;
>
> returns for the mode of size logical. But in the documentation is said
> that size should be integer. Does anyone know why the mode is logical?
>
Because NA is a logical constant.
-thomas
__
R-help@stat.math.ethz.ch mai
a design stratified by stratum and post-stratified by sex,
which is not the same as stratifying by stratum*sex or post-stratifying by
stratum*sex.
In this case you should probably rake() on stratum and sex rather than
just post-stratifying. Post-stratifying on sex is equivalent to one iterat
The error message about the feasible region comes from constrOptim(),
before your function is called. The error message about missing lambda1
comes from calling your function.
-thomas
On Sun, 9 Sep 2007, Yuchen Luo wrote:
> Dear Friends.
> I found something very puzzlin
;
> The following should work (untested):
>
> design <- svydesign(ids=~0, strata=~regiune + size_loc, data=tabel)
This would be a two-stage sample, you actually need ~interaction(regiune,
size_loc).
[this reply is just to make sure it ends up linked in the archives].
-thomas
__
el)
Second, you have not specified either weights or population sizes, so R
has no way to work out the sampling weights. That's why you get weights of
1. You should also get a warning.
-thomas
__
R-help@stat.math.ethz.ch mailing list
ages via Rserve than:
>>
>> Rconnection c=new Rconnection("127.0.0.1");
>> REXP xp=c.eval("try(png(\"test.png\"))")
>> c.voidEval("plot(1:10)");
>> c.voidEval("dev.off()");
>> is = c.openFile("test.png");
Julian Burgos wrote:
> mode()... of course!
Wrong. See ?mode
"Get or set the type or storage mode of an object."
Thomas P.
> Raymond Balise wrote:
>> What is the name of the function to give me the mode (central tendancy) of a
>> numeric variable that can be negati
elp/04/02/1409.html
Thomas P.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
where you can change the
confidence limits for the sample mean and have the data change in
response.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
R-hel
quot;foo", x= 1)
>
> bar(f)
>
> # bar(f) gives 0, not 1.
>
Because bar() isn't a generic function
> bar
function(object)
{
return(0)
}
If you had used setGeneric() before setMethod(), as recommended, your example
would have done what you expec
> typeof(m)
> [1] "integer"
>> class(m)
> [1] "integer"
>
> ...it seems to me like max() and summary(m)[6] ought to return the same
> number. Am I doing something wrong?
>
They do return the same number, they just print it differently. summary()
print
nd a search of r-help reveals two previous, different, suggestions for
%:%.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
R-help@stat.math.ethz.ch mailing list
https://stat
There could still be functions that divert a copy of all the output to a
file, for example. And indeed there are.
sink("transcript.txt", split=TRUE)
-thomas
On Fri, 24 Aug 2007, Muenchen, Robert A (Bob) wrote:
> I looked long and hard for that information. Thank you VE
Directories
Archive
Previous versions of the packages listed above.
-
linking to
[CRAN]/src/contrib/Archive
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the p
On Wed, 22 Aug 2007, Alan Harrison wrote:
> Hey folks,
>
> I'm trying to do all subsets on a zero-inflated poisson regression.
> I'm aware of the leaps and regsubsets functions but I don't know if they
> work for ZIP regressions or how the syntax fits in for them.
al maximum) for any likelihood.
The special case you may be thinking of is that in some problems the
E-step is equivalent to computing E[missing data | observed data] rather
than the more general E[loglikelihood|observed data]
-thomas
Thomas Lumley Assoc. Professor
WS file. The question of whether it is dangerous is
really an internal risk management issue for you.
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
sion on the data but
> I am not clear about if or better how I can use the
> weights in it. From the description of the weights
> argument of glm it seems to me that I cannot plug
> these weights in there.
>
You want svyglm() in the survey package.
