On 6/16/07, owenman [EMAIL PROTECTED] wrote:
Hi Hadley,
I tried your suggestion, using ggplot2, but I am still having a problem. The
final plot lacks the figure legend -- which it had before I added the
scale_fill_identity() bit. Can you see what I am doing wrong?
(By the way, all I am
Furthermore, one day we will all be doing our statistics in C. So higher level
programming is predicted to become more difficult!
Cheers,
Simon.
Simon Blomberg, BSc (Hons), PhD, MAppStat.
Lecturer and Consultant Statistician
Faculty of Biological and Chemical Sciences
The University of
Thank you so much Robert. I haven't thought about the idea of clumping
categories together. One of the reason is because these categories are bridge
condition rating scores. They indeed represent different meaning and
serviceability conditions. They vary from 0-9. I have about 300,000 data in
Hello
I have a question about performing a similarity analysis using R.
I will perform a similarity analysis comparing species.
I have a datamatrix that looks like the Pictures you can see in the
mail. It contains bivariate data and data in this Min Max mode.
I had to alter the multivariate
Hello,
Is there a way to define the width of the axis tick marks on
traditionnal plots? I did not find anything specific on this topic in
the help and par(lwd=...) does not affect the tick marks. I guess that
using axes=FALSE and recreating the axis with the axis() command could
do the trick
Dear all,
For analysis of a longitudinal data set with fixed measurement in time I built
a gls model (nlme). For testing hypotheses in this model I used the
linear.hypothesis function from the car package. A check with the results
obtained in SAS proc MIXED with a repeated statement revealed
On 16-Jun-07 01:12:18, Marc Schwartz wrote:
On Sat, 2007-06-16 at 00:43 +0100, [EMAIL PROTECTED] wrote:
On 15-Jun-07 19:43:55, John Kane wrote:
--- Douglas Bates [EMAIL PROTECTED] wrote:
On 6/15/07, Nicholas Lewin-Koh [EMAIL PROTECTED]
wrote:
[...]
I think you mean A, not Z. First
Hello,
I'm currently using a boxplot to visualize data for three different
models. As I have three models, I'm plotting three parallel boxplots
for each factor.
This works fine - what I need now is a line connecting the medians of
each boxplot of each model. I want to do this in order to
Hi: I am brand new to this group ( and To Tinn-R), so I have my first question:
How do I turn on the Call-Tips? I went through the help and I have installed
the SciViews but still can't get it to work. I would really appreciate your
help.
-
TV dinner still
Respected Sir,
I am working on Hidden Markov Models for count data. My data
consist of number of new infectives
in a ward per month. I have data for about 50 months. How can I fit a Hidden
Markon Model to my data.
I am using 'repeated' package('hidden' and 'chidden' arguments). I would
Hello,
I'm currently using a simple plot to visualize some mean values. I'm
having ~200 datapoints on the x-axis, each has 10 records. I'm
currently plotting only the mean value of each of the datapoints.
What I need is a way to visualize the quartiles/error/whatever of
these points. I thought
On Sat, 16-Jun-2007 at 04:09PM +1200, Patrick Connolly wrote:
| On Fri, 15-Jun-2007 at 01:50PM -0700, Li-Jung Liang wrote:
|
| | Hi,
| |
| | I upgraded my system from FC4 to FC5. So now I have R version 2.5.0
| | (2007-04-23).
| | But I ran into a problem with starting device X11 (message
How about quantile regression? Have a look at
http://had.co.nz/ggplot2/stat_quantile.html for some examples of what
that might look like.
Hadley
On 6/16/07, Arne Brutschy [EMAIL PROTECTED] wrote:
Hello,
I'm currently using a simple plot to visualize some mean values. I'm
having ~200
I think there is still a small bug which I reported some time ago to
r-sig-finance
(https://stat.ethz.ch/pipermail/r-sig-finance/2005q4/000498.html) and
which takes effect if the time series is not stored in the variable 'x':
The line
write(x, file = OxSeries.csv, ncolumns = 1, append =
Hi Arne,
You might also take a look at Prof. Harrell's function:
require(Hmisc) ## req. library [note: also needs lattice]
?smedian.hilow
Then look at:
?xYplot
And, in particular, at: panel.xYplot(), sub Usage:
This does what you want.
