I would recommend not representing means by bars at all.
Bars are for counts, stacking from zero. Means are point estimates.
ggplot has a lot of routines for displaying means with errors bars:
geom_linerange, geom_pointrange. To hone your ggplot skills I
recommend looking into these geoms.
Hi there,
I started getting a new error with the latest mclust package version 3.3.1.
My only solution was to install the older package 3.2.1 or even 3.1-10. , (i
think older ones will still work since i ve been using it for a while)
the sentence giving trouble is:
BIC -
Hi,
Rob Hyndman's forecast package does exponential smoothing forecasting
based on state space models (and lots of other stuff, ARIMA et al.).
It's not exactly the companion package to his book, but it comes close.
The book's (Forecasting with Exponential Smoothing - The State Space
On Fri, 11 Sep 2009 18:56:36 +0200, Gabor Grothendieck
ggrothendi...@gmail.com wrote:
in the devel version. If that does not help let me know offline
and I will try to help you.
Thanks Gabor,
I solved the problem.
Here is the code in case somebody else wants to have full completions for
I would like to know if you have any suggestions how to visualize the
results from a paired t-test (see the example data below). I tried to
produce plots that show the mean and CI's from the original data and the
estimate of the difference between means and the confidence intervals (see
below)
After upgrading R to 2.9.2, I can't use the anova() fuction.
It says could not find function Varcov .
What's wrong with my computer? Help needed, thanks!
Yao Zhu
Department of Urology
Fudan University Shanghai Cancer Center
No. 270 Dongan Road, Shanghai, China
[[alternative HTML version
Hi,
I am trying to create a heatmap with some specific requirements. Specifically,
I need to be able to center the color-scale around 0, and I need to truncate
the
data so that a few extreme values do not cause the rest of the heatmap to
appear
black (on a red/green scale).
After reading
I uses the Design library.
take this example:
library(Design)
n - 1000
set.seed(731)
age - 50 + 12*rnorm(n)
label(age) - Age
sex - factor(sample(c('Male','Female'), n,
rep=TRUE, prob=c(.6, .4)))
cens - 15*runif(n)
h - .02*exp(.04*(age-50)+.8*(sex=='Female'))
dt - -log(runif(n))/h
On Sep 12, 2009, at 5:24 AM, zhu yao wrote:
After upgrading R to 2.9.2, I can't use the anova() fuction.
It says could not find function Varcov .
What's wrong with my computer? Help needed, thanks!
You have not given us very much information but from the naming
conventions I would guess
Hi everyone
I have a little problem with R. I built a lineal regression equation using
stepAIC function in both directions. Once I get this formula (lineal
regression), I would like to save in a txt file data refered to p-value,
r-squared, coefficients,...from the choosen model previously
I've had the same problem with predict.Design, and have sent an email to the
maintainer of the Design package at Vanderbilt University. I wasn't even
able to run the examples given on the help page of predict.Design - I
received the same error about Varcov that you did.
I *think* it's a
Did you type library(Hmisc,T) before loading Design?
Carlos
--
From: David Freedman 3.14da...@gmail.com
Sent: Saturday, September 12, 2009 8:26 AM
To: r-help@r-project.org
Subject: Re: [R] could not find function Varcov after upgrade of R?
I've
I am unable to reproduce that problem, either. Have both of you
updated both the Design and Hmisc packages? Varcov is in Hmisc.
--
David Winsemius
On Sep 12, 2009, at 8:26 AM, David Freedman wrote:
I've had the same problem with predict.Design, and have sent an
email to the
maintainer of
I apologize for this change in the Hmisc package which breaks the
current version of Design in CRAN. Design should be updated by early
next week. In the meantime there are two solutions:
1. Install the rms package which is a replacement for Design with better
graphics, and note the few
On Sep 12, 2009, at 7:56 AM, Lucas Sevilla García wrote:
Hi everyone
I have a little problem with R. I built a lineal regression equation
using stepAIC function in both directions. Once I get this formula
(lineal regression), I would like to save in a txt file data refered
to p-value,
Hi Zhu,
could not find function Varcov after upgrade of R?
Frank Harrell (author of Design) has noted in another thread that Hmisc has
changed... The problem is that functions like anova.Design call a function
in the _old_ Hmisc package called Varcov.default. In the new version of
Hmisc this
On Fri, Sep 11, 2009 at 12:15 PM, A Ezhil ezhi...@yahoo.com wrote:
Dear All,
I have large matrix (46000 x 11250). I would like to do the linear regression
for each row. I wrote a simple function that has lm() and used
apply(mat,1,func). The issue is that it takes ages to load the file and
Hi Michael,
I've used the R plug-in and really like it. You can read my instructions
on how to install and use it by going to Amazon.com, searching for the
book, R for SAS and SPSS Users and then search inside the book for
the section, Running R from SPSS. I've only got about 3 pages on it
(28
Another possible interpretation is that each row contains several
vectors, possibly laid end to end. For example, if the row J were
length 30 (which it isn't), the first 10 might be Y, the next 10 X1,
and the next N2. The function might be lm(J[1:10] ~ J[11:20] +
J[21:30]).
