I'll give it a try,
Thanks!
-N
On 1/6/11 11:34 PM, Steve Lianoglou wrote:
Hi,
On Fri, Jan 7, 2011 at 2:10 AM, Noah Silverman wrote:
I have a data set with about 30,000 training cases and 103 variable.
I've trained an SVM (using the e1071 package) for a binary classifier {0,1}.
The accur
I dont think JRI can correctly handle plots from R. In my opinion, JRI is
designed mainly for data sending and receiving. Plot issues should be
addressed in Java, if you use R as part of your computing engine.
2011/1/7 ying zhang
> Hi Everyone,
>
>
>
> Thanks a lot for your guys help, I finally
Hi,
On Fri, Jan 7, 2011 at 2:10 AM, Noah Silverman wrote:
> I have a data set with about 30,000 training cases and 103 variable.
>
> I've trained an SVM (using the e1071 package) for a binary classifier {0,1}.
> The accuracy isn't great.
>
> I used a grid search over the C and G parameters with
I have a data set with about 30,000 training cases and 103 variable.
I've trained an SVM (using the e1071 package) for a binary classifier
{0,1}. The accuracy isn't great.
I used a grid search over the C and G parameters with an RBF kernel to
find the best settings.
I remember that for lea
>From a purely statistical and maybe somewhat naive point of view,
published p-values should be corrected for the multiple testing that
is effectively happening because of the large number of published
studies. My experience is also that people will often try several
statistical methods to get the
Hi,
Thank you,I will try to build the packages with RTools.
I found the following links for few packages.
rJava http://www.rforge.net/rJava/files
RJDBC http://www.rforge.net/RJDBC/files/
Regards,
Raji
--
View this message in context:
http://r.789695.n4.nabble.com/R-packages-for-R-2-11
Dear R forum helpers,
I am extremely sorry for the receipt of my incomplete mail yesterday. There was
connectivity problem at my end and so I chose to send the mail through my cell,
only to realize today about the way mail has been transmitted. I am again
sending my complete mail throu
I would try using the R 2.12.1 packages first, but if that does not
work, then you can go here:
http://cran.r-project.org/src/contrib/Archive/
to get older versions of the tar balls. I think you might have to
build them yourself. I kind of doubt anyone is keeping entire
duplicates of old CRAN pac
On Jan 6, 2011, at 11:48 PM, Raji wrote:
Hi ,
I am using R 2.11.1 . I need to download few packages for the same
for
Windows.But in CRAN i see the latest packages for R 2.12.1 only. Can
you
help me out with the locations where i can find the packages for R
2.11.1
Windows zip?
At the
Part of the phenomenon can be explained by the natural censorship
in what is accepted for publication: Stronger results tend to have less
difficulty getting published. Therefore, given that a result is
published, it is evident that the estimated magnitude of the effect is
in average lar
Several possibilities:
if (length(teams)!=length(unique(teams)) stop("Some teams are duplicated")
or
if (max(table(teams))>1) stop("Some teams are duplicated")
I'm sure there are others, too.
On Thu, Jan 6, 2011 at 12:21 PM, ADias wrote:
>
> Hi,
>
> I am with a problem on how to do a compar
What is the most efficient method of parsing a dataframe-like structure that
has been json encoded in record-based format rather than vector based. For
example a structure like this:
[ {"name":"joe", "gender":"male", "age":41}, {"name":"anna",
"gender":"female", "age":23} ]
RJSONIO parses this a
Hi ,
I am using R 2.11.1 . I need to download few packages for the same for
Windows.But in CRAN i see the latest packages for R 2.12.1 only. Can you
help me out with the locations where i can find the packages for R 2.11.1
Windows zip?
Thanks in advance
--
View this message in context:
http:
On Jan 6, 2011, at 10:03 PM, Nikos Alexandris wrote:
Greets (again) :-)
I finally ran mrpp tests. I think all is fine but one very important
issue: I
have no idea how to export/save an "mrpp" object. Tried anything I
know and
searched the archives but found nothing.
And what happened wh
How about this?
