Am Dienstag 16 Dezember 2008 17:13:33 schrieb Wayne F:
> stephen sefick wrote:
> > yes a parallel coordinates plot- I understand that it is for
> > multivariate data, but I am having a hard time figuring out what it is
> > telling me. Thanks for your help.
>
> In the lattice book, the author menti
Hi, I'm a new R user, coming from SPSS, and without a particularly strong
stats background.
I've got a data set that I'd like to do a mixed-design ANOVA with. No
missing values. Here's the summary:
summary(learnDat.ae)
Type Subjectidio struct TrainErrscond
0:20
Your design seems to be unbalanced: multistatum aov is intended for
balanced designs. My guess is that one idio subject has two Type=1
observations: in which case try removing one of them.
On Tue, 16 Dec 2008, Harlan Harris wrote:
Hi, I'm a new R user, coming from SPSS, and without a particu
In general I try not to post questions to forums until I've tried my best to
read about them in the available documentation. I recently undertook a
project that used odfWeave and have been very pleased with the package.
But, the R help documentation suggests that there are more sophisticated
thi
Ah, that was it. I had a bad row in there that I had forgotten to remove.
Thank you very much for the prompt (and correct!) response.
-Harlan
On Tue, Dec 16, 2008 at 3:58 PM, Prof Brian Ripley wrote:
> Your design seems to be unbalanced: multistatum aov is intended for
> balanced designs. My g
On Tue, 16 Dec 2008, Peter Dalgaard wrote:
power.prop.test (sic) is relying heavily on asymptotic normality, as do similar
formulas. It doesn't use continuity correction, but if you're working with such
small group sizes, I suspect that the correction term is the least of your
worries and tha
By trial and error I have discovered that it works if I don't use the formula
interface in combination with a covariance matrix as input.
If the covariance matrix has the dependent variable as its left-most
variable as the relaimpo documentation suggests, then the relaimpo package
will run by sim
Fredrik Lundgren wrote:
R-ers!
Referees demand that the line in the KM-curve should be changed to
dotted at the point where standarerror is <= 10 %. I don't think it's
a good habit but I urgently need to implement such a thing in R with
survfit, survplot or another program. They also want numb
Here are a couple of function definitions that may be more intuitive for some
people (see the examples below the function defs). They are not perfect, but
my tests showed they work left to right, right to left, outside in, but not
inside out.
`%<%` <- function(x,y) {
xx <- attr(x,'orig
Hi all,
Is it possible to programmatically minimise the main window of the
windows R gui? I'm designing a small gui with gwidgets & RGtk2 for an
non-statistician to use, and it would be nice if I could easily hide
all the R stuff that they don't need.
Thanks,
Hadley
--
http://had.co.nz/
Another Newbie Question sorry:
I am trying to apply a function a dataframe and could use some help:
Assuming, dim(df) = (10,2) say, I would like to apply a function that looks
at each row in turn and returns a list (dim =(10,1)) using the columns as
inputs to the function, but with no INDEX stuf
On Dec 16, 2008, at 6:00 PM, glenn roberts wrote:
Another Newbie Question sorry:
I am trying to apply a function a dataframe and could use some help:
Assuming, dim(df) = (10,2) say, I would like to apply a function
that looks
at each row in turn and returns a list (dim =(10,1)) using the
On Tue, 16 Dec 2008, hadley wickham wrote:
Hi all,
Is it possible to programmatically minimise the main window of the
windows R gui? I'm designing a small gui with gwidgets & RGtk2 for an
non-statistician to use, and it would be nice if I could easily hide
all the R stuff that they don't need.
Hi All:
I would like to extract the provider name, address, and phone number
from multiple webpages like this:
http://oasasapps.oasas.state.ny.us/portal/pls/portal/oasasrep.providersearch.take_to_rpt?P1=3489&P2=11490
Based on searching R-help archives, it seems like the XML package
might have
hi,
I try to append a line to a file with;
writeLines("xxx", con = "file.txt, sep = "\n")
but it always overwrites the existing content.
How can I "change" the "mode" of writeLines to append ("a") ?
