If you have gcc installed, yes, still a path issue:
You have tp put MinGW's ./bin directory into your PATH.
Best,
uwe
Pete Cap wrote:
*/Uwe Ligges [EMAIL PROTECTED]/* wrote:
Please follow the Instructions to set up your build environment as
mentioned in the R Installation and
On Mon, 12 Mar 2007, Sender wrote:
Any insight as to why this is printing twice?
Try:
m - NA
class(m) - mydist
m[]
res - m[]
res
(hint - print.default() is returning what it was asked to print, which
then gets printed again automatically)
[.mydist - function(x,...){
print(I called
On Tue Mar 13 00:21:22 CET 2007 Gavin Simpson wrote:
On Mon, 2007-03-12 at 16:02 -0700, Sender wrote:
Thanks for the suggestion Christian. I'm trying to avoid expanding the dist
object to a matrix, since i'm usually working with microarray data which
produces a distance matrix of size 5000
I am using R2.4.1 and using Rattle()
Rattle() -- Explore-- GGobi
I need to save the Scatter plot matrix in any type of image format.
But it save as *.xml file how can i reterive the *.xml into *.bmp or *.png?
I have tried the Export button in Rattle() not much options.
Need the group help
JJ
jun,
im am also quite new to R. so i think, this is a question all we R-newbees
ask ;-). having had the same problem the other day, i solved it the
following way:
Multiple Regressions - Tables
data(anscombe) # load anscombe
dataset (implemented
Hi,
I tried to use S-plus script with R. I thought it was easy because there
aren't a lot differences between S-plus and R syntaxe. However, I didn't
succeed to use stepwise function in R. I think the best equivalent in R
is step, but this function seems not to use same parameters.
is there a
Hi
Kindly correct me if I am posting a wrong query in the forum.
I am trying to handle my button:clicked event. But not able to proceed
further. Please help.
Following is my code:
library(RGtk2)
win - gtkWindowNew(type = NULL, show = TRUE)
butt - gtkButtonNewWithLabel(Submit, show = TRUE)
If PDF is OK, you can use the 'alpha' argument in colors, i.e.:
pdf( file.pdf)
p - seq(0.2,1.4,0.01)
x1 - dnorm(p, 0.70, 0.12)
x2 - dnorm(p, 0.90, 0.12)
plot(range(p), range(x1,x2), type=n)
polygon(p, x1, col = rgb(1,0,0, .5),lwd=4, lty=2)
polygon(p, x2, col = rgb(0,0,1, .5),lwd=4)
dev.off()
Hi,
Is there any method in R by which I can solve PDEs?
Thank you,
Amit
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
On 8/3/07 22:12, Gad Abraham [EMAIL PROTECTED] wrote:
Laura Hill wrote:
On 7/3/07 00:15, Gad Abraham [EMAIL PROTECTED] wrote:
On 6 Mar 2007, at 08:54, Laura Hill wrote:
Hi,
My name is Laura. I'm a PhD student at Queen's University Belfast
and have
just started learning R. I
On 8/3/07 22:12, Gad Abraham [EMAIL PROTECTED] wrote:
Laura Hill wrote:
On 7/3/07 00:15, Gad Abraham [EMAIL PROTECTED] wrote:
On 6 Mar 2007, at 08:54, Laura Hill wrote:
Hi,
My name is Laura. I'm a PhD student at Queen's University Belfast
and have
just started learning R. I
Amit,
A better tool for this purpose may be octave, which can be found at
http://www.gnu.org/software/octave/
Regards,
Tom
Amit Soni wrote:
Hi,
Is there any method in R by which I can solve PDEs?
Thank you,
Amit
[[alternative HTML version deleted]]
Try EBImage from Bioconductor.org
Best,
Oleg
Milton Cezar Ribeiro wrote:
Hi R-gurus
How can I read my bmp files into R?
Kind regards,
miltinho
Brazil
__
[[alternative HTML version deleted]]
R-Experts:
Does anyone know if there are R functions to perform the Freeman-Tukey
double arcsine transformation and then backtransform it?
Thanks,
Brant Inman
Mayo Clinic
__
R-help@stat.math.ethz.ch mailing list
Den Ti, 2007-03-13, 09:40 skrev j.joshua thomas:
I am using R2.4.1 and using Rattle()
Rattle() -- Explore-- GGobi
I need to save the Scatter plot matrix in any type of image format.
Have you tried the `DescribeDisplay' package?