-thomas
Thomas Lu
# here's your example correlation matrix:
sigma<- matrix(c(1.00, 0.75, 0,
0.75, 1.00, 0,
0.00, 0.00, 0), nr=3, byrow=TRUE)
chol(sigma)
# Error in chol(sigma) : the leading minor of order 3 is not positive definite
# DUH!
# let's chop off that dangling row and col
bles, you
can fit a model with all variables and then apply regsubsets() to the weighted
linear model arising from the IWLS algorithm. This will give an approximate
ranking of models that you can then refit exactly. This is useful if you wanted
to summarize the best few thousand models on 30 v
ssumes equal
variances (the original one), so you need var.equal=TRUE.
-thomas
> -Original Message-
> From: Moshe Olshansky [mailto:[EMAIL PROTECTED]
> Sent: Tuesday, August 07, 2007 9:05 PM
> To: Nair, Murlidharan T; r-help@stat.math.ethz.ch
> Subject: Re: [R] sma
of the mixture components drift
around over time. The location, scale, and mass of the four mixture
components really were the best summaries. This was the application that
constrOptim() was written for.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTE
p (put.var.ncdf) doesn't work, because
it says I am trying to "error: you asked to write 111788329 values, but the
passed data array only has 10573 entries!". So I think the problem is I need
an array with two dimensions (coordinates...) for my values. But do I get
this from my tables??
sumably correct if you have your model correctly specified.
To paraphrase the Hitchikers' Guide: This must be some definition of the word
'robust' that I was not previously aware of. :)
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMA
005 and verison 3.6-11 was recently posted. It provides fairly
comprehensive facilities for analysis of complex survey designs. Major
additions since 2.9 are calibration estimators (aka GREG or generalized
raking), simple two-phase designs, and smoothing.
-thomas
Thomas Lumley
graphics::par(bg='white')
Information from which this can be deduced and examples are in ?Startup, though
it isn't explicitly stated there.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
On Thu, 2 Aug 2007, Monica Pisica wrote:
>
> Hi,
>
> I am getting some strange results using round - it seems that it depends if
> the number before the decimal point is odd or even
Yes. This is explained in the help page for round().
-thomas
Thomas Lumley
ke a linear inequality to me.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do
no
need to constrain them to be <=1, as this is implied by the first
constraint.
It might be interesting to find out if some automated Lagrange-multiplier
approach could be built into constrOptim() for equality constraints, but
it is not a high enough priority that I am likely to do it.
r(mydata, exclude=NULL)
str(myfactor.try1)
str(myfactor.try2)
Prof Brian Ripley <[EMAIL PROTECTED]> wrote: The behaviour has been changed in
the R-devel version of R, so the 'by'
columns are not converted to factors.
On Tue, 31 Jul 2007, Thomas Pujol wrote:
> I have a two que
I have a two question regarding the "aggregate.data.frame" method of the
"aggregate" function.
My situation:
a. My "x" variable is a data.frame ("mydf") with two columns, both columns of
type/format "numeric".
b. My "by" variable is a data.frame("mybys") with two columns, both columns of
type
i am using R-Gui2.5.1 where can i find rattle() ?
previous version of R-Gui2.4.1 with rattle() works fine
i tried with the new version and i could not locate the rattle()
i follow the steps
1.install R-Gui-2.5.1
2. install gtk-2.10.7-win32-1
3. install gtk-dev-2.10.7-win32-1
4. install ggobi-
Dear Group,
I have installed R-GUI 2.5.1, thereby i tried install
>install.packages("RGtk2")
>install.packages ("rattle")
where i have problems such as below:
> install.packages("RGtk2")
Warning: unable to access index for repository
http://cran.au.r-project.org/bin/windows/contrib/2.5
Warning
what version of Wine are you running? and is this the patched (1.4.1) version
of
WinBUGS that you're trying to run?
cheers,
thomas.
> Date: Thu, 26 Jul 2007 12:03:38 -0400 (EDT)
> From: <[EMAIL PROTECTED]>
> Subject: [R] error in using R2WinBUGS on Ubuntu 6.10
but seems to discard the labels.
It doesn't discard the labels. They are kept in the attributes of the data
frame.