__
R-help@r-project.org mailing list
https://sta
On Tue, Dec 16, 2008 at 5:40 PM, Prof Brian Ripley
wrote:
> On Tue, 16 Dec 2008, hadley wickham wrote:
>
>> Hi all,
>>
>> Is it possible to programmatically minimise the main window of the
>> windows R gui? I'm designing a small gui with gwidgets & RGtk2 for an
>> non-statistician to use, and it
On 17/12/2008, at 1:43 PM, Jörg Groß wrote:
hi,
I try to append a line to a file with;
writeLines("xxx", con = "file.txt, sep = "\n")
but it always overwrites the existing content.
How can I "change" the "mode" of writeLines to append ("a") ?
The help on connections says:
In ge
G'day Hadley,
On Tue, 16 Dec 2008 18:54:48 -0600
"hadley wickham" wrote:
> On Tue, Dec 16, 2008 at 5:40 PM, Prof Brian Ripley
> wrote:
> > On Tue, 16 Dec 2008, hadley wickham wrote:
[...]
> >> Is it possible to programmatically minimise the main window of the
> >> windows R gui? I'm designing
Dear all,
I have the following data structure
> print(testlib)
$tags
tagcount.raw count.adj err
1 aa94 93 0.5
2 ac 1 2 0.2
3 ag 3 2 0.1
4
I don't know if this is what you want, but it seems that you just want
to print a subset of your columns:
testlib$tags[,c("tag", "count.raw", "count.adj")]
if you want to do something other than just "print" the columns then
look at the apply family of functions.
On Tue, Dec 16, 2008 at 9:02 PM
Much thanks! This helped a lot. Another quick one:
In using the lmList function in the nlme package, is it possible to subset
my data according to the number of observations in each level? (ie. I
obviously want to include only those levels in which the observations are of
sufficient size for regre
hi,
I want to append a string to a string like;
x <- c("abc")
append(x, "def")
so that I get for x:
[1] "abcdef"
not (!)
[1] "abc" "def"
How can I do that in R?
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-hel
Hi Chuck.
Well, here is one way
theURL =
"http://oasasapps.oasas.state.ny.us/portal/pls/portal/oasasrep.providersearch.take_to_rpt?P1=3489&P2=11490";
doc = htmlParse(theURL, useInternalNodes = TRUE,
error = function(...) {}) # discard any error messages
# Find the nodes
?paste
On Dec 16, 2008, at 10:39 PM, Jörg Groß wrote:
hi,
I want to append a string to a string like;
x <- c("abc")
append(x, "def")
so that I get for x:
[1] "abcdef"
not (!)
[1] "abc" "def"
How can I do that in R?
__
R-help@r-project.or
On Wed, Dec 17, 2008 at 9:09 AM, Jörg Groß wrote:
> hi,
>
>
> I want to append a string to a string like;
>
> x <- c("abc")
> append(x, "def")
paste (x, "def", sep="")
see ?paste
HTH
Aval
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mail
I was able to get a surface plot with wireframe, however I cant rotate it
around like you can with the plot3d function?
Is thier a way to do this in R?
To: r-help@r-project.org
Date: Tuesday, December 16, 2008, 9:13 AM
I am trying to do a surface profile plot.
data is
X
Hi all, I was hoping somebody may know of a function for simulating a
large binary sequence (length >10 million) using a (1st order) markov
model with known (2x2) transition matrix. It needs to be reasonably
fast. I have tried the following;
mc<-function(sq,P){
s<-c()
x<-row.names(P)
n<-len
On 16/12/2008 5:05 PM, Brad B wrote:
I was able to get a surface plot with wireframe, however I cant rotate it
around like you can with the plot3d function?
Is thier a way to do this in R?
You are making your question impossible to answer, by not giving the
right details. If you show us code
On Wed, 17 Dec 2008, Chris Oldmeadow wrote:
Hi all, I was hoping somebody may know of a function for simulating a large
binary sequence (length >10 million) using a (1st order) markov model with
known (2x2) transition matrix. It needs to be reasonably fast.