> x<-c(1:5,NA,NA,8:10)
> y<-1:10
> plot(0,0,xlim=c(0,10), ylim=c(0,10),type="n",main="Dont show the bloody 0
> values!!")
> lines(x~y, col="blue", lwd=2, subset = !is.na(x))
NAs let you do lots of useful manipulations in R.
Steven McKinney
_
On Jan 6, 2011, at 6:13 PM, Taylor, Eric HLS:EX wrote:
Hello;
How do I plot these data in R without the Months being ordered
alphabetically?
Months Prec
1 Jan 102.1
2 Feb69.7
3 Mar44.7
4 Apr32.1
5 May24.0
6 Jun18.7
7 Jul14.0
8 Aug
On Jan 6, 2011, at 4:34 PM, ADias wrote:
Hi
Suppose we have an object with strings:
A<-c("a","b","c","d")
Now I do:
B<-matrix(A,4,4, byrow=F)
and I get
a a a a
b b b b
c c c c
d d d d
But what I really want is:
a b c d
b c d a
c d a b
d a b c
How can I do this?
How else?
B<-matrix(A
Hi,
I'm trying to impute a large data set using mice but I keep getting this:
Error in nnet.default(X, Y, w, mask = mask, size = 0, skip = TRUE, softmax =
TRUE, :
too many (2944) weights
nnet.default uses the argument MaxNWts to set a maximum number of weights.
I've tried to change nnet.defaul
I was very impressed with Lehrer's article. I look forward to seeing what
the rebuttals come up with. The picture that Lehrer paints of the quality
of scientific publications is very dark, and it seems to me, quite
plausible. Note that Lehrer is the author of "Proust Was a Neuroscientist"
which
Hey everyone,
Im getting better at plotting my data but cant for the life of me figure
out how to show a line graph with missing data that doesnt continue the line
down to zero then back up to the remaining values.
Consider the following
x<-c(1:5,0,0,8:10)
y<-1:10
plot(0,0,xlim=c(0,10), ylim
Aaditya,
I was also having some trouble using RPy2 (spoiler alert: I gave up!) to write
a
GUI for some R scripts I've written. I found a workaround to integrate R and
python without using that module. The idea is:
1. Write R scripts you want to use in python. I have a file with all of the
fu
Greets (again) :-)
I finally ran mrpp tests. I think all is fine but one very important issue: I
have no idea how to export/save an "mrpp" object. Tried anything I know and
searched the archives but found nothing.
Any ideas? Is really copy-pasting the mrpp results the only way?
Thank you for yo
Hello;
How do I plot these data in R without the Months being ordered alphabetically?
Months Prec
1 Jan 102.1
2 Feb69.7
3 Mar44.7
4 Apr32.1
5 May24.0
6 Jun18.7
7 Jul14.0
8 Aug20.0
9 Sep32.4
10Oct58.9
11Nov94.
Hi All, and Heberto,
Did you ever resolve your installation problem with rJava?
I have a new windows 7 machine and can't seem to get it installed correctly.
I do have Java installed. I download rJava without proble, then:
> install.packages("rJava")
Installing package(s) into ‘C:\Users\Patric
Thanks a lot Greg,
you have been very helpful.
All the best
From: Greg Snow
Sent: Thu, January 6, 2011 9:29:36 PM
Subject: RE: [R] Assumptions for ANOVA: the right way to check the normality
Some would argue to always use the kruskal wallis test since we
Hi
Suppose we have an object with strings:
A<-c("a","b","c","d")
Now I do:
B<-matrix(A,4,4, byrow=F)
and I get
a a a a
b b b b
c c c c
d d d d
But what I really want is:
a b c d
b c d a
c d a b
d a b c
How can I do this?
thank you
A. Dias
--
View this message in context:
http://r.7896
Hi,
I am with a problem on how to do a comparison of values. My script is as
follows:
repeat{
cat("How many teams to use? (to end write 0) ")
nro<-scan(n=1)
if(nro==0)break
cat("write the", nro, "teams names \n")
teams<-readLines(n=nro)
if (teams[1]==teams[2)next
else print(teams)
}
On this ex
The only difference I see is the http vs https, perhaps you require a sort
of auth to access that file.
