When using fitdistr() with the exponential, log-normal and beta distributions,
you get the relevent rate, mean, standard deviation, shape1 and shape2 but
you get a number bellow those that are in () and I was wandering what exactly
those numbers represent and how they relate to the data.
Many
Sorry, I solved by myself.
Thanks.
Vito
From: Vito Ricci vito_ricci at yahoo.com
Subject: [R] ECDF values
Date: 2005-11-17 07:20:35 GMT (33 minutes ago)
Dear UseRs,
maybe is a silly question: how can I get Empirical CDF
values from an object created with ecdf()?? Using
print I obtain:
On 11/17/05, Vito Ricci [EMAIL PROTECTED] wrote:
Dear UseRs,
maybe is a silly question: how can I get Empirical CDF
values from an object created with ecdf()??
The return value of ecdf is a function. Use it as you would any other function.
-Deepayan
Vito == Vito Ricci [EMAIL PROTECTED]
on Thu, 17 Nov 2005 08:20:35 +0100 (CET) writes:
Vito Dear UseRs,
Vito maybe is a silly question: how can I get Empirical CDF
Vito values from an object created with ecdf()?? Using
Vito print I obtain:
Vito Empirical CDF
Vito
Hi
There is a very good introduction script to R on
http://www.r-project.org/
under manuals, including an index of nice functions. For
example you will find the basic plots, how to sort vectors and
so on.
Furthermore have a look at
?RSiteSearch
It is very useful to search in R archives for
Yuying Shi wrote:
Dear Sir/Madam,
I am a beginner in R. Here is my questions.
1. Can you give me one test for randomness (a name and descriptive
paragraph is sufficient).
2. I have learned a uniform random number generator [e.g. not the
algorithms: i)Wichmann-Hill, ii)
Thanks you.
Now, I can install and update some packages from local repos.
I put all R packages (zip files, using W2K)
in h:/myFolder/myRepository,
library(tools)
write_PACKAGES(h:/myFolder/myRepository)
options(repos=c(LocalR=file:///h:/myFolder/myRepository))
getOption(repos)
Dear List,
can anyone tell me how to plot a discontinuous y-axis (ordinate
with a -/ /- break sign) to fit in data with a wide range without the
need of logarthimic transformation? My data are distributed like this:
(abscissa: 1:10)
1. vector to plot
Min. 1st Qu. MedianMean 3rd Qu.
Hi,
values in parentesis below the estimate of a parameter
is the standard deviation of parameter, that's a
measure of variability.
Regards.
Vito
set.seed(123)
x - rgamma(100, shape = 5, rate = 0.1)
fitdistr(x, gamma)
shape rate
6.45947303 0.13593172
I have worked out that when I fit data I get an estimate and a standard error,
but all the definitions I can find describe the standard error of a sample as
the standard deviation over the square root of the sample size, so if I am
fitting to a log-normal distribution, what is the standard
str(summary(multinom.out)) often helps.
summary(multinom.out)$standard.errors
Arne Jol wrote:
Dear R users,
I'm using a multinomial LOGIT model to analyse choice behaviour of
consumers (as part of my masters thesis research).
Using the R documentation and search on the R website I have
-Original Message-
From: [EMAIL PROTECTED] [SMTP:[EMAIL PROTECTED] On Behalf Of Mark Miller
Sent: Thursday, November 17, 2005 10:16 AM
To: r-help@stat.math.ethz.ch
Subject: [R] Standard Error
I have worked out that when I fit data I get an estimate and a standard
error,
Hi
In Sweave, how does one change the size of the plots?
I tried using a hook:
echo=FALSE, print=FALSE, fig=TRUE=
options(SweaveHooks=list(fig=function() ps.options(width=1)))
library(graphics)
pairs(iris)
@
but this didn't change the size of the figure. How to make the
figures a
different
Ronaldo Reis-Jr. wrote:
Hi,
I have the follow function:
function() {
## Init of function
...
for(i in test) {
...
while(j = test2) {
...