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the post
our R distribution.
-thomas
On Wed, 25 Jul 2007, Tom La Bone wrote:
> Minitab can perform a "Parametric Distribution Analysis - Arbitrary
> Censoring" with one of eight distributions (e.g., weibull), giving the
> maximum likelihood estimates of the parameters in the di
It's a FAQ (Question 7.32)
-thomas
On Mon, 23 Jul 2007, [EMAIL PROTECTED] wrote:
>
> Dear Sir/Madam,
>
> I am running a R program for my SNP data. There are some errors when I run
> glm model in Hapassoc software, sometimes it is over the memory and
> sometimes
ed,
but for a linear or log-linear model it is just a matter of adding
predictors.
Now, I might well use a linear mixed model in this context, but he did
fairly clearly indicate that wasn't he was looking for.
-thomas
Thomas Lumley Assoc. Professor, Biostatisti
th.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
--
Thomas E Adams
National Weather Service
Ohio River Forecast Cent
survey literature seems to be
Binder, David A. (1983). On the variances of asymptotically
normal estimators from complex surveys. International Statistical
Review, 51, 279-292.
which is in the References section of help(svyrecvar).
-thomas
___
I am trying to save an R data.frame as an Excel sheet.
I do NOT want the column names saved into row 1.
I set colnames=F.
However, it still seems that the colnames are saved into row 1.
Is this a bug? Or am I coding incorrectly and.or misunderstanding this feature?
#example code:
sheet = "c:/test
FYI, Here is a tip that Gabor Grothendieck sent to the r-com help-list.
Thought others might find it helpful.
http://mailman.csd.univie.ac.at/pipermail/rcom-l/2007-July/001717.html
Subject: Re: [Rcom-l] running Excel/Visual Basic macro from within R[input]
[input] [input] [inpu
Is there an "easy" or good way to run/launch an Excel VBA macro from within R?
-
Pinpoint customers who are looking for what you sell.
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mail
On Sun, 15 Jul 2007, Tobias Verbeke wrote:
> The survey package of Thomas Lumley has very broad functionality for the
> analysis of data from complex sampling designs. Please find below the
> homepage of the package (which is available on CRAN):
>
> http://faculty.washington.edu
mobile phone number?
Thank you
Thomas
[[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 http://www.R-project.org/posting-guide.html
en have been deleted on leaving R. This is only a guess, of
course.
The syntax for write.dta is
write.dta(the.data.set, file="dataset.dta")
and for write.foreign is
write.foreign(the.data.set,codefile="dataset.do", datafile="dataset.raw",
package="
,2,function(x) if(fn.count(x)==0) NA else
t.test(x)$statistic) }
myfn.p.val <- function(df) { apply(df,2,function(x) if(fn.count(x)==0) NA else
t.test(x)$p.value) }
Uwe Ligges <[EMAIL PROTECTED]> wrote:
Thomas Pujol wrote:
> I have a dataframe ("mydf") that conta
On Mon, 9 Jul 2007, Jim Lemon wrote:
> Hi folks,
>
> I thought I recalled a request for turning a character string into an
> object name as in:
Yes. It's a FAQ.
-thomas
> x$as.name("y")<-1:4
>
> OR
>
> x<-data.frame(as.name("y&q
I have a dataframe ("mydf") that contains "differences of means".
I wish to test whether these differences are significantly different from zero.
Below, I calculate the t-statistic for each column.
What is a "good" method to calculate/look-up the p-value for each column?
mydf=data.frame(a=c(1,-
4.86768038.25129560.611092
> 98.967689 166.572985 289.08 517.425935
> [55] 955.487320 1820.793570 3581.521323 7273.674928 15255.446778
> 33050.861013 73982.100407
>>
>
> Is it strange or did I miss something ?
You missed something. It is not clear what
-base-latex r-base-dev r-gnome
recently to update to R 2.5.1 on my version of Ubuntu (6.06).
cheers,
thomas.