On 6 January 2011 19:53, John Kane wrote:
> # Can anyone suggest why this works
>
> datafilename <- "
> http://personality-project.org/r/datasets/maps.mixx.epi.bfi.data";
> person.data <- r
there is an option in google doc to make public that file providing and http
url, try Share -> Public as a web page... it may work if google does not
mess up the txt too bad
Alberto
On 6 January 2011 20:59, John Kane wrote:
> I don't know. I can access it from within OOo Calc so it might be an
Hello Diego,
This might not be relevant, but on reading your question the first
idea that struck me was that ordination trajectories of your lakes
over time might be more informative than clustering.
Michael
On 5 January 2011 01:31, Diego Pujoni wrote:
> Dear R-help,
>
> In my Master thesis I m
I really appreciate all your help but I've already tried everything that has
been suggested.
I changed the path to every possible combination that leads to an R
executable...and nothing seems to work.
I've checked to see that Im typing it right. I've also asked my sister to
make sure (a fresh set
Shige Song gmail.com> writes:
>
> Dear All,
>
> I am trying to compile&install the package "RGtk2" on my Ubuntu 10.04
(...)
> ./RGtk2/gdkClasses.h:4:23: error: RGtk2/gdk.h: No such file or directory
Hi,
In a few days ago, I have had the same error on my Debian Testing. After a lot
of spent ti
Here John,
from the manual
URLs
A note on file:// URLs. The most general form (from RFC1738) is
file://host/path/to/file, but R only accepts the form with an empty host
field referring to the local machine. This is then file:///path/to/file,
where path/to/file is relative to /. So although the
https
your second link is an https
that's not supported as I recall.
?url
On Thu, Jan 6, 2011 at 11:53 AM, John Kane wrote:
> # Can anyone suggest why this works
>
> datafilename <- "
> http://personality-project.org/r/datasets/maps.mixx.epi.bfi.data";
> person.data <- read.table(datafilen
Thanks very much Bill, good catch!
John
From: William Dunlap
Cc: r-h...@stat.math.ethz.ch
Sent: Thu, January 6, 2011 3:52:47 PM
Subject: RE: [R] algorithm help
> -Original Message-
> From: r-help-boun...@r-project.org
> [mailto:r-help-boun...@r-proj
On Thu, Jan 6, 2011 at 5:41 PM, stephen sefick wrote:
> #Is there a way to break the below zoo object into non-NA data frames
> algorithmically
> #this is a small example of a much larger problem.
> #It is really no even necessary to have the continuous chunks
> #end up as zoo objects but it is im
> -Original Message-
> From: r-help-boun...@r-project.org
> [mailto:r-help-boun...@r-project.org] On Behalf Of array chip
> Sent: Thursday, January 06, 2011 3:29 PM
> To: ted.hard...@wlandres.net
> Cc: r-h...@stat.math.ethz.ch
> Subject: Re: [R] algorithm help
>
> Thanks very much, Ted. Y
Yes, the new version works fine. Many thanks.
Best,
Shige
On Thu, Jan 6, 2011 at 6:25 PM, Michael Lawrence
wrote:
>
>
> On Thu, Jan 6, 2011 at 8:53 AM, Prof Brian Ripley
> wrote:
>>
>> You need RGtk2 2.20.7 which is now on CRAN. Others have seen this, but it
>> has taken a while to track down
Thanks very much, Ted. Yes, it does what I need!
I made a routine to do this:
f.fragment<-function(a,b) {
dat<-as.data.frame(cbind(a,b))
L <- rle(dat$a)$lengths
V <- rle(dat$a)$values
pos <- c(1,cumsum(L))
V1 <- c(-1,V)
start<-1+pos[V1==0]
end<-pos[V1==1]
cbind(
On Thu, Jan 6, 2011 at 8:53 AM, Prof Brian Ripley wrote:
> You need RGtk2 2.20.7 which is now on CRAN. Others have seen this, but it
> has taken a while to track down the exact cause.
>
> The diagnosis was that ML used a recent GNU tar which created a tarball
> with hard links that R's untar was
Have you run
genclntsh
and/or
genclntst
In ORACLE_HOME/bin
?