}
}
}
The problem is that sometimes, naturally, the while is not possible to be
resolved, and so the program
Dear list,
I have data on insect survival in different cages; these have the
following structure:
deathtime status id cageS F G L S
1.5 1 1 C1 8 2 1 1 1
1.5 1 2 C1 8 2 1 1 1
11.5 1 3 C1 8
Hello,
I have some troubles when building S4-class packages.
All my (S4-)code works well (without building a package).
When building a package, in the R prompt after
checking S3 generic/method consistency
Following error occurs:
Fehler: Kann R Kode in Packet 'AddNoise' nicht laden (~Error: Can
On 11/17/05 8:05 AM, Vivien W. Chen [EMAIL PROTECTED] wrote:
Sean,
Thanks!
It works!
I have another extended question: how to label the two lines in the graph?
I tried many ways, including text, label, list, etc., just cannot give a
very effective way to do.
If I were you, I would play
On Thu, 2005-11-17 at 11:40 +0100, jobst landgrebe wrote:
Dear List,
can anyone tell me how to plot a discontinuous y-axis (ordinate
with a -/ /- break sign) to fit in data with a wide range without the
need of logarthimic transformation? My data are distributed like this:
(abscissa:
Tuszynski, Jaroslaw W. wrote:
Hi,
While installing precompiled packages I often get warnings like the one in
the subject. I usually ignore them, but I still do not understand why
windows packages are build with unreleased versions of R.
Is there some way to get packages build under
On Thu, 17 Nov 2005, Robin Hankin wrote:
Hi
In Sweave, how does one change the size of the plots?
Of the actual .eps or .pdf files or of the included figures in the paper?
The former can be done easily via
foo,fig=TRUE,height=4,width=8=
...
@
etc., the latter can be done most
The Sweave User Manual says (p. 12):
Attention: One thing that gets easily confused are the width/height
parameters of the R
graphics devices and the corresponding arguments to the LATEX
\includegraphics command.
The Sweave options width and height are passed to the R graphics
devices, and hence
From: Ales Ziberna
Firstly, these are all very basic questions, thah you coukld
probobly answer
yourself by searching the manual and help files.
Nevertheless, here are the
answers to give you a little head start.
Dear R expert,
The following is my questions:
1. How to generate
jobst landgrebe jlandgr1 at gwdg.de writes:
Dear List,
can anyone tell me how to plot a discontinuous y-axis (ordinate
with a -/ /- break sign) to fit in data with a wide range without the
need of logarthimic transformation? My data are distributed like this:
(abscissa: 1:10)
1.
Hi Robin,
After \begin{document} of your Rnw file, you can easily set e.g.
\setkeys{Gin}{width=width=0.8\textwidth}
And then doing something like;
test=
pdf(file = ...)
@
Best,
Matthias
Hi Matthias
thanks for this. I have the manual here.
Do you have a working example of \setkeys{Gin}
On 11/15/2005 12:22 PM, Michael Wolosin wrote:
All -
I am trying to write R code to implement a recursive algorithm. I've
solved the problem in a klunky way that works, but uses more memory and
computing time than it should.
A more elegant solution than my current one would require
Is there an R implementation of a scheme for automatic smoothing
parameter selection with loess, e.g., by minimizing one of the AIC/GCV
statistics discussed by Hurvich, Simonoff Tsai (1998)?
Below is a function that calculates the relevant values of AICC,
AICC1 and GCV--- I think, because I to
Hi Matthias,
On 17 Nov 2005, [EMAIL PROTECTED] wrote:
Hello,
I have some troubles when building S4-class packages.
All my (S4-)code works well (without building a package).
When building a package, in the R prompt after checking S3
generic/method consistency Following error occurs:
Version 2.0-2 of bayesm is available on CRAN.
This version includes bug fixes for rhierMnlRwMixture and
rhierLinearModel.
peter rossi
___
R-packages mailing list
[EMAIL PROTECTED]
https://stat.ethz.ch/mailman/listinfo/r-packages
On Thu, 17 Nov 2005, Michael Friendly wrote:
Is there an R implementation of a scheme for automatic smoothing
parameter selection with loess, e.g., by minimizing one of the AIC/GCV
statistics discussed by Hurvich, Simonoff Tsai (1998)?
