I have written a function make.fun(), which I keep in my personal
``miscellaneous'' package. It searches the current working directory
for files named ``*.R'' and sources them if their modification date
is later than the date stored in ``.Last.make.date''. (The variable
.Last.make.date then ge
Hi, yes a loop would work. Maybe there are other options also. Bootstrapping
a PCA with a loop can be done as follows. You will have to adjust the
dimension of the matrices/array according to the dimensions of your data and
according to the values that you want to retrieve from your PCA.
Start
Hi all,
I am doing bootstrap on a distance matrix, in which samples have been
drawn with replacement. After that I do PCA on a resulted matrix, and
these 2 steps are repeated 1000 times.
pca(x) is a vector where I wanted to store all 1000 PCAs; and x is from
1 to 1000
SampleD is a new matrix a
Hi ,Ping .
There ARE two components using the iris[,-5] data.
The Mclust method is using the BIC value to obtain the optimal number of
components of the model, and the result is two.
Try to use Mc$parameters to see the parameters for each component.
I suggest u to read the help document seriousl
Hi,
Currently I have a dataset of 2400*408. And I would like to apply PCR method
to study the any correlation between the tests.
My current data is in data.frame and I have formed horizontal(1-407) to be
the exact data, and (408) to be my results data(Yes and No)
I have also binarized these Yes an
smith_cc yahoo.com> writes:
>
>
> The object is a mcmc sample from lmer. I am using R v2.7.1. Please let me
> know what additional information I can provide, hopefully I am just making a
> simple mistake. Thanks in advance!
>
> > data(ratdrink, package = 'faraway')
> > rd.er <- lmer(wt ~ weeks
Your sample works just fine:
> x <- read.table(textConnection("Name Heigth
+ W1 22
+ W2 45"), header=TRUE, row.names=1)
> closeAllConnections()
>
> x
Heigth
W1 22
W2 45
>
Take a look at your data file. You might have some lines with a
different number of fields.
On Mon, Jun
On 1/07/2008, at 9:30 AM, Peter Alspach wrote:
Georg
?lm suggests "'na.exclude' can be useful"
But he (Georg) did indeed use na.action=na.exclude !!!
So that's not the problem/solution.
The difference between what he did and what you did is
essentially that
Georg
?lm suggests "'na.exclude' can be useful"
Thus:
> round(resid(lm(c(1:4,NA,9)~c(3:7,NA), na.action=na.exclude)), 5)
1 2 3 4 5 6
0 0 0 0 NA NA
HTH
Peter Alspach
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of Georg Ehret
>
The object is a mcmc sample from lmer. I am using R v2.7.1. Please let me
know what additional information I can provide, hopefully I am just making a
simple mistake. Thanks in advance!
> data(ratdrink, package = 'faraway')
> rd.er <- lmer(wt ~ weeks*treat + (1 | subject), data = ratdrink)
> rd.m
Now that we have case cohort model , we have 1000 people and 50 cases
Let the first 10 cases occur at the same time
second 10 "
third 10 "
fourth 10"
fifth10"
How easy is it to randomly sample 50 di
Dear R community,Can I please get some advice on the following: I wish
to obtain a list of residuals, padded by NAs for NAs in my source data. I
tried several options of "na.action", but did not succeed...
Example: I would like to get "0,0,0,0,NA,NA":
> a
[1] 1 2 3 4 NA 9
> b
[1] 3 4 5
On Mon, 2008-06-30 at 10:41 -0700, Birgitle wrote:
> I tried to use ctree but am not sure about the meaning of the plot.
>
> My.data.ct<-ctree(Resp~., data=My.data)
> plot(My.data.ct)
>
> My data.frame contains 88 explanatory variables (continous,ordered/unordered
> multistate,count data) and one
I'm surprised that 'norm' was suggested, given your clear statement
that you have both categorical and continuous variables.
The right package (within the "Shafer stable" of cat, norm, mix, and pan)
is the 'mix' package. It is expressly written for this case of
mixed variable types.