> Message: 98
> Date: Wed, 4 Jul 2007 02:34:37 -0700 (PDT)
> From: msmith <[EMAIL PROTECTED]>
> Subject: Re: [R] How to install R 2.5 with Synaptic in Ub
en one might use it like
> this
>
>myfunction <- function () {
># Create bigobject here
>
>if (return.value.assigned()) {
>bigobject
>} else {
>summary(bigobject)
>}
>}
That's wh
I've read that certain operations performed on a matrix (e.g. ribind, cbind)
are often much faster compared to operations performed on a data frame.
Other then the "bind functions", what are the main operations that are
significantly faster on a a matrix?
I know that data frames allow for colum
suggests having yet another apply function, that would
assume an INDEX argument and might be written
yapply<-function(X,FUN, ...) {
index<-seq(length.out=length(X))
mapply(FUN,X,INDEX=index,MoreArgs=list(...))
}
However, I think it would be preferable in many cases
I often need to "combine" data frames, sometimes "vertically" and other times
"horizontally".
When it "better" to use merge? When is it better to use rbind or cbind?
Are there clear pros and cons of each approach?
-
[[alternative HTML version del
I am transitioning from SAS to R and am struggling with a relatively simple
analysis. Have tried Venables and Ripley and other guides but can't find a
solution.
I have an experiment with 12 tanks. Each tank holds 10 fish. The 12 tanks
have randomly assigned one of 4 food treatments - S(tarve),
The calculations are in summary.regsubsets.
Sending three copies of questions like this does not increase the chance
of a response.
-thomas
On Thu, 21 Jun 2007, [EMAIL PROTECTED] wrote:
> Hi All,
>
> I used "regsubsets" in package "leaps" to do th
I have been trying to learn the various "apply" functions but am still learning
their appropriate use. I appreciate any help the R community can offer me.
Sorry for the length of this post.
Background:
I have data on my hard drive organized in the following manner:
The data pertains to many
This is FAQ 7.32 How can I capture or ignore errors in a long simulation?
-thomas
On Tue, 19 Jun 2007, Peter Sajosi wrote:
> Hello,
>
> I have a question about error handling. I run simulation studies and often
> the program stops with an error, for example during maximu
On Tue, 19 Jun 2007, spime wrote:
>
> Is there any windows version of Design package???
>
Not at the moment. It is being updated for changes in R 2.5.0.
[This would be a FAQ except that it should stop being asked soon]
-thomas
>
>
>
>
>
> Frank E Harrell
, of course, for a discrete predictor of heterogeneity, using
strata().
-thomas
> On Monday 18 June 2007 22:56:54 Frank E Harrell Jr wrote:
>> sj wrote:
>>> I am using psm to model some parametric survival data, the data is for
>>> length of stay in an emerge
to dat2 with BNUM as index. I
would like to add the columns from dat1 to the results of
b.sum <- tapply(dat2, BNUM, sum).
However the BNUM of b.sum are only a subset of the dat1.
Does anybody knows a elegant way to solve the problem?
Thanks in advance
Thoma
tood some unusual possibility in the Stata file format -- this
has happened once before -- but it is fairly well documented. In any
case, there is not much that can be done without more information.
-thomas
__
R-help@stat.math.ethz.ch
Why not using:
lm(X[[Ytext]]~Xvar,data=X)
ThPe
Pedro Mardones wrote:
> Dear all;
>
> Is there any way to make this to work?:
>
> .x<-rnorm(50,10,3)
> .y<-.x+rnorm(50,0,1)
>
> X<-data.frame(.x,.y)
> colnames(X)<-c("Xvar","Yvar")
>
> Ytext<-"Yvar"
>
> lm(Ytext~Xvar,data=X) # doesn't run
>
in the optimization procedure.
Thomas
PS: another question, what is the purpose of the state variable N?
I guess it can be derived from the other states.
Jeremy Goldhaber-Fiebert wrote:
> Hello,
>
> I am using odesolve to simulate a group of people moving through time
> and transm
t;
>> and which functions to use for that?