If you particularly want loess smoothing then I don't
-Original Message-
From: Wassell, James T., Ph.D.
Sent: Thursday, November 17, 2005 9:40 AM
To: 'Deepayan Sarkar'
Subject: RE: nlme question
Deepayan,
Thanks for your interest. It's difficult in email but I need the
variance of Kappa = mu + 1.645*tau + 1.645* sigma
Just using the
On 11/17/2005 9:39 AM, Duncan Murdoch wrote:
On 11/15/2005 12:22 PM, Michael Wolosin wrote:
All -
I am trying to write R code to implement a recursive algorithm. I've
solved the problem in a klunky way that works, but uses more memory and
computing time than it should.
A more elegant
Dear all,
We are facing this problem for long, and so ask for your help.
We are plotting 2 graphs in a postscript device (left part -layout
function-), and the common legend for these graphs on the right part.
The legend in the postscript device looks ok: this is color lines with
numbers on the
James,
By assumption, sigma and tau are assumed uncorrelated, which I believe
Deepayan noted below. Sigma is also random error so it is uncorrelated
with your fixed effects. What are the covariance terms you are seeking?
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL
Hello,
I am importing the following file
;aa;bb;cc
1988;12;12;12
1989;78;78;12
1990;78;78;12
1991;78;78;12
1992;78;78;12
1993;78;78;12
1994;78;78;12
data-read.csv2(test.csv,header=T)
--
it gives
X aa bb
I have a feeling that Vasu wants (mistakenly) this:
dat - read.table(clipboard, header = FALSE)
dat
V1 V2 V3 V4
1 Name Weight Height Gender
2 Anne150 65 F
3Rob160 68 M
4 George180 65 M
5 Greg205 69 M
str(dat)
Dear Mike,
You could try
bestLoess - function(model, criterion=c(aicc, aicc1, gcv),
spans=c(.05, .95)){
criterion - match.arg(criterion)
f - function(span) {
mod - update(model, span=span)
loess.aic(mod)[[criterion]]
}
result - optimize(f, spans)
Hello R Help,
I have a question regarding Multinomial (Conditional) LOGIT models in R.
For my masters thesis I like to use Multinomial LOGIT models to analyse
consumer choice data.
After orientation on the R homepage and internet I found a method for
multinomial LOGIT. This model is as
Last Friday, I noticed that it is difficult to work with regression
models in which there are factors. It is easier to do the old fashioned
thing of coding up dummy variables with 0-1 values. The predict
function's newdata argument is not suited to insertion of hypothetical
values for the
I want to retrieve the column names(Weight, height, Gender) so that i can
use them as labels in plots further down.
According to your suggestion:
dat[[1]]
[1] 150 160 180 205
But i want to get the col name(weight) too. A user will upload any data file
and i shud be able to access the col names
Thank you for taking the time to think about my problem.
The reference states: The covariance structure must be considered,
because for unbalanced data the estimates (i.e. mu, sigma and tau hats)
are not typically independent. Page 105. It would be nice to simply
assume zero covariance terms,
marc, thanks!
You answered my question. Thanks for the explanation. I had replied for the
second time before i could recieve ur suggestion.
Andy, thanks to u too.
Vasu.
On 11/17/05, Marc Schwartz (via MN) [EMAIL PROTECTED] wrote:
I have a feeling that Vasu wants (mistakenly) this:
dat -
Paul Johnson [EMAIL PROTECTED] writes:
Last Friday, I noticed that it is difficult to work with regression
models in which there are factors. It is easier to do the old fashioned
thing of coding up dummy variables with 0-1 values. The predict
function's newdata argument is not suited to
Thanks very much, John
The formula for AICC1 was transscribed from an ambiguously
rendered version (in the SAS documentation). This is a
corrected version.
loess.aic - function (x) {
if (!(inherits(x,loess))) stop(Error: argument must be a loess
object)
# extract values from
On Thu, 2005-11-17 at 17:03 +0100, Florence Combes wrote:
Dear all,
We are facing this problem for long, and so ask for your help.