## Example; also look at Prof Harrell's
You could calculate the confidence interval of the correlation at
your desired df: http://davidmlane.com/hyperstat/B8544.html
The below code takes as arguments the observed correlation, N, and
alpha, calculates the confidence interval and checks whether this
includes 0.
Yet another solution:
with(X,lm(get(Ytext)~Xvar))
On 14-Jun-07, at 5:18 PM, Greg Snow wrote:
Try:
lm( formula( paste( Ytext, '~ Xvar' ) ), data=X)
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
[EMAIL PROTECTED]
(801) 408-8111
-Original
I tried the following and it works for me (after the changes to make):
library(fSeries)
data(dem2gbp)
IanSeries = dem2gbp[, 1]
garchOxFit(~garch(1,1),IanSeries)
Any writing of data is performed in the GarchOxModelling.ox file.
The number of lines of code in the function .garchOxFit() does not
Line number 55 in the original mail from 2005 was a reference to
garchOxFit (not .garchOxFit) in fSeries version 220.10063 (not
240.10068), as mentioned in
https://stat.ethz.ch/pipermail/r-sig-finance/2005q4/000498.html . Of
course, in the current version of .garchOxFit, the line number has
Tirthadeep wrote:
Hi,
I am using logistic regression to classify a binary psychometric data. using
glm() and then predict.glm() i got the predicted odds ratio of the testing
data. Next i am going to plot ROC curve for the analysis of my study.
Now what i will do:
1. first select a
At 03:17 AM 6/16/2007, adschai wrote:
Thank you so much Robert. I haven't thought about the idea of
clumping categories together. One of the reason is because these
categories are bridge condition rating scores. They indeed represent
different meaning and serviceability conditions. They vary
On 6/14/07, Greg Snow [EMAIL PROTECTED] wrote:
Try:
lm( formula( paste( Ytext, '~ Xvar' ) ), data=X)
That type of construction is perilously close to parse(paste(...)) and
we know what Thomas said about that (see fortune(parse)).
A safer way of constructing a formula from names stored in a
Clearly X11() was found, so grDevices must be on the search path.
This error message is about X11 fonts.
It is allowed to exclude grDevices from the list of default packages, and
if you do, it is not loaded. That is a change in 2.5.0 but not a bug.
If you chose not to ask for it, we presume you
Nicholas Lewin-Koh wrote:
Hi,
I am doing a retrospective analysis on a cohort from a designed trial,
and I am fitting
the model
fit-glmD(survived ~ Covariate*Therapy + confounder,myDat,X=TRUE,
Y=TRUE, family=binomial())
For logistic regression you can also use Design's lrm function which
A couple of easy ways are to create the calling sequence as a call or
character string and then evaluate it:
eval(bquote(lm(.(as.name(Ytext)) ~ Xvar, X)))
eval(parse(text = paste(lm(, Ytext, ~ Xvar, X
Note that these solutions both have the advantage over some of the prior
solutions that
Dear Tine,
linear.hypothesis() currently has no method specifically for gls objects,
and so this usage invokes the default method. I'm not sure off-hand what's
appropriate for an F-test in this context (and indeed why the default test
is inappropriate). Can you describe the correct test or supply
I have a data set that contains income data and a group identifier. Sort of
like:
DATA
Group,Income
A,2300
B,6776
A,6668
A,6768
B,9879
C,5577
A,7867
(etc),(etc)
I am trying to compute the gini coefficient for each group.
I have tried the following and none seem to do the trick:
1)
I have read the R online help and wiki and I cannot seem to get something to
work the way I need it to.
I want to create a new data frame from an subset of an existing data frame
which has no reference to the original superset. If you following this
example, what I am trying to do may make more
Dear users;
I am doing GLMs with the Gamma distribution, and I always get errors (no valid
set of coefficients: please supply starting values) or warnings (NaNs
produced in log(x)) when I use the links identity or inverse, but I don´t get
them if I use the log link.
For example:
HI
Is there any function in R that tells us error rate(misclassification rate)
for logistic regression type classification?
i also want to know the function to determine type I and type II error.
I have found a link where misclass and confusion are used. But I dont
know the package name.