You would nee
Hello all,
I would like to know whether there exists any way to calculate the AIC
or the BIC criteria for a nnet object (not only in the multinomial
case).
Commands like stepAIC, AIC or extractAIC do not work with a feed
forward neural net and I cannot find any command that deals with nnet
ob
On 30/06/2008, at 11:43 PM, mysimbaa wrote:
Dear R users,
Is it possible to add comments in a plot window?
I have 3 plots -> this plots have to be commented on same window
Is possible to do the following :
http://www.nabble.com/file/p18193822/plot%2526comments.JPG
plot%26comments.JPG
I don't
On 6/30/08, Troy S <[EMAIL PROTECTED]> wrote:
> r-friends--
>
> I am trying to make a lattice plot with a single label at 0.05. A reference
> line at y=0.05 as well... This is what I have so far. The label reads 0.0
> and there is a grid instead of a single reference line. Can someone help
does it really getting kicked down to another row or is this just an
artifact of printing in the command window?
On Mon, Jun 30, 2008 at 2:16 PM, <[EMAIL PROTECTED]> wrote:
> Hi,
>
> I have a CSV file where each row has at least 20 columns and some rows have
> up
> to 30 columns of data. When I u
Why are you not using read.csv()?
> -Original Message-
> From: [EMAIL PROTECTED]
> [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
> Sent: Monday, June 30, 2008 2:17 PM
> To: R-help@r-project.org
> Subject: [R] Problem reading a CSV
>
> Hi,
>
> I have a CSV file where each row
Robert A LaBudde wrote:
At 03:02 AM 6/30/2008, Robert A. LaBudde wrote:
I'm looking for a package that has a start-of-the-art method of
imputation of missing values in a data frame with both continuous and
factor columns.
I've found transcan() in 'Hmisc', which appears to be possibly suited
Hi,
I have a CSV file where each row has at least 20 columns and some rows have up
to 30 columns of data. When I use the command,
Pathways<-read.table('MetaCycSample3.csv',sep=',',header=FALSE,quote='"')
anything past the 21st column gets kicked down to a new row. How can I fix this?
Thanks,
-N
r-friends--
I am trying to make a lattice plot with a single label at 0.05. A reference
line at y=0.05 as well... This is what I have so far. The label reads 0.0 and
there is a grid instead of a single reference line. Can someone help please?
Troy
x<-18:35
(pv<-1/(x-17))
xydf<-data.frame(x,
At 03:02 AM 6/30/2008, Robert A. LaBudde wrote:
I'm looking for a package that has a start-of-the-art method of
imputation of missing values in a data frame with both continuous
and factor columns.
I've found transcan() in 'Hmisc', which appears to be possibly
suited to my needs, but I haven'
R is doing what you are telling it to do. You aren't assigning the
result of your indexing to a new data.frame, and so it is simply
print()ing the result. Example,
x <- 1:10
x[-1]
x
vs.
x <- 1:10
x <- x[-1]
x
Joe Trubisz wrote:
Hi...
I have a rather large dataframe that I'm trying to rem
I tried to use ctree but am not sure about the meaning of the plot.
My.data.cf<-ctree(Resp~., data=My.data)
plot(FemMalSex_NAavoid88.ct)
My data.frame contains 88 explanatory variables (continous,ordered/unordered
multistate,count data) and one response with two groups.
In the plot are only two
Ido M. Tamir wrote:
Hi,
yes a bold statement, but I get different behaviour
from 2.6.2 and 2.7.0 in read.table, and I don't find
any documentation in http://cran.r-project.org/src/base/NEWS.
A file like (space delimited):
foo + .
bar - .
This was reverted in 2.7.1
o
hello everyone
I have used the function Mclust, and i found the result(the component $z) is
just two class, why?