I dont recall very well where I learned about this, or how it is documented...
But it does something to some files in $ORACLE_HOME/lib that is needed in order
for Roracle to build.
lib[598]% nm libclntsh.so | grep sqlprc
0
On 06-Jan-11 22:16:38, array chip wrote:
> Hi, I am seeking help on designing an algorithm to identify the
> locations of stretches of 1s in a vector of 0s and 1s. Below is
> an simple example:
>
>> dat<-as.data.frame(cbind(a=c(F,F,T,T,T,T,F,F,T,T,F,T,T,T,T,F,F,F,F,T)
> ,b=c(4,12,13,16,18,20,28,
#Is there a way to break the below zoo object into non-NA data frames
algorithmically
#this is a small example of a much larger problem.
#It is really no even necessary to have the continuous chunks
#end up as zoo objects but it is important to have them end
#up with the index column.
#thanks for a
Is it at all possible to specify this so that different tests display different
parameters,
ie have the continous test display F, df and p while tes categorical test
display only P values?
sf1 <- summary(trt~sex+ascites+age,data=ex,test=T,method="reverse",catTest=u)
print(sf1, prtest = "P")
/
try this:
?rle
Carl
**
From: array chip
Date: Thu, 06 Jan 2011 14:16:38 -0800 (PST)
Hi, I am seeking help on designing an algorithm to identify the
locations of stretches of 1s in a vector of 0s and 1s. Below is an
simple example:
> dat<-as.data.frame(cbind(a=c(F,F,T,T,T,T,F,F,T,
The next week's New Yorker has some decent rebuttal letters. The case
is hardly as clear-cut as the author would like to believe.
Carl
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
Allright..Works like a charm. However I do believe that the prtest vector
should have been mentioned in the catTest or conTest option. Appreciate your
time and effort.
Best,
//M
On 6. jan. 2011, at 23.24, Erik Iverson wrote:
>
>> Does the prtest argument help when you actually use the 'print'
Does the prtest argument help when you actually use the 'print' function
around your summary.formula object? I think that's how I
solve it.
I.e.,
sf1 <- summary(trt~sex+ascites,data=ex,test=T,method="reverse",catTest=u)
print(sf1, prtest = "P")
Descriptive Statistics by trt
+---+---+
sys.call(1) will work now, but as my code evolves it tends
towards having more layers of function calls and so the count
given in sys.call(count) has to be altered. This is a maintainance
problem. Sometimes, as when using generic functions, you are
not even aware that the number of calls between
The closest I get is
u<-function(a,b){
j<-fisher.test(a)
p<-list(P=j$p.value,stat=1,df=1,testname=j$method,statname="")
return(p)
}
However then I manually have to edit the output. Is there a smart way of doing
this?
You're not explaining
On Thu, Jan 6, 2011 at 4:59 PM, Duncan Murdoch wrote:
> On 06/01/2011 4:45 PM, Sebastien Bihorel wrote:
>>
>> Dear R-users,
>>
>> Is there a way I can prevent global variables to be visible within my
>> functions?
>
>
> Yes, but you probably shouldn't. You would do it by setting the environment
>
Hi, I am seeking help on designing an algorithm to identify the locations of
stretches of 1s in a vector of 0s and 1s. Below is an simple example:
> dat<-as.data.frame(cbind(a=c(F,F,T,T,T,T,F,F,T,T,F,T,T,T,T,F,F,F,F,T)
,b=c(4,12,13,16,18,20,28,30,34,46,47,49,61,73,77,84,87,90,95,97)))
> dat
Dear all,
I´m specifying the fisher.exact test for use with summary.formula as follows:
u<-function(a,b){
j<-fisher.test(a)
p<-list(P=j$p.value,stat=NA,df=NA,testname=j$method,statname="")
return(p)
}
However I´m also required to specify stat
On 06/01/2011 4:45 PM, Sebastien Bihorel wrote:
Dear R-users,
Is there a way I can prevent global variables to be visible within my
functions?