If this is what is
madmax1425 wrote:
Hi there,
I started getting a new error with the latest mclust package version 3.3.1.
My only solution was to install the older package 3.2.1 or even 3.1-10. , (i
think older ones will still work since i ve been using it for a while)
the sentence giving trouble is:
BIC
Dear all,
I have a data set as follows:
ID cycle.number cycle.result
1 2525 1 38
2 2525 2 38
3 2525 3 25
4 2525 4
Is there a place to find a list of the legal values for the coord_trans
parameters. I spent a bunch of time searching the ggplot2 docs and r-help
for same without success. I also made an attempt at looking at the code in R
which also failed.
In the book, or with apropos(^Trans, ignore = F)
Try this:
If cycle.number is ordered:
do.call(rbind, lapply(split(x, x$ID), tail, 1))
On Sat, Sep 12, 2009 at 12:36 PM, caroline choong carolinevcho...@gmail.com
wrote:
Dear all,
I have a data set as follows:
ID cycle.number cycle.result
1 2525
On Sep 12, 2009, at 11:36 AM, caroline choong wrote:
Dear all,
I have a data set as follows:
ID cycle.number cycle.result
1 2525 1 38
2 2525 2 38
3 2525 3
Searching help pages of contributed packages just got
easier with the release of the new sos package. This is a
replacement for and substantial enhancement of the existing
RSiteSearch package. To learn more about it, try
vignette(sos).
We hope you find this as useful as we
I am trying to estimate by MLE weibull coefficients and deviation. But how
can i estimate deviation? I tried to find at the list and at the internet
this but couldn't make it. Anyone could help me on this?
Thanks.
[[alternative HTML version deleted]]
Hello R-help community:
I have what I think is a simple question that I hope someone can
answer. When using the median() function on any zoo object (in
particular, mine is an irregular time series), I get the following
error, which is thrown from .gt():
Error in if (xi == xj) 0L else if
Thanks for the reminder - actually I think I've become sloppy about the 'T'
(and the order of loading the Hmisc and Design packages), but that doesn't
seem to be the problem. Also, all of my packages have been updated
david
Carlos Alzola wrote:
Did you type library(Hmisc,T) before loading
Thanks for your replies.
I use the following script:
if(!exists(i)) stop (set the variable i, call. = FALSE)
but before the stop expression, Error gets displayed:
Error: set the variable i
Is there another function that stops the execution, prints an expression
without printing Error or any
Can you provide a reproducible example. See last line to every message
on r-help. When I try it it works:
median(zoo(1:3))
2
2
On Sat, Sep 12, 2009 at 1:14 PM, Marc Chiarini marc.chiar...@tufts.edu wrote:
Hello R-help community:
I have what I think is a simple question that I hope someone
Hello,
I am trying to get fitted/estimated values using kernel regression and a
triangular kernel. I have found packages that easily fit values from a
kernel regression (e.g. ksmooth) but do not have a triangular distribution
option, and density estimators that have triangular distribution
Try:
RSiteSearch(kernel triangular)
On Sat, Sep 12, 2009 at 1:51 PM, Bryan thespamho...@gmail.com wrote:
Hello,
I am trying to get fitted/estimated values using kernel regression and a
triangular kernel. I have found packages that easily fit values from a
kernel regression (e.g. ksmooth)
Dear all,
I can't load my workspace of 25Mo on R version 2.9.2, because of a stack
overflow. But I saved it normally (save.image()), and I didn't get any
notification...
Does anyone know what that can be due to? Is there any limitation of number of
objects (+/-63000)?
Thanks
Edwige Polus.
David Freedman wrote:
Thanks for the reminder - actually I think I've become sloppy about the 'T'
(and the order of loading the Hmisc and Design packages), but that doesn't
seem to be the problem. Also, all of my packages have been updated
Note that Frank Harrell already answered that
sebed1110-div...@yahoo.fr wrote:
Dear all,
I can't load my workspace of 25Mo on R version 2.9.2, because of a stack
overflow. But I saved it normally (save.image()), and I didn't get any
notification...
Does anyone know what that can be due to? Is there any limitation of number of
objects
My apologies. I don't know how it happened, but somehow the library
must have been corrupted. I re-installed the zoo package, and all was
well again. Thanks!