Mc <- Mclust(iris[,-5])
Mc$z
thanks
wangchunping
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/
Hi all,
I have a problem with the function "read.table"
I have a text file wich I want to analyse in R
Example:
Name Heigth
W1 22
W2 45
Expression:
> parameters.W.df <- read.table("parameters.W.txt", header=TRUE,
> row.names=1)
What I get back:
Error in scan, line 1 has not
Hi...
I have a rather large dataframe that I'm trying to remove rows from.
I'm issuing the command:
dtx[-which(dtx$rdate > "2008-06-16"),]
and it tries to print out over 170,000 lines of output. So...I did:
options(max.print=1e6)
and ran it again. It worked, but when I did a:
which(dtx$rdate
Hi,
yes a bold statement, but I get different behaviour
from 2.6.2 and 2.7.0 in read.table, and I don't find
any documentation in http://cran.r-project.org/src/base/NEWS.
A file like (space delimited):
foo + .
bar - .
2.7.0:
> tab <- read.table("test.txt",as.is=TRUE)
> tab
Hi there,
I am currently working in a research institute and I have only a reduced
account. My aim is to install the New version of R under my own directory to
prove the advantages of this version to my IT service to lead them to install
it on the full server.
So I download the last .tar.gz
Dear R users,
Is it possible to add comments in a plot window?
I have 3 plots -> this plots have to be commented on same window
Is possible to do the following :
http://www.nabble.com/file/p18193822/plot%2526comments.JPG
plot%26comments.JPG
I don't know how to do it. Maybe plot.window or someth
Here is a way that works for me using tkexamp in the TeachingDemos package
(which uses tkrplot internally):
calc2 <- function(mat, vary1=0, vary2=0) calc(mat, c(vary1,vary2))
library(TeachingDemos)
tkexamp( calc2(mat, vary2=vary[2]),
list(vary1=list('slider',from=0,to=4000, resolution=10
On Tue, Jun 24, 2008 at 3:32 AM, Thorsten Vogel
<[EMAIL PROTECTED]> wrote:
> Dear List Members
>
> As a relatively new R user I am extremely glad for there being a nice tool
> such as ggplot for producing easily nice graphs in R. Now I want to produce
> graphs with two y-axis. I know that this has
Try:
for(i in 1:10){
jpeg(sprintf("Rplots%02d.jpg", i))
plot(rnorm(20))
dev.off()
}
On Mon, Jun 30, 2008 at 11:58 AM, Leandro Marino <[EMAIL PROTECTED]>
wrote:
> Hi list,
>
> I want to make a lot of graphics to my end course project. So, i was using
> this sintax:
>
>
> jpeg(filename =
paste(sep="", "graf", 1:250, ".jpg")
See ?paste,
G.
On Mon, Jun 30, 2008 at 11:58:51AM -0300, Leandro Marino wrote:
> Hi list,
>
> I want to make a lot of graphics to my end course project. So, i was using
> this sintax:
>
>
> jpeg(filename = "graf01.jpg", width = 1024, height = 1024,
> u
Hi list,
I want to make a lot of graphics to my end course project. So, i was using
this sintax:
jpeg(filename = "graf01.jpg", width = 1024, height = 1024,
units = "px", pointsize = 25, quality = 100, bg = "grey95",
res = NA, restoreConsole = TRUE)
i=1
par(mfrow=c(4,1),col="grey90",fon
Hi list,
I want to make a lot of graphics to my end course project. So, i was using
this sintax:
jpeg(filename = "graf01.jpg", width = 1024, height = 1024,
units = "px", pointsize = 25, quality = 100, bg = "grey95",
res = NA, restoreConsole = TRUE)
i=1
par(mfrow=c(4,1),col="grey90",fon
On Mon, 30 Jun 2008, Juan Pablo Romero Méndez wrote:
Thanks!
It turned out that Rmpi was a good option for this problem after all.
To help with improving snow I'd be interested to hear more bout why
Rmpi works for you but snow did not.