Take a look at http://www.ggobi.org/describe-display/ for a
# I use this code to label a graph with the R2:
# graph
x - rnorm(100)
y - x + rnorm(100)
lm1 - lm(y~x)
plot(x,y)
# label
R2text - substitute(paste(R^2, = ,r2),list(r2=r2))
text(1,-3,R2text, col=red)
# i have modified this a bit, so that i have a vector with other labels,
each of which
# will
hi,
your first argument to substitute should be an expression, not a character
string (which the output of paste() will give you)
so...
# first assign to variable r2 (think you forgot to do that)
# in your example
r2 - summary(lm1)$r.squared
# then to your label
R2text -
Uwe Ligges [EMAIL PROTECTED] wrote: If you have gcc installed, yes, still a
path issue:
You have tp put MinGW's ./bin directory into your PATH.
Best,
uwe
Uwe,
Got it. I had placed ..\mingw\mingw32\bin in the path instead. I also had to
place the directory for the HTML Help Workshop in the
Dear Renko
To modify the script
plot(x,y)
r2-summary(lm1)$r.squared*100
# label
R2text - substitute(paste(R^2, = ,r2),list(r2=r2))
text(-1,1,R2text, col=red) # To see of the coordinates of the graph.
Grettings
Felipe
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED]
Le Mardi 13 Mars 2007 00:28, Sender a écrit :
Hello:
Could anyone point me to a nice example where someone has created methods
for [ on a user defined Class?
I looked at the package Matrix but that was a little daunting. I'm looking
for someone a little more introductory. I've tried to
I do not understand why you play with 'substitute' instead of something
like this:
# CAUTION: this will work only for bivariate case
# plotmaking function
plotModel - function(m)
{
x - m$model$x
y - m$model$y
r2 - summary(m)$r.squared
plot(x,y)
abline(m)
Hi R-users,
I would like to plot the effects of one of the predictor variables on
the response variable in the GLMM I ran with the lme4 package. Usually
when doing a multivariate analysis I would obtain the residuals of the
model without the predictor variable of interest (x1) and then plot
I believe the short answer to your question lies in
summary(ans.reg[[i]])$coefficients
which will give you a matrix with coefficients and standard errors (and
more). You can also find out what other information you can get from the
regressions if you type
attributes(ans.reg[[i]])
Despite a long search on the archives, I couldn't find how to do this.
Thanks in advance for what is likely a simple issue.
I have a data set where the first column is name (i.e., 'Joe Smith',
'Jane Doe', etc). The following columns are data associated with that
person. I have many people with
Dear all,
I am trying to model variation of distribution of species assemblages
according to environmental variables. For that I use a log linear
multinomial regression.
In order to select variables that mostly discriminate the assemblages, I
tried to apply a hierarchical partitioning protocol
Hi,
I am trying to estimate an ARIMA model in the case where I have some
specific knowledge about the coefficients that should be included in the
model. Take a classical ARIMA (or even ARMA) model:
P(B) X(t) = Q(B) epsilon(t),
where X(t) is the data, epsilon is a white noise, B is the
Sarthi,
See help(gSignalConnect) for instructions on how to connect to GObject
signals.
For this particular case, try gSignalConnect(butt, clicked, function(wid)
print(clicked!)).
See the demos included in the RGtk2 paper for numerous examples of using
gSignalConnect().
Michael
On 3/13/07,
I'm sorry for my first post as I did not properly understood your
problem.
The reason why you were getting paste(R^2, = , 48.7) instead of the
properly formatted R^2=48.7
is that in creating 'texts' in your code you were mixing character
string with expressions resulting in 'texts' being a list
Thomas Adams wrote:
Amit,
A better tool for this purpose may be octave, which can be found at
http://www.gnu.org/software/octave/
Parabolic PDEs handled by the method of lines are effectively systems of
ODEs and can be solved by (tada!) ODEsolve.
-p
Regards,
Tom
Amit Soni wrote:
are the carats in your notation meant to be time subscripts ?
also, I think I know what a and b are meant to be ( the coefficients of
the polynomaisl corresponding
To the ar part of the model but correct me if I'm wrong ) but is there
an ma piece to it also ?
And I don't see an error term ?
I
i tried with package DescribeDisplay
dd_load(DescribeDisplay)
Load describe display
i couldnt find any documentation. could you give me a sample
help
On 3/13/07, Henric Nilsson (Public) [EMAIL PROTECTED] wrote:
Den Ti, 2007-03-13, 09:40 skrev j.joshua thomas:
I am
Inman, Brant A. M.D. wrote:
R-Experts:
Does anyone know if there are R functions to perform the Freeman-Tukey
double arcsine transformation and then backtransform it?