Yes, but you probably shouldn't. You would do it by setting the
environment of the function to something that doesn't have the global
environment a
Dear R-users,
Is there a way I can prevent global variables to be visible within my
functions?
Sebastien
__
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/post
Well, the goal is to include a reference to f2 in the error message
returned by f2('char'); sys.call(1) appears to do the trick. You
mentioned this function could be unreliable, could you please provide an
example?
Sebastien
William Dunlap wrote:
>> -Original Message-
>> From: r-help-b
Hi:
I'm not sure what you mean by line weight - I interpreted it to mean size,
but you already have have it in your geom_line() call. If you want thicker
lines, increase size. As for the others, try this:
ggplot(ddata, aes(x = area, y = disc, colour = year)) +
geom_point() + geom_line(aes(gro
--- On Thu, 1/6/11, Alberto Negron wrote:
From: Alberto Negron
Subject: Re: [R] Accessing data via url
To: "John Kane"
Cc: "R R-help"
Received: Thursday, January 6, 2011, 4:20 PM
there is an option in google doc to make public that file providing and http
url, try Share -> Public as a web
Hi:
On Thu, Jan 6, 2011 at 5:36 AM, Eduardo de Oliveira Horta <
eduardo.oliveiraho...@gmail.com> wrote:
> Peter,
>
> thank you, that's what I was looking for!
>
> David, I forgot to tell you my OS. Sorry... it's Win7. I'm running a RKWard
> session.
>
> And this is strange:
>
> > Cairo("example.p
On 06/01/2011 20:29, Greg Snow wrote:
> Some would argue to always use the kruskal wallis test since we never know
> for sure if we have normality. Personally I am not sure that I understand
> what exactly that test is really testing. Plus in your case you are doing a
> two-way anova and krusk
I don't know. I can access it from within OOo Calc so it might be an authority
problem but it seems unlikely or would Google sites have some strange
restrictions ?
I did discover that the trees.txt file was rather messed up so I tried again
with a clean csv file and I'm still getting the same
David,
I think the poster wants to use one of the columns as x and the other as y,
ignoring the remaining columns. If that is the case then he/she needs to read
the section in "Introduction to R" on subsetting data frames.
I agree that the output so far is meaningless, from the degrees of free
See inline
> From: Frodo Jedi [mailto:frodo.j...@yahoo.com]
> Sent: Thursday, January 06, 2011 12:37 PM
> To: Greg Snow; r-help@r-project.org
> Subject: Re: [R] Problem with 2-ways ANOVA interactions
>
> Dear Greg,
> thanks so much, I think that now I have understood. Please confirm me this
>
Andy, thanks for providing a clear way of saying it. I thought I was
clear in the first place, but oh well).
Here is the structure of my source files:
hwpkg/DESCRIPTION
hwpkg/R/hw.R
hwpkg/inst/NEWS.Rd
I'm using Windows XP. When I install this package, I do this:
Rcmd INSTALL hwpkg
Which resu
Some would argue to always use the kruskal wallis test since we never know for
sure if we have normality. Personally I am not sure that I understand what
exactly that test is really testing. Plus in your case you are doing a two-way
anova and kruskal.test does one-way, so it will not work for
On Jan 6, 2011, at 2:34 PM, kiotoqq wrote:
I used chisq.test(read.table("C:/Users/Maggy/Downloads/dust.asc",
header=TRUE))
So, where did you download this data and when is your homework due?
and got this
Pearson's Chi-squared test
data: read.table("C:/Users/Maggy/Downloads/dust.
I was communicating with Kevin off-list.
The problem seems to be run time, not install time. News() calls
tools:::.build_news_db(), and the 2nd line of that function is:
nfile <- file.path(dir, "inst", "NEWS.Rd")
and that's the problem: an installed package shouldn't have an inst/
subdirector
Ok,
I see ;-)
Let´s put in this way then. When do I have to use the kruskal wallis test? I
mean, when I am very sure that I have
to use it instead of ANOVA?