Nevetheless, pnmath seems very promising, although it
Jenny,
You may try here: http://en.wikipedia.org/wiki/Normality_test which
mentions the R package nortest
and here;
The Probability Plot Correlation Coefficient Test for Normality, James
J. Filliben:
http://www.jstor.org/sici?sici=0040-1706(197502)17%3A1%3C111%3ATPPCCT%3E2.0.CO%3B2-6&cooki
Hi Vito
(question to the authors of MASS below)
2008/6/30 vito muggeo <[EMAIL PROTECTED]>:
> Dear Haubo,
> many thanks for your reply.
> Yes you are right, by scaling the "score", I get the same results.
>
> However it sounds strange to me. I understand that the SE and/or t-ratio of
> the intercep
sickboyedd gmail.com> writes:
>
>
> Hello all,
>
> I am hoping to use survival analysis to examine whether parasite attack
> increases nest death in a species of social wasp. I therefore have data for
>
> 1. Whether the nest "died" in the 6 week census period ("Status", where
> 1=died, 0=surv
Lauri Nikkinen wrote:
> R users,
>
> I have a problem with function strwidth in 2.7.1. I'm trying to set
> the plot margins in a way that horizontal
> column labels will fit to the graph. tmp.t is a list of data.frame
> objects. This code works well in 2.6.0.
>
>
I don't think this has to do wit
On 30 June 2008 at 08:57, Magnus Torfason wrote:
| Hi all, I would like the following code to work, but it doesn't:
|
| library(DBI)
| library(RODBC)
| m <- dbDriver("RODBC") # Example for dbConnect(DBI), causes error
| m <- dbDriver("ODBC") # Example for DBIDriver-class(DBI), causes error
|
|
Sorry, I found that there is a new bmp() device and when I lower the
resolution parameter e.g. to 72, everything works fine.
Best
Lauri
2008/6/30, Lauri Nikkinen <[EMAIL PROTECTED]>:
> R users,
>
> I have a problem with function strwidth in 2.7.1. I'm trying to set
> the plot margins in a way tha
"Juan Pablo Romero Méndez" <[EMAIL PROTECTED]> writes:
> Thanks!
>
> It turned out that Rmpi was a good option for this problem after all.
>
> Nevetheless, pnmath seems very promising, although it doesn't load in my
> system:
>
>
>> library(pnmath)
> Error in dyn.load(file, DLLpath = DLLpath, ...
Hi,
I cant seem to get some uppercase greek symbols (e.g. Delta) using
plotmath. I'm on version R 2.7.0 (2008-04-22) Fedora Core 7 (34
bit). I have installed a whole heap of fonts, but still no luck, and
any help would be appreciated.
Cheers,
Jarrod
--
The University of Edinburgh
Robert A. LaBudde wrote:
I'm looking for a package that has a start-of-the-art method of
imputation of missing values in a data frame with both continuous and
factor columns.
I've found transcan() in 'Hmisc', which appears to be possibly suited to
my needs, but I haven't been able to figure o
R users,
I have a problem with function strwidth in 2.7.1. I'm trying to set
the plot margins in a way that horizontal
column labels will fit to the graph. tmp.t is a list of data.frame
objects. This code works well in 2.6.0.
...snip..
library(gplots)
for (i in names(tmp.t)) {
bmp(filen
Hi all, I would like the following code to work, but it doesn't:
library(DBI)
library(RODBC)
m <- dbDriver("RODBC") # Example for dbConnect(DBI), causes error
m <- dbDriver("ODBC") # Example for DBIDriver-class(DBI), causes error
The errors are:
Error in do.call(as.character(drvName), list(...))
Hi,
thanks but not exactly.
If you plot x vs. y you will see that the function that fits the data is a
log-normal distribution multiplied with a constant.
So what I want to do is more like a regression..
Estimating parameters to a model..
Gunther
-Ursprüngliche Nachricht-
Von: Peng Jian
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
~Much better.