We are plotting 2 graphs in a postscript device (left part -layout
function-), and the common legend for these graphs on the right part.
The legend in the
Hi,
I just started using R a few weeks ago and have a problem with linking Fortran
subroutines to R. For some reasons, I need to compile a Fortran program in R
(or Splus) and the whole program consists a couple of subroutines, say, subA
and subB. There is no difficulty in linking the
Hi there,
I'm a newbie, plesae bear with me.
I have a dataset with about 1 ~ 3 data points. Would like fit to
both Gamma and Normal distribution to see which one fits better. How do I do
this in R? Or I could do a normality test of the data, if it's normal, I
then will do a normal fit,
The locfit package (which, I believe, contains an independent implementation
of loess, plus more) contains the gcvplot() and aicplot() functions that I
think can do this.
Best,
Andy
From: Michael Friendly
Thanks very much, John
The formula for AICC1 was transscribed from an ambiguously
Why not put the two subroutines into one file and compile them into one DLL?
Or compile them separately into .o, but make them into one DLL.
Andy
From: Li, Guang Q
Hi,
I just started using R a few weeks ago and have a problem
with linking Fortran subroutines to R. For some reasons,
This is an iceberg question -- most of it (i.e. statistical issues) is
hidden beneath the surface.
To avoid a lengthy dissertation on statistical philosophy, I would merely
suggest:
1.
require(lattice)
?qqmath
2. With that many points **any** test for a specific distributional form
will be
I think the authors are mistaken. Sigma is random error, and due to its
randomness it cannot be systematically related to anything. It is this
ind. assumption that allows for the likelihood to be expressed as
described in Pinhiero and Bates p.62.
If you are finding that sigma is systematically
On Thu, 2005-11-17 at 17:09 +0100, Matthieu Cornec wrote:
Hello,
I am importing the following file
;aa;bb;cc
1988;12;12;12
1989;78;78;12
1990;78;78;12
1991;78;78;12
1992;78;78;12
1993;78;78;12
1994;78;78;12
On 17 Nov 2005 18:00:45 +0100, Peter Dalgaard [EMAIL PROTECTED] wrote:
Paul Johnson [EMAIL PROTECTED] writes:
Last Friday, I noticed that it is difficult to work with regression
models in which there are factors. It is easier to do the old fashioned
thing of coding up dummy variables with
I would appreciate some help writing R code to plot predicted species
richness vs. observed species richness (nat_est) with 95% CI lines.
I'm using glm to get model coefficients and remove-one cross validation
to get predicted (cv.glm).
Here is what I have for the code so far:
SRCOUNT -
That's why we recommend that you do not use dev.copy but replot on the
target device.
Different devices have different fonts and font metrics, and so the plot
as laid out for one will almost always not be right for the other.
According to the help page for dev.copy you cannot by default copy
Hello,
I would like to transform a contingency table (A x B) into a data
frame while keeping the cross-tabulation structure (i.e. rows =
levels of A, columns = levels of B). I have tried as.data.frame,
xtabs, etc... and always got a flattened list of 3 variables (A, B,
Freq).
How to do that?
On 11/17/05, Doran, Harold [EMAIL PROTECTED] wrote:
I think the authors are mistaken. Sigma is random error, and due to its
randomness it cannot be systematically related to anything. It is this
ind. assumption that allows for the likelihood to be expressed as
described in Pinhiero and Bates
Charles Raux wrote:
Hello,
I would like to transform a contingency table (A x B) into a data
frame while keeping the cross-tabulation structure (i.e. rows =
levels of A, columns = levels of B). I have tried as.data.frame,
xtabs, etc... and always got a flattened list of 3 variables (A,
Hi,
I have a data set where times of sample collection are (for some unknown
reasons) stored as numerical values such as 727, 1134, etc., to represent
the times 7:27, 11:34, etc. How can I recover these times from the
numerical values? Also, can I obtain the elapsed time between two
Hi there,
I am trying to perform different normality tests in R. I have no problem
when I use Shapiro.test( ). However, when I try to use any normality
tests from the Nortest package, I kept getting this error Error in
read.table(source, header = T, fill = T) :
'file' must be a
My experiences parallel Dirk's - I also work for several financial
institutions and large corporates, and probably 80% of them allow me
to plug in a USB key and move files around.