Well, if not, both are given by explicit formulas, so it shouldn't take
long to implement, cf.:
The Teacher's Corner
This isn't pretty, but should work:
x - 10 # number of occurrences
y - split(all.data,f=all.data$names)
z - y[unlist(lapply(y,nrow))x]
newdata - vector()
for( k in z ) {
newdata - rbind(newdata,k)
}
Basically I split your data frame into groups by name (into a list), then
selected elements in
Hello,
I am looking for an R function that impliments Duncan's post-hoc test. I am
aware of multcomp and its function glht but, unless I am missing
something, this cannot impliment the Duncan test.
Any help of pointers are welcome.
Bill Shipley
__
try this:
set.seed(123)
all.data - data.frame(name = sample(c(Joe, Elen, Jane, Mike),
8, TRUE),
x = rnorm(8), y = runif(8))
##
tab.nams - table(all.data$name)
nams - names(tab.nams[tab.nams = 2])
all.data[all.data$name %in% nams, ]
I hope it helps.
Best,
Dimitris
Dimitris
On Tue, 2007-03-13 at 10:38 -0400, Mike Jasper wrote:
Despite a long search on the archives, I couldn't find how to do this.
Thanks in advance for what is likely a simple issue.
I have a data set where the first column is name (i.e., 'Joe Smith',
'Jane Doe', etc). The following columns are
Mike Jasper wrote:
Despite a long search on the archives, I couldn't find how to do this.
Thanks in advance for what is likely a simple issue.
I have a data set where the first column is name (i.e., 'Joe Smith',
'Jane Doe', etc). The following columns are data associated with that
person. I
On Tue, 2007-03-13 at 10:32 -0500, Marc Schwartz wrote:
On Tue, 2007-03-13 at 10:38 -0400, Mike Jasper wrote:
Despite a long search on the archives, I couldn't find how to do this.
Thanks in advance for what is likely a simple issue.
I have a data set where the first column is name
Sorry if the notation is unclear. You got it right:
P(x) = (1 - a_1*x - a_2*x^2) * (1 - b_1*x^23 - b_2*x^24) * (1 - c_1*x^168).
The a_i's, b_i's and c_i's are the coefs of the polynom P.
And there is also an MA part, which is Q(B) epsilon(t). Here epsilon(t) is
the error process, and Q is
Dear R Help,
I have noticed some inconsistent behaviour of add1 and drop1 with a
weighted linear model, which affects the interpretation of the results.
I have these data to fit with a linear model, I want to weight them by
the relative size of the geographical areas they represent.
Hi,
I have recently installed version 2.4.1 of R and also installed
SciViews-R 0.8.9. It worked fine. Then I installed the Rcmdr 1.2-7 from
CRAN . However the 'R commander menu' in the dockable panel does not
work. If I start Rcmdr in R without SciViews, it works perfectly.
Is there any way that
Jenny Hodgson wrote:
Dear R Help,
I have noticed some inconsistent behaviour of add1 and drop1 with a
weighted linear model, which affects the interpretation of the results.
I have these data to fit with a linear model, I want to weight them by
the relative size of the geographical areas
d. sarthi maheshwari samay.sar at gmail.com writes:
Hi
Kindly correct me if I am posting a wrong query in the forum.
I am trying to handle my button:clicked event. But not able to proceed
further. Please help.
Following is my code:
library(RGtk2)
win - gtkWindowNew(type = NULL,
Great. Thanks again for all the suggestions.
On 3/13/07, Vincent Goulet [EMAIL PROTECTED] wrote:
Le Mardi 13 Mars 2007 00:28, Sender a écrit:
Hello:
Could anyone point me to a nice example where someone has created
methods
for [ on a user defined Class?
I looked at the package
Stephen, Norbert, Anup, and Mark, Thank you all for your help. With these
tips, I now have a much better understanding of the structure in R. Another
related question that has been haunting me is whether it is necessary to be
a convert from other statistical packages to R. Obviously, the great
Hmmm, this is the same I got
add1(model,.~.+x1+x2)
Single term additions
Model:
y ~ 1
Df Sum of SqRSSAIC
none 74.541 24.703
x1 144.377 30.164 14.942
x2 136.619 37.922 17.918
R version 2.4.1 (2006-12-18)
i386-pc-mingw32
locale:
On 3/13/07, j.joshua thomas [EMAIL PROTECTED] wrote:
i tried with package DescribeDisplay
dd_load(DescribeDisplay)
Load describe display
i couldnt find any documentation. could you give me a sample
I've just improved http://www.ggobi.org/describe-display/, and
Hi. I've installed the fSeries package, trying to do Arfima fitting.