Thanks
Best regards
P.S. In addition, which is the non parametric methods corresponding to a 2
ways
anova?..or have I to
repeat m
# Can anyone suggest why this works
datafilename <-
"http://personality-project.org/r/datasets/maps.mixx.epi.bfi.data";
person.data <- read.table(datafilename,header=TRUE)
# but this does not?
dd <- "https://sites.google.com/site/jrkrideau/home/general-stores/trees.txt";
treedata <- read.tab
Dear Greg,
thanks so much, I think that now I have understood. Please confirm me this
reading what follows ;-)
To summarize from the beginning, the table I analyzed is the result of a simple
experiment. Subjects where exposed to some stimuli
and they where asked to evaluate the degree of real
I used chisq.test(read.table("C:/Users/Maggy/Downloads/dust.asc",
header=TRUE))
and got this
Pearson's Chi-squared test
data: read.table("C:/Users/Maggy/Downloads/dust.asc", header = TRUE)
X-squared = 5226.164, df = 3735, p-value < 2.2e-16
and I think it should be right for the who
On 06/01/2011 2:19 PM, Kevin Wright wrote:
Yes, exactly. But the problem is with NEWS.Rd, not NEWS.
I'm not sure who you are arguing with, but if you do file a bug report,
please also put together a simple reproducible example, e.g. a small
package containing NEWS.Rd in the inst directory (w
On Jan 6, 2011, at 1:23 PM, kiotoqq wrote:
I've got a dataset which looks like this in the beginning:
cbr dust smoking expo
1 0 0.20 15
2 0 0.25 14
3 0 0.25 18
4 0 0.25 14
5 0 0.25 14
(till no. 1240, anyway
Given the data structure below and the call to ggplot2, how can I increase the
size of the axis scale points, the line weight, and the size of the legend?
ddata <-structure(list(year = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("2003", "2007"), class = "fact
Yes, exactly. But the problem is with NEWS.Rd, not NEWS.
pkg/inst/NEWS.Rd is moved to pkg/NEWS.Rd at build time, but for
installed packages, "news" tried to load "pkg/inst/NEWS.Rd".
I'm going to file a bug report.
Kevin
On Thu, Jan 6, 2011 at 7:29 AM, Kevin Wright wrote:
> If you look at too
> Michael Friendly
> on Thu, 06 Jan 2011 09:33:25 -0500 writes:
> No one replied to this, so I'll try again, with a simple example. I
> calculate a set of log odds ratios, and turn them into a data frame as
> follows:
>> library(vcdExtra)
>> (lor.CM <- loddsrat
Hi Everyone,
Thanks a lot for your guys help, I finally got it running, now I can call my
R function from my java code.
But there is one problem left.
In my R code , it open a window and plot a curve.
Once running in Java, the window did successfully opened, but nothing
inside, instead of
Folks:
The following has NOTHING (obvious) to do with R. But I believe that
all on this list would find it relevant and, I hope, informative. It
is LONG. I apologize in advance to those who feel I have wasted their
time.
http://www.newyorker.com/reporting/2010/12/13/101213fa_fact_lehrer
Best re
I've got a dataset which looks like this in the beginning:
cbr dust smoking expo
1 0 0.20 15
2 0 0.25 14
3 0 0.25 18
4 0 0.25 14
5 0 0.25 14
(till no. 1240, anyway, a huge set)
I have to analyse cbr and smo
Hi,
I wrote a simple script to retrieve an n number of followers for a given
user in Twitter. I used a sample of n=10 to test my script and worked
perfectly but once I started to changes n I started to get the following
error:
Error in list_to_dataframe(res, attr(.data, "split_labels")) :
Res
I'm guessing this page will answer
your question:
http://www.portfolioprobe.com/2010/10/04/a-tale-of-two-returns/
If not, then you need to be more
specific.
On 06/01/2011 18:07, Amelia Vettori wrote:
Dear R forum helpers,I have following datatrans<- data.frame(currency_transacted = c("EURO", "U
I think that you are looking for the 'resid' and 'fitted' functions, these will
give you the residuals and fitted values from an lm object (that added together
gives the original response but are orthogonal to each other). Those values
can then be assigned to a data frame or used by themselves.