Yep, I find it strange too...
Dave M.
On 11/18/05, Dirk Eddelbuettel [EMAIL PROTECTED] wrote:
On 17 November 2005
There are many ways to get this kind of message. With binary
outcomes, if complete separation is possible, nlminb (or optim) will
get tired trying to crank the slope up to Inf; in general, it suggests
the model is overparameterized in some way.
You say this is only a
Dear all,
I'd like to change a point pattern to a grid of cells and use one of the
variables as the output.
e.g. The point pattern is of a window of (500*500) and several features such
as pH, SoilType etc. I like to divide it into a grid with cell size 5*5, and
use the mean of the point
Is it safe to make any assumptions about how Makevars is used?
In particular, I want to include some conditional material, and wonder
if the GNU make conditional commands would work (at least for those
building with GNU make). Does Makevars get included in the Makefile?
Does it get treated as a
x.f - function(x) x %/% 100 + (x %% 100) / 60
x.f(c(727, 1134))
[1] 7.45000 11.56667
I assume for the elapsed time you can just subtract the numbers.
On 11/17/05, Ravi Varadhan [EMAIL PROTECTED] wrote:
Hi,
I have a data set where times of sample collection are (for some unknown
I am suddenly having a problem with my R installation (R 2.1.1) in that any
linear models that access variables that have a . in their name fail.
e.g.
tempdata-data.frame(dep=rnorm(1000),pred.test=rnorm(1000))
lm(dep~pred.test,data=tempdata)
Error in parse(file, n, text, prompt) : parse error
I had a similar problem when I posted this recently:
RODBC and Excel: Wrong Data Type Assumed on Import
http://tolstoy.newcastle.edu.au/~rking/R/help/05/11/14938.html
My conclusion was: Being lucky shouldn't be part of processing Excel
files, which is the case when RODBC is used.
This reply
Hi,
First off here is my system configuration:
Dual 2.3 Ghz PowerPC G5
Mac OS X 10.4.3
R for Mac OS X Aqua GUI 1.12 (installed in default location)
Mysql 5.0.13 located in: /usr/local/mysql-max-5.0.13-rc-osx10.4-powerpc/ and
default version in /usr/local/mysql
I downloaded
On 11/17/05, Christoph Scherber [EMAIL PROTECTED] wrote:
Dear list,
I have data on insect survival in different cages; these have the
following structure:
deathtime status id cageS F G L S
1.5 1 1 C1 8 2 1 1 1
1.5 1 2 C1
Hi! I'm new to R, and I have a question about how R works with large data sets
--- in particular, data sets that come from databases.
I'm using R 2.2.0 with the DBI package (0.1-9) and the RMySQL package (0.5-5).
My get-my-feet-wet-with-R project is to make a histogram from a data set stored
in
Hi,
I have a data.frame a like this:
a
v1 v2 v3 v4
1 1 1 A X
2 2 2 A X
3 3 3 A X
4 4 4 B X
5 5 5 B X
6 6 6 C Y
7 7 7 C Y
8 8 8 C Y
9 9 9 D Y
10 10 10 D Y
I want to get a weighted average for each combination of v3 and v4,
using v1 as values and
[R] Histogram over a Large Data Set (DB): How?