Chris,
The trick is to recognize t
On my current home system, I am getting undesirable output from
graphical devices such as png() and pdf(). The graphical output is
blurry. I haven't experienced the problem on other systems. As you
will see from the attached text file (more information on this file
below), the problem does not occu
you can have a look at the rollapply() function in the zoo package, e.g.,
x <- rbinom(100, 1, 0.5)
z <- zoo(x)
rollapply(z, 3, sum)
I hope it helps.
Best,
Dimitris
Chris Oldmeadow wrote:
Hi all,
I have a very large binary vector, I wish to calculate the number of
1's over sliding windows
>
>Dear R Core Team,
>
>
>
>I am using package {urca} to do cointegration and estimate ECM model,
>but I have the following two problems:
>
>
>
>(1)I use ca.jo() to do cointegration first and can get the
>cointegration rank, alpha and beta. The next step is to test some
>restrictions on beta
> sl <- function(x,z) c(0,cumsum(diff(x)[1:(length(x)-z-1)])) +
> rep(sum(x[1:z]),length(x)-z)
> x <- rbinom(10, 1, 0.5)
> system.time(xx1 <- slide(x,12))
utilisateur système écoulé
36.860.45 37.32
> system.time(xx2 <- sl(x,12))
utilisateur système écoul
Hi all,
I recently put a new version of my french introduction to R online. It
is more specifically targeted at social sciences students and
researchers, but could be interesting for beginners who are not
really familiar with statistics and coding.
The document is available (in french) in PDF, as
Hi: Veslot: I'm too tired to even try to figure out why but I think
that there is something wrong with your sl function. see below for an
empirical
proof of that statement. OR maybe you're definition of sliding window
is different than rollapply's definition but rollapply's answer makes
more
Hi Chris,
On Tuesday 16 December 2008, Chris Oldmeadow wrote:
> Hi all,
>
> I have a very large binary vector, I wish to calculate the number of
> 1's over sliding windows.
> [...snip...]
Your function does not seem to function very well, could you please offer a
self-contained, reproducible ex
Hi guys,
I'm working on a package, and I want to create a new version file pdf.
On R 2.6.2 it ran ok with the code: R CMD Rd2dvi.sh --pdf pkg.
But it doesn't run on R 2.8.0.
What I'm doing wrong?
These are my components:
ActivePerl-5.8.8.822-MSWin32-x86-280952
basic-miktex-2.7.2960
For this particular proble (counting), doesn't cumsum solve it
effectively and efficiently?
vv <- cumsum(v)
vv[n:length(vv)] - vv[1:(length(vv)-n+1]
Of course, this doesn't work for the general case of an arbitrary
sliding window function.
-s
On 12/15/08, Chris Oldmeadow wrote:
>
Jeff Hamann forestinformatics.com> writes:
>
> After writing some code (stupidly without checking to see if there was
> code to do this already) to generate PostGIS SQL insert statements for
> simple geometry (wkt), I didn't check see if there is already something
> available to convert WKT s
On Tue, 16 Dec 2008, David Winsemius wrote:
You cannot keep them as strings and still get the benefits of working with
date-class objects. You should read more documentation regarding dates. The
You can: order() will work on the Date class and the ordering can be
applied to the original data.
Dear List:
Has anyone done any work developing functions for producing Soundex
codes in R? RSiteSearch('soundex') did not yield any results or did my
google searches.
Harold
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-h
While I do not know if anything has changed in lattice, you should provide
a self-contained, reproducible example as indicated by the posting guide.
That way we (and you) can determine if it's a syntax error, or an issue
with your particular data.
On Tue, 16 Dec 2008 14:56:09 +, "Fredrik Ka
if you want the speed, you can simply build an fts time series from
it, then apply the moving.sum function and throw away the dates.
this will probably be the fastest implementation of rolling applies
out there unless you do a cumsum difference function.
I got a sample timing of 2 seconds on 12m
sorry for reposting. Some code was missing in my previous email...
--
Dear Gavin
glm reported exactly what it noticed, giving a warning that some very
small fitted probabilities have been found.
However, your data are **not** quasi-separated. The
Thanks very much. the presentation is very helpful.