~ If m is your linear regression model,
~ * boxcox(m) in the MASS package will look for a power (more or less)
transformation to normalize the residuals -- see the
book for more information
~ * plot(m) will produce plots inclu
Thanks Ben - will give MASS package a look and try the boxcox function!
Appreciate your time in answering my question :o)
Jenny
On Mon, 30 Jun 2008, Ben Bolker wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
~Much better.
~ If m is your linear regression model,
~ * boxcox(m) in
Hi Ben and R-help communtiy,
More specifics:
I am using sea-surface temperature (averaged over an area) and also winds
(averaged over an area) to use in a linear regression model as predictors
for rainfall over a small region of Africa. So I have 1 time series of
sea-temp and one timeseries o
I agree with Ben . without providing any information of the data, we
cannot make inference on the distribution itself.
actually density estimation is a tough problem( and classical ). Of
course,
there are methods like GMM or some other method based on statistical
learning,
however, th
Thanks Gabor, this seems to work:
## plot with left and right axes
## modified from http://www.mayin.org/ajayshah/KB/R/html/g6.html
set.seed(1)
z <- zoo(cbind(A = cumsum(rnorm(100)), B = cumsum(rnorm(100, mean =
0.2
opar <- par(mai = c(.8, .8, .2, .8))
plot(z[,1], type = "l",
xlab = "X ax
Hi Romain,
Many thanks for this example as well.
Tolga
Romain Francois <[EMAIL PROTECTED]>
30/06/2008 12:33
To
[EMAIL PROTECTED]
cc
r-help@r-project.org
Subject
Re: [R] Plotting three time series on the same graph
Hello Tolga,
Further hacking on par(mar) leads me to the code below. I
Hi, Gunther,
maybe fitdistr() in MASS library can do the job ,
the code should be
>library(MASS)
> fitdistr( x, densfun = "log-normal")
by using your data we can obtain the parameters ,
meanlog sdlog
2.5808007 1.2999517
(0.3752637) (0.2653515)
is that what you want?
On 2008-6-30, at
Dear Vito
No, you are not wrong, but you should center score prior to model estimation:
summary(fm1 <- polr(factor(grade)~I(score - mean(score
which gives the same standard errors as do lrm. Now the intercepts
refer the median score rather than some potential unrealistic score of
0.
You can
As I didn't get Sweave to include tcltk graphics, I am desperately trying to
save R-tcltk graphics as *.jpeg, does anybody know whether there is a way to do
that?
any help would be highly appreciated,
best regards,
Andreas Posch
__
R-help@r-project.
Jenny Barnes mssl.ucl.ac.uk> writes:
>
> Dear R-help community,
>
> Does anybody know of a stats function in R that tells you which
> distribution best fits your data? I have tried look through the archives
> but have only found functions that tell you if it's normal or log etc.
> specifical
Hello Tolga,
Further hacking on par(mar) leads me to the code below. I hope it can
help you.
Cheers,
Romain
y <- 1:100 + runif( 100, min = -10, max = 10 )
x <- 1000 + 1:100 + runif( 100, min = -10, max = 10 )
z <- seq( 7, 25000, length.out = 100) + runif( 100, min = -2000, max
= 2000)
Received Mon 30 Jun 2008 8:58pm +1000 from Karl Ove Hufthammer:
> Ingo Michaelis:
>
> > I try to use the interactive plot package playwith on my machine (Ubuntu
> > 8.04 64 bit / Gnome) using R version 2.7.1. My problem is that the widgets
> > are not shown. I tried to plot the examples from the
Dear R-help community,
Does anybody know of a stats function in R that tells you which
distribution best fits your data? I have tried look through the archives
but have only found functions that tell you if it's normal or log etc.
specifically - I am looking for a function that tells you (give
In the zoo package there is an example of a graph with an axis on
the left and on the right in the examples section of ?plot.zoo. Run
that with but use ylab = "" on the plot call to make room for the third axis.
