronski
> Sent: Thursday, August 17, 2006 11:08 AM
> To: Spencer Graves
> Cc: r-help@stat
Thank you for your reply.
VARCOMP is available at SPSS advanced models, I'm not sure for how long it
exists... I only work with SPSS for the last 4 years...
My model only has crossed random effects, what perhaps would drive me to
lmer().
However, as I have unbalanced data (why it is normally called
On Thu, 17 Aug 2006, Lothar Botelho-Machado wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Thank you,
>
> It seems that a list of plots is just possible using lattice plots. But
> that's a good keyword for me to look for, I appreciate your help!
Actually, that is not a list of *pl
Hi, Markus,
Are these always integers? Why do you think they should be normal or
Weibull? Seems more like a mixture with a point mass at 0 and something
else (e.g. Poisson, negative binomial, normal). Though it's hard to tell
with what you have provided. If that's the case you'll have to write
Also check out the displaylist:
http://tolstoy.newcastle.edu.au/R/help/04/05/0817.html
On 8/17/06, Lothar Botelho-Machado <[EMAIL PROTECTED]> wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Thank you,
>
> It seems that a list of plots is just possible using lattice plots. But
> that'
Most plotting functions in the nlme package use lattice graphics
functions based on the grid package. Identify will not work with
lattice graphics. I'm not sure if there is a replacement.
On 8/17/06, Greg Distiller <[EMAIL PROTECTED]> wrote:
> I have a quick question regarding the use of identif
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Thank you,
It seems that a list of plots is just possible using lattice plots. But
that's a good keyword for me to look for, I appreciate your help!
Lothar
Christos Hatzis wrote:
> Yes, you can do that for lattice-based plots. The functions in the
Dear Rick,
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Rick Bilonick
> Sent: Thursday, August 17, 2006 7:07 AM
> To: John Fox
> Cc: 'R Help'; 'Rick Bilonick'
> Subject: Re: [R] Specifying Path Model in SEM for CFA
>
. . .
>
> I'm trying to
Dear Julie,
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of julie7.josse
> Sent: Thursday, August 17, 2006 4:01 AM
> To: r-help
> Subject: [R] tkinser
> Importance: High
>
> Dear list,
>
> I 'd like to know if it is possible to delete my text win
On Wed, 2006-08-16 at 17:01 -0400, John Fox wrote:
> Dear Rick,
>
> It's unclear to me what you mean by constraining "each column of the factor
> matrix to sum to one." If you intend to constrain the loadings on each
> factor to sum to one, sem() won't do that, since it supports only equality
> co
Will this do? best, Simon
## simulate some data...
set.seed(1)
joint <- c(rep(1,20),rep(2,20),rep(3,20))
time <- runif(60)+1
subject <- factor(rep(1:12,rep(5,12)))
mu <- time*joint
joint <- factor(joint)
y <- rgamma(mu,mu)
## fit model
b <- glmmPQL(y~joint*time,random=~1|subject,family=Gamma(link
I have a quick question regarding the use of identify to interact with
points on a scatterplot. My question is essentially: can identify be used
when one is plotting model objects to generate diagnostic plots?
Specifically I am using NLME.
For example, I am plotting the fitted values on the x ax
Dear list,
I 'd like to know if it is possible to delete my text window after running it??
I have add a Menu to my text window and so i can for example open a script;
then i run it and i have my result on my R console.
But i'd like that after running, the code disappears automatically. i d'like
Dear Paul,
(I forgot to answer over the weekend). With mpi it is essentially the same.
When using makeCluster, specify the number of slaves. If you have three
machines, and you want each to run two slave processes, just use a 6.
Before that, though, you should tell LAM/MPI how to set up the "la
Martin Maechler wrote:
>> "Gregor" == Gregor Gorjanc <[EMAIL PROTECTED]>
>> on Fri, 11 Aug 2006 00:27:27 + (UTC) writes:
>
> Gregor> Gabor Grothendieck gmail.com> writes:
> >>
> >> Here are three ways:
> >>
> >> xx <- as.Date("2006-01-05")
> >>
> >>
> "Gregor" == Gregor Gorjanc <[EMAIL PROTECTED]>
> on Fri, 11 Aug 2006 00:27:27 + (UTC) writes:
Gregor> Gabor Grothendieck gmail.com> writes:
>>
>> Here are three ways:
>>
>> xx <- as.Date("2006-01-05")
>>
>> # 1. use as.POSIXlt
>> as.POSIXlt(xx)
Hans-Joerg Bibiko wrote:
> Dear all,
>
> I wrote some functions using the special argument '...'. OK, it works.
>
> But if I call such a function which also called such a function, then
> I get an error message about unused arguments.
>
> Here's an example:
>
> fun1 <- function(x,a=1)
> {
>
The following reshapes mat so we can take the means of the columns
of the resulting 3d array and then transposes it back to the original
orientation:
t(colMeans(array(t(mat), c(100, 448, 24
You might want to try it on this test set first where anscombe
is an 11x8 data set built into R. He
nls not converging for zero-noise cases
epamail.epa.gov> writes:
>
> No doubt Doug Bates would gladly accept patches ... .
>
The zero-noise case is irrlevant in practice, but quite often I have uttered
&/(!! (vituperation filter on) when nls did not converge with real data. The
dreaded "min
> "Arnau" == Arnau Mir Torres <[EMAIL PROTECTED]>
> on Wed, 16 Aug 2006 19:38:27 +0200 writes:
Arnau> Hello.
Arnau> I have the following distance matrix between 8 points:
Arnau> [1,] 0.00 3.162278 7.280110 8.544004 7.071068 9.899495 6.403124
8.062258
Arnau> [
59 matches
Mail list logo