Instructions in fSeries.pdf ask to use ArfimaOxFit.ox and
ArfimaOxPredict.ox files, which i'm unable to find (the suggested path
described in fSeries.pdf does not contains the files). Does any one can
share those files with me,
I was using Version 2.3.1 for Windows (binary download version). Guess I
should be using the latest version, (but the reason is I'm writing up my
PhD and I thought my results would be more 'repeatable' if I didn't keep
changing my version of the software, I didn't really think there would
be any
The R timeDate class is in the fCalendar package.
Does anyone know how to change the output format of a timeDate object?
(Other than by explicitly supplying a format= argument to the format()
function.) I tried creating a timeDate object, and then changing the
format slot. However, all the
There are two articles describing time and date classes in the R-News
letter:
Brian D. Ripley and Kurt Hornik. Date-time classes. R News, 1(2):8-11,
June 2001.
http://cran.r-project.org/doc/Rnews/Rnews_2001-2.pdf
Gabor Grothendieck and Thomas Petzoldt. R help desk: Date and time
classes in R.
Dear Kihwang,
I believe that you'll have to use an older version of the Rcmdr package with
SciViews; you can download version 1.1-2 of the Rcmdr from the SciViews web
page http://www.sciviews.org/SciViews-R/. For more information, you might
contact the SciViews developers.
I hope this helps,
Hello:
Does anyone know if there exists a package that handles methods for [
for
dist objects?
I would like to access a dist object using matrix notation
e.g.
dMat = dist(x)
dMat[i,j]
You can use the [[ operator defined for distance matrices currently
I'm curious what this transformation does, but I am not curious enough to pay
$14 to find out. Someone once told me that the arcsine was a good way to
transform data and make it more 'normal'. I am wondering if this is an
improved method. Anyone know of a free reference?
-Original
I have searched the archives for using insert into to update spreadsheets
using RODBC and have come up short. So, first off, is it possible?
I have put together a dummy xls table (c:\foo.xls)for exploring
possibilities of RODBC. Ultimately, I am interested in replacing much of
our previous
On Tue, 13 Mar 2007 14:15:16 -0400,
Bos, Roger [EMAIL PROTECTED] wrote:
I'm curious what this transformation does, but I am not curious enough
to pay $14 to find out. Someone once told me that the arcsine was a
good way to transform data and make it more 'normal'. I am wondering if
this is
Jenny Hodgson wrote:
I was using Version 2.3.1 for Windows (binary download version). Guess I
should be using the latest version, (but the reason is I'm writing up my
PhD and I thought my results would be more 'repeatable' if I didn't keep
changing my version of the software, I didn't really
Hi Toby,
[EMAIL PROTECTED] wrote:
I have searched the archives for using insert into to update spreadsheets
using RODBC and have come up short. So, first off, is it possible?
I don't think so. Writing to an Excel spreadsheet is probably easier
done using the RDCOMClient package. There are
As a further footnote on this, I can't resist mentioning a letter
that appears
in Technometrics (1977) by Steve Portnoy who notes that
2 arcsin(sqrt(p)) = arcsin(2p - 1) + pi/2
and asks: it would be of historical interest to know if any early
statisticians
were aware of this, and if
The Southern California Chapter of the American Statistical Association
invites you to attend the 26th annual Applied Statistics Workshop on
Saturday March 31, 2007 at the University of California Los Angeles. The
topic is Advances in Latent Variable Modeling presented by Professor
Bengt
On 3/13/07, Peter Dalgaard [EMAIL PROTECTED] wrote:
Jenny Hodgson wrote:
I was using Version 2.3.1 for Windows (binary download version). Guess I
should be using the latest version, (but the reason is I'm writing up my
PhD and I thought my results would be more 'repeatable' if I didn't keep
Bos, Roger wrote:
I'm curious what this transformation does, but I am not curious enough to pay
$14 to find out. Someone once told me that the arcsine was a good way to
transform data and make it more 'normal'. I am wondering if this is an
improved method. Anyone know of a free
I'm trying to create a barplot that has two sets of data next to each
other. I'm using barplot with the add=TRUE option, but this simply
adds the second dataset on top of the first, obscuring it. How do I
add the new data to the right on the existing barplot so that both
sets are
I do recall seeing posts on RDOM flying around from time to time and today
have stumbled across as well through my RODBC searches. I have also been
reminded from another reply of RCOM being a potential solution. I had
hoped to stick to more of a pure sql based process, but certainly R makes
Tried. Did not work. Thanks anyway. I will contact the SciViews
developers as you suggested.