Have you tried just grabbing the whole column using dbGetQuery? Try doing
this:
spams - dbGetQuery(con,select unixtime from email limit 100)
Then increase from 1,000,000 to 1.5 million, to 2 million, etc. until you
break something (run out
On 11/17/2005 6:25 PM, Weiwei Shi wrote:
Hi,
I have a data.frame a like this:
a
v1 v2 v3 v4
1 1 1 A X
2 2 2 A X
3 3 3 A X
4 4 4 B X
5 5 5 B X
6 6 6 C Y
7 7 7 C Y
8 8 8 C Y
9 9 9 D Y
10 10 10 D Y
I want to get a weighted average
Have you considered using corARMA with, e.g., lme in library(nlme),
as described in Pinheiro and Bates (2000) Mixed-Effects Models in S and
S-PLUS (Springer, esp. table 5.3)?
hope this helps.
spencer graves
p.s. You might get quicker and more useful replies if you
Both your questions seem too vague to me. You might get more useful
replies if you provide a simple example in a few lines of R code that a
reader could copy from your email into R and see the result (as
suggested in the posting guide! www.R-project.org/posting-guide.html).
The
axis.break() in the plotrix package will do that. You still have to modify
the axis scale.
Cheers
Francisco
From: jobst landgrebe [EMAIL PROTECTED]
To: r-help@stat.math.ethz.ch
Subject: [R] discontinuous y-axis (ordinate with a -/ /-)
Date: Thu, 17 Nov 2005 11:40:01 +0100
Dear List,
On 11/17/05, Weiwei Shi [EMAIL PROTECTED] wrote:
Hi,
I have a data.frame a like this:
a
v1 v2 v3 v4
1 1 1 A X
2 2 2 A X
3 3 3 A X
4 4 4 B X
5 5 5 B X
6 6 6 C Y
7 7 7 C Y
8 8 8 C Y
9 9 9 D Y
10 10 10 D Y
I want to get a weighted
I use ess 5.101 in GNU emacs on windows 2000 x86 system.
The problem is like bellows:
1. When I execute R-2.2.0 by stand-alone mode, help files opens very
fast.
2. When I execute Rterm in GNU emacs, however, help files hangs to
open. It makes me inconvenient.
How can I
I need to fit a number of models with different number of predictors
in each model. Say for example, I have three predictors: x1, x2, x3
and I want to fit three models:
lm(y~x1+x2)
lm(y~x2+x3)
lm(y~x1+x2+x3)
Instead of typing all models, what I want is to create a
Try this:
x - data.frame(x1 = x1, x2 = x2, x3 = x3)
lm(y ~., x[,1:2])
lm(y ~., x[,2:3])
lm(y ~., x[,1:3])
On 11/18/05, Juni Joshi [EMAIL PROTECTED] wrote:
I need to fit a number of models with different number of predictors
in each model. Say for example, I have three predictors:
Dear R-list
I have been trying to make survreg fit a normal regression model with left
truncated data, but unfortunately I am not able to figure out how to do it.
The following survreg-call seems to work just fine when the observations are
right censored:
library(survival)
n-10
#censored
On 11/17/05, Gabor Grothendieck [EMAIL PROTECTED] wrote:
On 17 Nov 2005 18:00:45 +0100, Peter Dalgaard [EMAIL PROTECTED] wrote:
Paul Johnson [EMAIL PROTECTED] writes:
Last Friday, I noticed that it is difficult to work with regression
models in which there are factors. It is easier to
I have three files of data which are available at http://zhangw.com/
R/, varied at the number of data. I tried to use R to analyze using
shapiro.test, ks.test, and t.test. t.test ran as expected, however,
when I run shapiro.test and ks.test commands, error message always
occurred. Error
Hi,R-list!
I am a newbie to the R and what I want to know mostly now is as follow:
Using rnorm(),we could get the random numbers with normal distribution,
but how to generate the random numbers with the lognormal distribution?
Thank you in advance!
[EMAIL PROTECTED]
2005-11-18
Hi David,
you could see my contribute:
Fitting distributions with R
http://cran.r-project.org/doc/contrib/Ricci-distributions-en.pdf
Hoping it could be helpful.
Regards,
Vito
You wrote:
Hi there,
I'm a newbie, plesae bear with me.
I have a dataset with about 1 ~ 3 data points.
广星 wrote:
Hi,R-list!
I am a newbie to the R and what I want to know mostly now is as follow:
Using rnorm(),we could get the random numbers with normal distribution,
but how to generate the random numbers with the lognormal distribution?
What about searching in the help files?
It's not that
85 matches
Mail list logo