>
> I *guess* write.table() will do the trick, given "dat" is what I guess
> it is...
Another approach (that preserves factor levels if you have them) is to use
write.foreign in the 'foreign' package. This wr
od [at least, I don't understand them, and I have simulations
that appear to contradict the views of people who claim to understand
them].
The difficulty probably depends on the size of the problem -- the air
pollution problems have n~1000, p~20, nc~7, or larger.
-thomas
_
worse that this, for example,
x[[7]][y][[4]] <- foo(arg1)
w <- foo(arg2)+1
names(x)[foo(arg3)] <- foo(arg4)
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read
are the same is *not* what the message says.
>
> You can't just look at elements of the results of dist() and simply
> relate them back to object numbers. Try as.matrix(x.dist) for a
> human-readable form.
>
>
> On Fri, 1 Jun 2007, Thomas Zastrow wrote:
>
>> Dea
Dear all,
I'm completely new to R and at first I must say that it is a great program!
But I have a problem with the function isoMDS from the MASS package. I
have this code which I load with source() from a file:
x <- c(163.59514923926784, 150.01448475257115, .. {here are some
more values})
ids.
>>
>> I hope there are some cheaper ways of doing it... Because the
>> dataframe is huge, it takes almost an hour to do the task. Thanks
>> so much in advance!
>
> Does this do what you want in a faster way?
>
rowsum() should probably be faster (but pe
.
>
>LuckeJF> Testing for normality prior to choosing a test
>LuckeJF> statistic is generally not a good idea.
>
> Definitely. Or even: It's a very bad idea ...
>
I think that's something we can all agree on.
-thomas
; save(dtaa,"dtaa",file="c:/dtaa")
>
> d = load("c:/dtaa")
>
>From ?load
Value:
A character vector of the names of objects created, invisibly.
So d is correct. Try ls() to find the loaded data.
-thomas
_
doesn't have an na.rm argument.
Does the same thing happen if you call svychisq() directly rather than via
summary(svytable())?
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
___
oxph doesn't converge with the same matrix?
coxfilter() fits 8000 one-variable models, which works (for appropriate
values of "works"). coxph() refuses to fit one 8000-variable model.
-thomas
__
R-help@stat.math.ethz.ch mailing list
h
<-function (color)
{
rgb <- col2rgb(color)/255
L <- c(0.2, 0.6, 0) %*% rgb
ifelse(L >= 0.2, "#60", "#A0")
}
This uses a pale yellow for dark backgrounds and a dark blue for light
backgrounds, and it seems to work reasonably well.
I want to compare the fit of a quadratic model to continuous data, with that
of a cubic spline fit. Is there a way of computing AIC from for e.g. a GAM
with a smoothing spine, and comparing this to AIC from a quadratic model?
Cheers
**
Tom Reed
PhD S
lman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
--
Thomas E Adams
National Weather Service
Ohio River Forecast Center
1901 South State Route 134
Wilmington,
oCollumn is not visible.
You could do
lapply(foos, function(foo) subset(foo, select=fooCollum))
capturing fooCollum by lexical scope. In R this is often a better option
than passing extra arguments to lapply (or other functions that take
function arguments).
-thomas
__
e does in Lisp. I naively tried
>
You could write with_options() as
with_options <-function(optionlist, expr){
oldoptions<-options(optionlist)
on.exit(options(oldoptions))
eval(substitute(expr), parent.frame())
}
and then do
with_options(l
Marc,
That did it! Thank you so much for your help…
Regards,
Tom
Marc Schwartz wrote:
> On Wed, 2007-05-16 at 16:34 -0400, Thomas Adams wrote:
>
>> I am generating a single graphic containing about 31 Boxplots; the issue
>> I am having is that not all the labels (3 ch
rched and can not find a way to do this automatically — I
could not find anything in the "R Graphics" book by Paul Murrell that
pointed me in the right direction either.