Kihwang
John Fox wrote:
Dear Kihwang,
I believe that you'll have to use an older version of the Rcmdr package with
SciViews; you can download version 1.1-2 of the Rcmdr from the SciViews web
page
Hi out there,
I am trying to fit a species accumulation curve (increase in number of
species known vs. sampling effort) for multiple regions and several
bootstrap samples. The bootstrap samples represent different
arrangements of the actual sample sequence.
I fitted a series of nlme-models and
Add/subtract a small constant to/from your latter dataset (x-values) and
plot it without axes.
Petr
Jason Horn napsal(a):
I'm trying to create a barplot that has two sets of data next to each
other. I'm using barplot with the add=TRUE option, but this simply
adds the second dataset on
Received Wed 14 Mar 2007 1:53am +1100 from j.joshua thomas:
i tried with package DescribeDisplay
dd_load(DescribeDisplay)
Load describe display
i couldnt find any documentation. could you give me a sample
Try
install.packages(DescribeDisplay)
On Mar 13, 2007, at 3:34 PM, Jason Horn wrote:
I'm trying to create a barplot that has two sets of data next to each
other. I'm using barplot with the add=TRUE option, but this simply
adds the second dataset on top of the first, obscuring it. How do I
add the new data to the right on the
I am running a recursive feature selection wrapper on svm for a large
data set. The routine gets progressively slower. I am deleting the
objects not required. Is there anything else you advise me look for?
I tried running it from the command line but it does not print anything
on the screen. I
I'm trying to use nonlinear regression to estimate model parameters
for a constant rate birth-death process conditioned on the fact that
the population has not gone extinct. Because the birth and death
parameters obtained from standard application of gnls() appear to be
biased, I'd like
Thanks to all of you who got me the answer. The key I was missing was
%in%. Had never seen it before.
best.
On 3/13/07, Dimitris Rizopoulos [EMAIL PROTECTED] wrote:
try this:
set.seed(123)
all.data - data.frame(name = sample(c(Joe, Elen, Jane, Mike),
8, TRUE),
x = rnorm(8), y =
Peter Dalgaard wrote:
Bos, Roger wrote:
I'm curious what this transformation does, but I am not curious enough to
pay $14 to find out. Someone once told me that the arcsine was a good way
to transform data and make it more 'normal'. I am wondering if this is an
improved method.
The point of the given transformation is not so much for normality as it
is for variance stabilization. The variance of the Freeman-Tukey
transform depends only on the denominator of the proportion in
question...something that can be used to advantage.
Brant
-Original Message-
From:
On 3/13/2007 3:14 PM, hadley wickham wrote:
On 3/13/07, Peter Dalgaard [EMAIL PROTECTED] wrote:
Jenny Hodgson wrote:
I was using Version 2.3.1 for Windows (binary download version). Guess I
should be using the latest version, (but the reason is I'm writing up my
PhD and I thought my results
On Tue, 2007-03-13 at 15:34 -0400, Jason Horn wrote:
I'm trying to create a barplot that has two sets of data next to each
other. I'm using barplot with the add=TRUE option, but this simply
adds the second dataset on top of the first, obscuring it. How do I
add the new data to the
Another way:
require(sp)
require(rgdal)
library(rgdal)
## read using one of the many GDAL drivers
d - readGDAL(im.bmp)
summary(d)
## map colours for RGB and display
col - SGDF2PCT(d)
d$idx - col$idx
image(d, idx, col = col$ct)
## Available drivers:
gdalDrivers()
Milton Cezar Ribeiro wrote:
Dear R users
I am trying to obtain p-values for (quasi)poisson lmer models, using
Markov-chain Monte Carlo sampling and the command summary.
My problems is that p values derived from both these methods are
totally different. My question is
(1) there a bug in my code and
(2) How can I
Thanks for the tip about the empty vector, I ever knew you could do that. I
just have one problem,
Lets say Q is a 2x2 matrix
p is a 1x2 matrix
q is a 2x1 matrix
y is vector of times, say y = c(5, 10)
How do I multiply Q by each time y[i]?