-Whit
On Mon, Dec 15, 2008 at 6:31 PM, Dirk Eddelbuettel wrote:
> On Mon, Dec 15, 2008 at 01:16:46PM -0500, Whit Armstrong wrote:
>> I have a network of four machines set up. I'm having trouble spawning
>> my slaves on these machines.
>>
>>
Dear all,
I'm using zeroinfl() from the pscl-package for zero inflated Poisson
regression. I would like to calculate (aproximate) prediction intervals
for the fitted values. The package itself does not provide them. Can
this be calculated analyticaly? Or do I have to use bootstrap?
What I tried u
Thierry,
Simon had written some code for this but we never got round to fully
integrate it into the "pscl" package. A file pb.R is attached, but as a
disclaimer: I haven't looked at this code for a while. It still seems to
work (an example is included at the end) but please check.
hth,
Z
On
Hi
Does anyone know how I can use structured arrays in r
similar to a dataframe in matlab
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting
Hi,
sorry, but it shouldn't be "different". The result should be the same but I was
looking if there is a method I can use...
# having a function defined like baptiste proposed:
isIn <-
function (interval, x)
{
(x > min(interval)) & (x < max(interval))
}
#--
a <- rno
You cannot keep them as strings and still get the benefits of working
with date-class objects. You should read more documentation regarding
dates. The as.Date function turns strings into a form that is stored
internally as number of days since some reference date and what you
are seeing is
Hi, there,
I used R CMD check to build my "ATGGS" package under window XP system. My R
version is 2.7.2. But I encounter some problems. The log file is like:
**
installing R.css in C:/ATGGS.Rcheck
-- Making
Maithili Shiva wrote:
Dear R helpers,
How do you estimate the (Location, Scale, Shape) parameters of Generalized
Extreme Value distribution using R?
...
Package lmom, function pelgev.
J. R. M. Hosking
__
R-help@r-project.org mailing list
https://
On Tue, 16 Dec 2008, Sergi M.Garrido wrote:
Hi guys,
I'm working on a package, and I want to create a new version file pdf.
On R 2.6.2 it ran ok with the code: R CMD Rd2dvi.sh --pdf pkg.
But it doesn't run on R 2.8.0.
What I'm doing wrong?
Not telling us what the problem was. But the co
Hello;
This is bit long email but hope someone can guide me.
I have questions regarding socket, readLines and textConnection. I am
not sure if my code is efficient (due to textConnection) and how to
handle client disconnect and restart of the socket server in R.
I have a huge(3.5+G) text file on
I want to generate a list (called "dataList" below) where each of its
levels is named. These names are assigned to nameList, which contains
all possible permutations of size two taking letters from a larger
alphabet, e.g., "aa",...,"Fd",..,"Z1",... One of these permutations is
the character s
Yes you are right. However using that code, format of date is altered. I need
to main same format as the input data i.e. "10-02-2008" not "2008-10-02",
still having date-class. Any better idea?
David Winsemius wrote:
>
> You might want to look at your date format more closely. Both the
> sepa
Dear R helpers,
How do you estimate the (Location, Scale, Shape) parameters of Generalized
Extreme Value distribution using R?
I have tried VGAM but just not able to write the R script.
Please advise.
With regards
Maithili
__
R-help@r-project.org m
Cliff Behrens wrote:
I want to generate a list (called "dataList" below) where each of its
levels is named. These names are assigned to nameList, which contains
all possible permutations of size two taking letters from a larger
alphabet, e.g., "aa",...,"Fd",..,"Z1",... One of these permutatio
Hi all,
I'd like to know, if I can solve this with a shorter command:
a <- rnorm(100)
which(a > -0.5 & a < 0.5)
# would give me all indices of numbers greater than -0.5 and smaller than +0.5
I have something similar with a dataframe and it produces sometimes quite long
commands...