To add a third axis supposing 1 - 15 is the range of our third time series:
usr <- p
Thanks Romain for trying to help, but my issue is that I have three time
series, not two, so at least two of them would have to go on the same
side.
There may be no solution to this problem in R but if there is, would
appreciate hearing about it from someone ?
Figure 1 in this link shows what
Ingo Michaelis:
> I try to use the interactive plot package playwith on my machine (Ubuntu
> 8.04 64 bit / Gnome) using R version 2.7.1. My problem is that the widgets
> are not shown. I tried to plot the examples from the documentation, but it
> does not work anyway.
FWIW, I have the same proble
Hi
[EMAIL PROTECTED] napsal dne 30.06.2008 11:14:48:
> Dear R help list
>
> I have recently started using R to visualize time series of water level
> measurements. The code I wrote
> does exactly what I want:
>
> plot(x, a$B112, axes=FALSE, ylim=c(405,410), col="red", pch=15,
> type="o", yla
Dear all,
It appears that MASS::polr() and Design::lrm() return the same point
estimates but different st.errs when fitting proportional odds models,
grade<-c(4,4,2,4,3,2,3,1,3,3,2,2,3,3,2,4,2,4,5,2,1,4,1,2,5,3,4,2,2,1)
score<-c(525,533,545,582,581,576,572,609,559,543,576,525,574,582,574,471,59
Hello,
I try to use the interactive plot package playwith on my machine (Ubuntu 8.04 64
bit / Gnome) using R version 2.7.1. My problem is that the widgets are not
shown. I tried to plot the examples from the documentation, but it does not work
anyway. I tried on a WindowsXP machine and everything
Dear list,
I have to vectors:
x <- rep(c(2,4,8,24,48,72),2)
y
<-c(82543,169105,207615,96633,31988,7005,82687,172931,205541,101842,31898,69
50)
that follows a log-normal function as
f(x)= SO/(sqrt(2*pi)*sigma *x) * exp(-(ln x - mu)^2/(2*sigma^2))
that is a log-normal distribution multiplied wit
Hi Daniel,
You did not make clear why you want to export the data. If you want to
export data to another program the usual way to export data to a text
file is through the use of write.table(). Something along the lines of:
summary(cars) # cars is a standard R dataset
write.table(summary(cars
Dear R help list
I have recently started using R to visualize time series of water level
measurements. The code I wrote
does exactly what I want:
plot(x, a$B112, axes=FALSE, ylim=c(405,410), col="red", pch=15,
type="o", ylab="metres above sea level", main="Main Plot Title")
axis(2, at=405:410,
Dear R Users,
I would like to plot three time series on the same graph, two axis on the
left and one axis on the right.
The time series that I am graphing on the left do not share a similar
scale: one has a range of 1:100 and the other a range of 25000:7. How
can I display the tick marks f
On 28 июн, 03:19, "Bricklemyer, Ross S" <[EMAIL PROTECTED]> wrote:
> I am having difficulty calculating the median of grouped data. I have 8 to
> 10 repeated measures per sample and I have successfully used the following
> code to calculate the average for each sample.
>
> libs.norm.preds.median
A small update for xlsReadWritePro is available.
(This is the shareware version of the free xlsReadWrite package, still
windows only)
= Changes in version 1.4.0 =
* Added 'default.' prefix for colClasses argument
(proposed by John Hathaway)
* Images - which have been added manually - ca
Robert,
Try Amelia, which can be used with Zelig for post-imputation estimation. I
find it a very helpful combination.
Shige
On Mon, Jun 30, 2008 at 3:02 PM, Robert A. LaBudde <[EMAIL PROTECTED]> wrote:
> I'm looking for a package that has a start-of-the-art method of imputation
> of missing va
I'm looking for a package that has a start-of-the-art method of
imputation of missing values in a data frame with both continuous and
factor columns.
I've found transcan() in 'Hmisc', which appears to be possibly suited
to my needs, but I haven't been able to figure out how to get a new
data
78 matches
Mail list logo