I want to use copula package in R to generate random vector of multivariate F
distribution with a pre-specified diagonal covariance matrix, say, diag(2, 3,
0, 0, 0). Can someone tell me how I can specify the diagonal covariance
matrix in the copula function mvdc? Thank you very much.
In the R code of Mardia's test, what does the line x1 = x[x[, p] == i, -p]
mean? Thanks a lot!
function (x)
{
p = dim(x)[2]
f = p - 1
clases = length(table(x[, p]))
for (i in 1:clases) {
x1 = x[x[, p] == i, -p]
ndat = dim(x1)[1]
mo3 = mo3(x1)
The October 2006 R News had an article in which the authors discussed a new
package that implemented the Birnbaum-Saunders distribution. However, the
package (aptly named bs) does not appear to be available for installation.
Does anyone know the status of this package? Thanks.
Tom La Bone
On 16 June 2007 at 16:50, Jiao Yang wrote:
| In the R code of Mardia's test, what does the line x1 = x[x[, p] == i, -p]
mean? Thanks a lot!
Read it from the inside out:
x[, p] == i find elements of column p in x that equal i
the result is
Not sure what 'x2' is that you are plotting; it is not defined.
read.delimand subset return dataframes, so you don't need
data.frame.
Here is something that does work:
x - shirt,size,40
+ shirt,color,10
+ shirt,length,10
+ shirt,brand, 1
+ shoes,style,5
+ shoes,brand,4
+ shoes,color,1
x -
does this do what you want?
plot(0, xlim=c(0,10), xaxt='n')
axis(1, at=c(0,5,10))
axis(1,at=0:10,tcl=-.2, labels=FALSE)
On 6/14/07, Sébastien [EMAIL PROTECTED] wrote:
Hello,
Is there a way to define the width of the axis tick marks on
traditionnal plots? I did not find anything
Well apparently this has nothing to do with the gini() command.
I cannot get it to work for something as simple as sum()
Here is the little example I am playing with, maybe someone can help me find
my error:
a-c(A,B,C,A,B,C,A,A,C,B)
b-c(23,6534,456,234,7,567,345,9,565,345)
c-cbind(a,b)
by(c,
I too have no idea what the object named x2 is, or where it came
from. Particularly since after your use of subset(), the new
dataframe, y, *does* include a row where V2 = 'color'.
But I have a guess at what your problem may be.
In your original dataframe (x) the first and second columns are
I received your error now:
In the function .garchOxFit the following line:
write(x, file = OxSeries.csv, ncolumns = 1, append = TRUE)
should be changed to:
write(x = series, file = OxSeries.csv, ncolumns = 1, append = TRUE)
(See below for how to reproduce this error - and identify the fix).
Hi,
When I using Xemacs+ESS to write a R code, I need to comment out a code line
by line putting #
It is possible to configure ESS to comment and uncomment a selected block of
code.
Thanks
Ronaldo
--
__ _
/ `-' ) ,,,
| | ()|||[:::e
\__.-._) ''' unk
--
Prof. Ronaldo
On 6/16/07, Ronaldo Reis Junior [EMAIL PROTECTED] wrote:
When I using Xemacs+ESS to write a R code, I need to comment out a code line
by line putting #
It is possible to configure ESS to comment and uncomment a selected block of
code.
This question probably belongs on the ESS-help mailing
Economics Guy wrote:
Well apparently this has nothing to do with the gini() command.
I cannot get it to work for something as simple as sum()
Here is the little example I am playing with, maybe someone can help me find
my error:
a-c(A,B,C,A,B,C,A,A,C,B)
Not really, but it is a good way to get major and minor tick marks
(thanks it might be useful later in my project). What I to modify is the
width of the segments which correspond to the marks?
I know that I can do that with a lwd command in axis()... but there
might be an option to set directly
I am using plot(survfit(Surv(time,status) ~...) and would like to add
error bars rather than the confidence intervals. Am I able to do this
at specified times? e.g. when time = 20 40.
leukemia.surv - survfit(Surv(time, status) ~ x, data = aml)
plot(leukemia.surv, lty = 2:3,xlim = c(0,50))
#can
44 matches
Mail list logo