Regards,
Marc
Gabor Grothendieck wrote:
Can you provide a reproducible example. See last line to every message
on r-help. When I
Dear guRus,
I am starting to work with the ggplot2 package and have two very dumb
questions:
1) deterministic position_jitter - the jittering is stochastic; is there
any way to get a deterministic jittering? For instance:
example.data -
On Sat, Sep 12, 2009 at 1:34 PM, Stephan Kolassa stephan.kola...@gmx.de wrote:
Dear guRus,
I am starting to work with the ggplot2 package and have two very dumb
questions:
1) deterministic position_jitter - the jittering is stochastic; is there any
way to get a deterministic jittering? For
Hello johannes,
You're example looks nice and I am hoping to see more ideas from other
members.
Just one tiny idea:
In -
stripchart
Also use ylim to include the ZERO line (and then actually add the line) like
this:
plot.ylim - c(min(d, 0), max(d, 0))
abline(h = 0, lty = 2, col = blue, lwd =2)
Gabor,
Thanks for your quick reply (on a weekend even!) I've looked through the
results of the search you recommended, and several related searches, and
don't see anything exceptionally helpful. Kernel regression is a relatively
new analysis for me; I apologize for needing a little more
Also have a look at the foreach package:
http://finzi.psych.upenn.edu/R/library/foreach/html/foreach-package.html
On Fri, Sep 11, 2009 at 11:05 PM, Noah Silverman n...@smartmediacorp.comwrote:
Hi,
Our discussions about 64 bit R has led me to another thought.
I have a nice dual core
What about kknn -- that was listed as having the triangular distribution?
On Sat, Sep 12, 2009 at 3:42 PM, Bryan thespamho...@gmail.com wrote:
Gabor,
Thanks for your quick reply (on a weekend even!) I've looked through the
results of the search you recommended, and several related searches,
I need to detect outliers in a large data set which is highly right-skewed. I
plan to use medcouple-based outlier detection. Is there any support for
medcouple-based outlier detection in R? Are there any other routines in R to
perform outlier detection in highly right-skewed data?
Manuj Sharma
On Sep 12, 2009, at 3:54 PM, Manuj Sharma wrote:
I need to detect outliers in a large data set which is highly right-
skewed. I plan to use medcouple-based outlier detection. Is there
any support for medcouple-based outlier detection in R?
library(sos) # a package that links to Baron's
Hi Brian,
I am trying to get fitted/estimated values using kernel regression and a
triangular kernel.
Look at Loader's locfit package. You are likely to be pleasantly surprised.
Regards, Mark.
Bryan-65 wrote:
Hello,
I am trying to get fitted/estimated values using kernel regression
Hi,
the error message is Error: protect(): protection stack overflow
Edwige.
Dear all,
I can't load my workspace of 25Mo on R version 2.9.2, because of
But I saved it normally (save.image()), and I didn't get any notification...
Does anyone know what
Dear Experts,
I'm a new R user and I'll appreciate your help regarding the following. I'm
trying to generate an exhaustive search of all candidate models in a simple
linear regression and select the one with the lowest CV-error (or
alternatively the lowest Error on a Test set -- if I have lots of
I originally looked over kknn because I need to be able to specify a
bandwidth parameter. I am trying to replicate some previous non-R work in
R, so I can't stray to far from the procedure used there. In reading the
paper referenced in the docs, I see that kknn can reduce to the
NadarayaWatson
You can specify the number of nearest neighbors.
On Sat, Sep 12, 2009 at 5:16 PM, Bryan thespamho...@gmail.com wrote:
I originally looked over kknn because I need to be able to specify a
bandwidth parameter. I am trying to replicate some previous non-R work in
R, so I can't stray to far from
On 12/09/2009 5:04 PM, sebed1110-div...@yahoo.fr wrote:
Hi,
the error message is Error: protect(): protection stack overflow
63000 objects is far more than most people would use, so you may have
hit an internal limit. The protection stack is used internally by R
to temporarily mark objects
Dear All
I hope you can help me with this small problem. I want to draw a normal
distribution line to this data:
p-rnorm(100, mean=5, sd=3000)
hist(p)
Kabeli
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing
Do watch out, however, for *where* i exits.
That is, if you type search() you will see a list of environments in
which i might be found. You're probably assuming that i, if
exists(i) is true, is in .GlobalEnv, but it might be in one of the
other environments, in which case exists('i') will be
Dear All
let me go one step further by asking you if you could help me show that the
distribution of this data in normal. have a little idea (by trial and
error) but i seem to not fully understand how its done.