I'd like t
Quite irritating to me as the Manager of .NA too, when I
used NA for .NA :-)-O
el
Peter Dalgaard wrote:
> Cliff Behrens wrote:
>> One of these permutations
>> is the character string "NA". It seems that when I try to name one of
>> the dataList levels "NA", using names(dataList)<- nameList, the
Peter,
OK...here is reproducible, self-contained code:
library(gregmisc)
columnNames <- c("A","B","C","D","N","a","b","c")
namePerms<- permutations(length(columnNames),2,columnNames,repeats=TRUE)
nameList <- paste(namePerms[,1],namePerms[,2],sep="")
dataList <- lapply(1:length(nameList), functio
the function works for me
s<-rbinom(1000,1,0.5)
t<-slide(s,50)
just too slow.
Thanks.
__
R-help@r-project.org 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 p
Daniel Brewer wrote:
Hi,
I am trying to sort out a discrepancy between power calculations results
between me and another statistician. I use R but I am not sure what she
uses. It is on the proportions test and so I have been using
pwr.prop.test. I think I have tracked the problem down to pwr.
Peter Dalgaard wrote:
Daniel Brewer wrote:
Hi,
I am trying to sort out a discrepancy between power calculations results
between me and another statistician. I use R but I am not sure what she
uses. It is on the proportions test and so I have been using
pwr.prop.test. I think I have tracked t
I have a date-like-vector like :
> date_file
"10-02-2008" "10-03-2008" "10-06-2008" "10-07-2008" "10-09-2008"
"10-10-2008" "10-13-2008" "10-14-2008" "10-15-2008"
"10-16-2008" "10-17-2008" "10-20-2008" "10-21-2008" "10-22-2008"
"10-23-2008" "10-24-2008" "10-28-2008" "10-29-2008"
"10-30-2008" "1
Cliff Behrens wrote:
Peter,
OK...here is reproducible, self-contained code:
library(gregmisc)
Relying on a 3rd party package is not kosher either... Whatever did
list("NA"=2) or l <- list(2); names(l) <- "NA" do to you?
columnNames <- c("A","B","C","D","N","a","b","c")
namePerms<- permutat
> good morging,
>
> I need to install R-2.x on my host:
>
> Linux, 2.6.5-7.308-smp #1 SMP Mon Dec 10 11:36:40 UTC 2007 x86_64
> x86_64 x86_64 GNU/Linux
>
> now I have check the packages on your document:
> http://cran.r-project.org/bin/linux/suse/ReadMe.html
> but I have a problem whit xorg-x11
stephen sefick wrote:
>
> yes a parallel coordinates plot- I understand that it is for
> multivariate data, but I am having a hard time figuring out what it is
> telling me. Thanks for your help.
>
In the lattice book, the author mentions that static parallel plots aren't
very useful, in gener
Dear R help,
I have an xls file with the name ONS.csv having 25 obseravations as given below.
This is my data. (i.e. the first column of file ONS.csv)
(5.55,4.56,17.82,5.03,5.3,40.28,8.05,27.8,5.85,5.42,14.75,46.13,18.5,4.58,
4.31,9.19,6.61,15.92,96.94,21.63,4.44,4.88,241.74,38592.1,5.24)
I a
2008/12/16 RON70
>
> Yes you are right. However using that code, format of date is altered. I
> need
> to main same format as the input data i.e. "10-02-2008" not "2008-10-02",
> still having date-class. Any better idea?
You may try this:
format(sort(a,decreasing=TRUE),"%m-%d-%Y")
>
>
>
> D
You might want to look at your date format more closely. Both the
separator and the year format specs fail to match your input.
> as.Date("10-02-2008", format = "%m/%d/%y")
[1] NA
> as.Date("10-02-2008", format = "%m-%d-%Y")
[1] "2008-10-02"
--
David Winsemius
On Dec 16, 2008, at 7:54 AM, RON7
I am trying to do a surface profile plot.
data is
X Y(1) Z(1)
1-jan-02 2002 number
2-jan-02 2002 number
.
.
.
1-jan-03 2003 (Y2) number Z(2)
2-jan-03 2003 (Y2) number Z(2)
.
.
.
until dec 31 2007.
I used the plot3d funtio
This message accidentally (list moderator mistake) made it to
R-packages; it clearly should have been R-help only.
Please only reply to R-help if you can help Sue.
Martin Maechler,
R-packages list moderator
>> Hi, there,
>> I used R CMD check to build my "ATGGS" package under window XP system.