I would like to
Hi,
Consider the following (much simplified) Sweave example:
--
First, we set the value of $x$:
chunk1,eval=FALSE=
x - 1
@
Then we set the value of $y$:
chunk2,eval=FALSE=
y - 2
@
Thus, the overall algorithm has this structure:
combined,eval=FALSE=
chunk1
chunk2
@
Hi there,
I am using gls from the nlme library to fit an AR(1) regression model.
I am wondering if (and how) I can separate the auto-correlated and random
components of the residuals? Id like to be able to plot the fitted values +
the autocorrelated error (i.e. phi * resid(t-1)), to compare
Hi,
I would like to know how to perform a Poisson rate test in R, both to one
sample and two sample. I have looked for it in CRAN homepage, but i couldn´t
find it. Thanks,
Luis Ernesto.
__
[[alternative HTML version deleted]]
Your output is probably buffered. Uncheck the buffered output flag on the
Misc tab ( I am assuming that your are running under Windows, but you did
not say). Are you paging because you have used up all your available
physical memory? This would cause things to slow down. Use the performance
On 3/13/07, Duncan Murdoch [EMAIL PROTECTED] wrote:
On 3/13/2007 3:14 PM, hadley wickham wrote:
On 3/13/07, Peter Dalgaard [EMAIL PROTECTED] wrote:
Jenny Hodgson wrote:
I was using Version 2.3.1 for Windows (binary download version). Guess I
should be using the latest version, (but the
Kevin R. Coombes [EMAIL PROTECTED] writes:
Hi,
Consider the following (much simplified) Sweave example:
--
First, we set the value of $x$:
chunk1,eval=FALSE=
x - 1
@
Then we set the value of $y$:
chunk2,eval=FALSE=
y - 2
@
Thus, the overall algorithm has this
Kate Stark wrote:
Hi there,
I am using gls from the nlme library to fit an AR(1) regression model.
I am wondering if (and how) I can separate the auto-correlated and random
components of the residuals? Id like to be able to plot the fitted values +
the autocorrelated error (i.e. phi *
On 3/13/2007 7:46 PM, hadley wickham wrote:
On 3/13/07, Duncan Murdoch [EMAIL PROTECTED] wrote:
On 3/13/2007 3:14 PM, hadley wickham wrote:
On 3/13/07, Peter Dalgaard [EMAIL PROTECTED] wrote:
Jenny Hodgson wrote:
I was using Version 2.3.1 for Windows (binary download version). Guess I
should
[1] In the example I presented, you're right; I can just use a verbatim
environment. In the following more complicated example
combined,eval=FALSE
if (some.condition) {
chunk1
} else {
chunk2
}
@
I would still want to be able to see the outline of what is going on,
and a verbatim environment
G'day Kevin,
On Tue, 13 Mar 2007 20:18:11 -0500
Kevin R. Coombes [EMAIL PROTECTED] wrote:
[1] In the example I presented, you're right; I can just use a
verbatim environment. In the following more complicated example [...]
I would still want to be able to see the outline of what is going on,
___
Hello,
Normally when you call model.matrix, you get a matrix that has
aliased/redundant columns deleted. For example:
m - expand.grid(a=factor(1:3), b=factor(1:3))
model.matrix(~a + b, m)
(Intercept)
On Wed, 2007-03-14 at 14:57 +1100, Hong Ooi wrote:
Hello,
Normally when you call model.matrix, you get a matrix that has
aliased/redundant columns deleted. For example:
m - expand.grid(a=factor(1:3), b=factor(1:3))
model.matrix(~a + b, m)
(Intercept) a2 a3 b2 b3
1 1 0 0
Dear All,
I've a 10 by 5 data frame like this
set.seed(1001)
a - rnorm(10)
b - rnorm(10)
c - rnorm(10)
d - rnorm(10)
e - rnorm(10)
A - cbind(a,b,c,d,e)
Each row is one datum. I want to resample within A[,5]. Fit the regression
lines lm(A[,5] ~ A[,1] + A[,2]) and lm(A[,5] ~ A[,3] + A[,4]) to
Hi,
I have two matrix of high dimension representing data for two classes. The
matrix are of 1500 columns, each column represent one feature.
Is it possible to extract the discriminating feature and non-discriminating
feature by applying lda from MASS library. Or is there any other library
I cannot seem to get the aic or extractaic call to work with multinomial
logistic regression models.
Here is what I am doing:
library('Design')
lrm1-lrm(r1~p1)
#where p1 is multinomial and r1 is binomial
library('MASS')
aic(lrm1)
Error in if (fam %in% c(gaussian, Gamma, inverse.gaussian)) p - p
94 matches
Mail list logo