Thank you,
Tom
--
Thomas E Adams
National Weather Service
Ohio River Forecast Center
1901 South State Route 134
Duncan,
Thank you for your help — that certainly did the trick. With Sweave
being new to me, I somehow missed the obvious…
Regards,
Tom
Duncan Murdoch wrote:
> On 15/05/2007 9:22 PM, Thomas Adams wrote:
>> I am using R 2.5 on a Linux Redhat platform. I can successfully run
>&g
I am using R 2.5 on a Linux Redhat platform. I can successfully run some
example *.Rnw files through Sweave and generate pdf files. When I try my
own example file, "test.Rnw":
\documentclass[a4paper]{article}
\title{Test Sweave Example}
\author{Thomas Adams}
\begin{document}
\maketit
explicitly, the columns of Q from the QR factorization would suffice.
>
Not only is the hat matrix never calculated explicitly, the Q matrix isn't
calculated either. The code forms R and Q^TY directly (the same code is
used in the biglm package to provide bounded-
ution. So, in the US, it depends on the data and their source.
Publishers that I have talked to tend to claim that data are definitely
copyrightable, but since they tend to own the copyrights one might do well
to recall the immortal words of Mandy Rice-Davies.
-thomas
Tho
gestion for this.
r2dtable().
If this is a power calculation, though, you probably want to fix only one
margin, which is a much simpler problem, and if the table is not too large
it would not be difficult to compute the exact probability for each
element of the sample space and so get
error.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guid
math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
--
Thomas E Adams
National Weather Service
Ohio River Forecast
on()' on how to cite R or R packages in publications.
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide co
possible to
> Excel) and import it to R
> SPSS does not externalize the data format :-(
> Regards Knut
>
We don't have SPSS so unfortunately this work around is not possible.
Thank you both,
Frank
--
..
Dr. Frank Thomas
FTR Internet R
eur dans read.spss("C:RdataESS1_ICT.SAV") :
impossible d'ouvrir le fichier
I guess the error is evident for everyone else, but I don't see it.
Thanks
Frank Thomas
--
......
Dr. Frank Thomas
FTR Internet
Hi all,
I tried to do normalization of affymetrix data with bioconductor on a
Linux server. When I read in the cel files all seemed ok. But the next
step caused an error. With Win XP all works fine. Did anyone experience
similar problems?
Thanks,
Thomas
> PI <- ReadAffy(
sue is whether the estimated variance of an OLS estimator is
greater or less than the true variance of the OLS estimator. This can go
either way.
-thomas
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
out interaction
terms). The "effects" package does it better for linear regression models.
-thomas
> Here is an example illustrating my problem
>
> 1.I do a linear regression as follows
>
> summary(lm(n.day13~n.day1+ffemale.yell+fmale.yell+fmale.chroma,data=surv)
On Tue, 17 Apr 2007, Frank E Harrell Jr wrote:
> The points that Thomas and Brian have made are certainly correct, if one is
> truly interested in testing for differences in medians or means. But the
> Wilcoxon test provides a valid test of x > y more generally. The test is
>
her's exact test on the
table. This is almost never useful (because it doesn't come with an
interval estimate), but is interesting because it (and the generalizations
to other quantiles) is the only exactly distribution-free location test
that does not have the 'non-transiti
ing,... not 1.9.1?
No -- there is a new x.y.0 twice per year. Checking the r-announce
archives shows that 2.0.0 came out in October 2004 and 1.9.1 in June 2004.
Describing 1.9.1 as "the latest version" was inaccurate, but it may well
have been a more recent version than for most of the
I am trying to do what is perhaps the most basic procedure which can be done
with the R software.
Under Windows XP Home Edition, I want to get a copy of the function "gam,"
then put it in and use it. I intentionaly use informal terms, rather than
technical terms whose exact meaning I might or m
;s Law will settle some issues, but there are problems
where it is working to increase the size of datasets just as fast as it
increases computational power.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washing
1 - 100 of 1987 matches
Mail list logo