Hi R-users,
I want to apply a function to each column of a data frame that is numeric.
Thus I tried to check it for each column first:
> apply(df, 2, function(x) is.numeric(x))
A60 A64 A66a A67 A71 A75a A80
A85 A91 A95 A96 A97
Try:
sapply(df, is.numeric)
On Tue, Dec 16, 2008 at 1:25 PM, Mark Heckmann wrote:
> Hi R-users,
>
> I want to apply a function to each column of a data frame that is numeric.
> Thus I tried to check it for each column first:
>
> > apply(df, 2, function(x) is.numeric(x))
>
> A60 A64
On Dec 16, 2008, at 7:19 AM, Antje wrote:
Hi David,
thanks a lot for your proposal. I got a lot of useful hints from all
of you :-)
David Winsemius schrieb:
It's not entirely clear what you are asking for, since
which(within.interval(a, -0.5, 0.5)) is actually longer than
which(a > -0.
Thank you all for the reply. I´ll start using <-.
Best regards,
Petter Hedberg
University of Warsaw.
2008/12/16 Gabor Grothendieck :
> In most cases <- and = are the same yet its not always
> true so its safest to use <- for assignment.
>
> Check this out:
>
> http://tolstoy.newcastle.edu.au/R/
On Tue, 2008-12-16 at 13:31 +0100, vito muggeo wrote:
> dear Gavin,
> I do not know whether such comment may be still useful..
Very much so, Thank you.
>
> Why are you unsure about quasi-separation?
> I think that it is quite evident in the plot
Unsure in the sense that I had been unable to asc
On Tue, 16 Dec 2008, Nathan S. Watson-Haigh wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Charles C. Berry wrote:
On Mon, 15 Dec 2008, Nathan S. Watson-Haigh wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Nathan S. Watson-Haigh wrote:
I'm trying to calculate Pearson correlatio
On Mon, 15 Dec 2008, Shu Chen wrote:
Hi, there,
I used R CMD check to build my "ATGGS" package under window XP system. My R
version is 2.7.2. But I encounter some problems. The log file is like:
**
installing R.cs
Hi David,
thanks a lot for your proposal. I got a lot of useful hints from all of you :-)
David Winsemius schrieb:
It's not entirely clear what you are asking for, since
which(within.interval(a, -0.5, 0.5)) is actually longer than which(a >
-0.5 & a < 0.5).
Right but in case 'a' is someth
On Mon, 15 Dec 2008, ARIF WIJAYA wrote:
Hai everbody,??Is there anyone have simple application b-spline in r
language? I need it for make me understanding about b-spline for
polynomial spline.
Try this:
library(splines)
example(bs)
Did you reading the posting guide??
There are some ter
Peter,
I've inserted response inline below:
Cliff
Peter Dalgaard wrote:
Cliff Behrens wrote:
Peter,
OK...here is reproducible, self-contained code:
library(gregmisc)
Relying on a 3rd party package is not kosher either... Whatever did
list("NA"=2) or l <- list(2); names(l) <- "NA" do to y
I have been using the following random intercept model with non-informative
prior:
model {
for (i in 1:n.samples) {
vomit[i] ~ dbern(p[i])
logit(p[i]) <- beta0 + alpha[siteid[i]]
}
for (j in 1:n.sites) {
alpha[j]~dnorm(0,tau)
}
beta0 ~ dnorm(0.0,1.0E-6)
tau ~ dgamma(0.01,0.01)
}
list(n.samples=3780
Antje wrote:
Hi,
sorry, but it shouldn't be "different". The result should be the same but I was
looking if there is a method I can use...
# having a function defined like baptiste proposed:
isIn <-
function (interval, x)
{
(x > min(interval)) & (x < max(interval))
}
Along the lines
On Dec 16, 2008, at 8:49 AM, Prof Brian Ripley wrote:
On Tue, 16 Dec 2008, David Winsemius wrote:
You cannot keep them as strings and still get the benefits of
working with date-class objects. You should read more documentation
regarding dates. The
You can: order() will work on the Date
Hi,
I have some summary data from which I know a few points and I'd like
to remove them. Does anyone know if there is an R module that
implements something like Hanson (1975)?