H-rnorm(100, mean=5, sd=3000)
par(las=1)
hist(H, breaks=seq(4, 6,
A better subject for your question might have been helpful. There are many
options for hist and truehist in the MASS package, but this might help:
x=rnorm(100, mean=5, sd=3000)
hist(x, prob=T)
x2=density(x)
lines(x2$x,x2$y)
KABELI MEFANE wrote:
Dear All
I hope you can help me with
Thank you Sir
I have been trying to come up with the code for 6 hours thats why i ended up
forgetting the title.
Kabeli
--- On Sat, 12/9/09, David Freedman 3.14da...@gmail.com wrote:
From: David Freedman 3.14da...@gmail.com
Subject: Re: [R] (no subject)
To: r-help@r-project.org
Date:
Why don't you just do this:
H-rnorm(100, mean=5, sd=3000)
par(las=1)
hist(H, breaks=seq(4, 6, 1000), freq=F)
f- function(x) exp(-(x-5000)^2/1800)/sqrt(1800*pi)
x- seq(4, 6, 100)
lines(x, dnorm(x, 5, 3000))
On Sat, Sep 12, 2009 at 5:47 PM, KABELI
Thank You
It really works fine and i do understand it. Now i can sleep, its 0200 hours
here.
Why don't you just do this:
H-rnorm(100, mean=5, sd=3000)
par(las=1)
hist(H, breaks=seq(4, 6, 1000), freq=F)
f- function(x) exp(-(x-5000)^2/1800)/sqrt(1800*pi)
x- seq(4,
I have a huge number such as 78923698701
z-78923698701
I want to find the integer of a given location, for example here, what is
the 2nd number? 8.
Thanks in advance!
--
View this message in context:
http://www.nabble.com/the-integer-of-a-given-location-tp25418729p25418729.html
Sent from the R
Is this what you want:
z-78923698701
substring(as.character(z), 2, 2)
[1] 8
On Sat, Sep 12, 2009 at 6:16 PM, darkhorn darkh...@gmail.com wrote:
I have a huge number such as 78923698701
z-78923698701
I want to find the integer of a given location, for example here, what is
the 2nd
Hi darkhorn,
Here are two suggestions:
# Suggestion 1
z - 78923698701
foo - function(x, pos) strsplit(as.character(x),)[[1]][pos]
foo(z,2)
# [1] 8
# Suggestion 2
foo2 - function(x, pos) substr(x,pos,pos)
foo2(z,2)
# [1] 8
See ?strsplit and ?substr for more details.
HTH,
Jorge
On Sat, Sep 12,
Thank you very much. :-)
as.integer(substring(as.character(z), 2, 2))
[1] 8
as.integer(foo2(z,2))
[1] 8
--
View this message in context:
http://www.nabble.com/the-integer-of-a-given-location-tp25418729p25419555.html
Sent from the R help mailing list archive at Nabble.com.
Marc Schwartz-3 wrote:
Using the data that is in the online plot rather than the above, here
is a first go. Note that I am not drawing the background grid in the
barplot or the lines for table below it. These could be added if you
really need them.
snip
HTH,
Marc Schwartz
Hi,
In the code below I create a small data.frame (dat) and then cut it
into different groups using CutList. The lists in CutList allow to me
choose whatever columns I want from dat and allow me to cut it into
any number of groups by changing the lists. It seems to work OK but
when I'm done I
On Sun, 2009-07-26 at 13:17 +0200, Poersching wrote:
stvienna wiener schrieb:
Hi all,
I am plotting a financial time series, but I need a more detailed X-Axis.
Example:
x - zoo(rnorm(1:6000), as.Date(1992-11-11)+c(1:6000))
plot(x)
The X-Axis is labeled 1995, 2000 and 2005.
I
Try this:
library(zoo)
x - zoo(rnorm(1:6000), as.Date(1992-11-11)+c(1:6000))
plot(x, xaxt = n)
# cut time into years, remove duplicate years and convert back to Date
yy - as.Date(unique(cut(time(x), year)))
axis(1, yy, format(yy, %y))
There are a number of examples of custom X axes in the
On Sep 12, 2009, at 10:13 PM, Mark Knecht wrote:
Hi,
In the code below I create a small data.frame (dat) and then cut it
into different groups using CutList. The lists in CutList allow to me
choose whatever columns I want from dat and allow me to cut it into
any number of groups by changing
There is a command-line flag for this:
tystie% R --help
...
--max-ppsize=NSet max size of protect stack to N
so you do not need to re-compile. It is not uncommon to need more
space to load objects than to save them, and the need to raise this
limit to re-load a worskpace has come up
67 matches
Mail list logo