Hanson (1975). Stably updating mean and standard deviation of data.
Communications of the ACM, 18(1), 57-58.
Hi,
I am trying to sort out a discrepancy between power calculations results
between me and another statistician. I use R but I am not sure what she
uses. It is on the proportions test and so I have been using
pwr.prop.test. I think I have tracked the problem down to pwr.prop.test
not using the
dear Gavin,
I do not know whether such comment may be still useful..
Why are you unsure about quasi-separation?
I think that it is quite evident in the plot
plot(analogs ~ Dij, data = dat)
Also it may be useful to see the plot of the monotone (profile) deviance
(or the log-lik) for the coef of
from ?apply:
" If 'X' is not an array but has a dimension attribute, 'apply' attempts
to coerce it to an array via as.matrix' if it is two-dimensional (e.g.,
data frames) or via 'as.array'."
if any of the columns in your dataframe is not numeric, apply will try
to coerce all of them to the least
Dear list,
Sorry for asking this question, but has something changed in the
syntax for bwplot in Lattice? In an old publication, I used
> bwplot( VOTMS ~gender |type * group,
data=merge(vot,words,by="ord"),
nint=30,
horizontal=F,
layout=c(3,3),
On Tue, Dec 16, 2008 at 8:23 AM, Gabor Grothendieck
wrote:
> There seems to be something wrong:
>
>> slide(c(1, 1, 0, 1), 2)
> [1] 2 2
>
> but the output should be c(2, 1, 2)
That should be c(2, 1, 1)
>
> At any rate try this:
>
> library(zoo)
> 3 * rollmean(x, 3)
>
>
> On Mon, Dec 15, 2008 at 1
... and an addendum
Hadley Wickham's plyR package attempts to redress these (nevertheless
documented) apparent inconsistencies in the *apply family of functions by
handling everything in a more consistent intuitive manner. You may wish to
use those instead of the base R *apply functions.
-- Bert
Dear Gavin,
glm reported exactly what it noticed, giving a warning that some very
small fitted probabilities have been found.
However, your data are **not** quasi-separated. The maximum likelihood
estimates are really those reported by glm.
A first elementary way is to change the tolerance an
Antje wrote:
Hi all,
I'd like to know, if I can solve this with a shorter command:
a <- rnorm(100)
which(a > -0.5 & a < 0.5)
# would give me all indices of numbers greater than -0.5 and smaller than +0.5
I have something similar with a dataframe and it produces sometimes quite long
commands.
I remember having similar problem with inprod function. As far as I could
remember a sole deference in my models was that I used inprod instead of
explicit sum (exactly as you did). In my case the inprod version was faster but
result were completely aberrant. So I abandoned the inprod as unreli
Cliff Behrens wrote:
Peter,
I've inserted response inline below:
Cliff
Peter Dalgaard wrote:
Cliff Behrens wrote:
Peter,
OK...here is reproducible, self-contained code:
library(gregmisc)
Relying on a 3rd party package is not kosher either... Whatever did
list("NA"=2) or l <- list(2); na
On Tue, 16 Dec 2008, RON70 wrote:
I have a date-like-vector like :
date_file
"10-02-2008" "10-03-2008" "10-06-2008" "10-07-2008" "10-09-2008"
"10-10-2008" "10-13-2008" "10-14-2008" "10-15-2008"
"10-16-2008" "10-17-2008" "10-20-2008" "10-21-2008" "10-22-2008"
"10-23-2008" "10-24-2008" "10-28-
Sorry...I didn't realize that there were such distinct lines drawn
around core vs contributed packages. I merely thought that r-help put
those with questions in touch with others who might have used or
authored a package and experienced the same problem. I didn't intend to
make more work for
Laura,
Try using a different browser for your download. On MacOS X, Safari quite often
does weird stuff to files
I want to download, frequently damaging the files. Downloading the same file
from the same site using
FireFox usually works fine.
Hope this helps,
Kathi
--
DropNet AG - Das Unter
1 - 100 of 108 matches
Mail list logo