Dear R forum helpers,I have following datatrans <-
data.frame(currency_transacted = c("EURO", "USD", "USD", "GBP", "USD", "AUD"),
position_amt = c(1, 25000, 2, 15000, 22000, 3))date <-
c("12/31/2010", "12/30/2010", "12/29/2010", "12/28/2010", "12/27/2010",
"12/24/2010", "12/23/2010"
Remember that an non-significant result (especially one that is still near
alpha like yours) does not give evidence that the null is true. The reason
that the 1st 2 tests below don't show significance is more due to lack of power
than some of the residuals being normal. The only test that I wo
Has anyone succeeded in porting any PDF compression tools to R so far?
Regards,
Yihui
--
Yihui Xie
Phone: 515-294-2465 Web: http://yihui.name
Department of Statistics, Iowa State University
2215 Snedecor Hall, Ames, IA
On Wed, Jan 5, 2011 at 7:34 PM, Andrew Miles wrote:
> I assume you mean PD
You really need to spend more time with a good aov textbook and probably a
consultant that can explain things to you face to face. But here is a basic
explanation to get you pointed in the right direction:
Consider a simple 2x2 example with factors A and B each with 2 levels (1 and
2). Draw a
'merge' comes in handy:
> spec <- read.table(textConnection("Species 1 2 3
+ a t y h
+ b f j u
+ c r y u"), header=TRUE)
> comm <- read.table(textConnection("community sp
Santanu,
I second Phil's suggestion. sas.get is actually quite nice.
Another current option is using a command-line utility called dsread
(http://www.oview.co.uk/dsread/) to convert the sas7bdat file to a csv or tsv
format, which can then easily be read into R using read.table and its
deriva
This question of mine is now solved, thanks to a suggestion by Homer Strong,
the organizer of the R user group in Portland, Oregon.
The "unmet dependencies" as reported by install was caused by an incorrect
entry in /etc/apt/sources.list. Previously I had
deb http:///bin/linux/ubuntu hardy/
Dear David,
Thats great, thanks very much for the help, much appreciated.
On 6 Jan 2011, at 15:53, David Winsemius wrote:
On Jan 6, 2011, at 6:36 AM, Chris Mcowen wrote:
> Dear List,
>
> I have a data frame called trait with roughly 800 species in, each species
> have 15 columns of informat
On Jan 6, 2011, at 11:23 AM, Sören Vogel wrote:
Thanks for your replies. I am no mathematician or statistician by far,
however, it appears to me that the actual value of any of the two LLs
is indeed important when it comes to calculation of
Pseudo-R-Squared-s. If Rnagel devides by (some transfo
You need RGtk2 2.20.7 which is now on CRAN. Others have seen this,
but it has taken a while to track down the exact cause.
The diagnosis was that ML used a recent GNU tar which created a
tarball with hard links that R's untar was not prepared to deal with.
We consider that is a bug in GNU tar
Look forward to it.
Thanks.
Shige
On Sat, Jan 1, 2011 at 8:45 AM, Michael Lawrence
wrote:
> Please watch for 2.20.5 and let me know if it helps. Not really sure what is
> going on here, but someone else has reported the same issue.
>
> Thanks,
> Michael
>
> On Wed, Dec 29, 2010 at 6:44 AM, Shig
Thanks for your replies. I am no mathematician or statistician by far,
however, it appears to me that the actual value of any of the two LLs
is indeed important when it comes to calculation of
Pseudo-R-Squared-s. If Rnagel devides by (some transformation of) the
actiual value of llnull then any cal
Sören Vogel gmail.com> writes:
>
> Hello, after calculating a multinomial logit regression on my data, I
> compared the output to an output retrieved with SPSS 18 (Mac). The
> coefficients appear to be the same, but the logLik (and therefore fit)
> values differ widely. Why?
Since constants t
On Jan 6, 2011, at 11:06 AM, Sören Vogel wrote:
Hello, after calculating a multinomial logit regression on my data, I
compared the output to an output retrieved with SPSS 18 (Mac). The
coefficients appear to be the same, but the logLik (and therefore fit)
values differ widely. Why?
The likeli
On Thu, Jan 6, 2011 at 5:56 AM, emj83 wrote:
>
> Hi,
>
> I have several matrix in a list, for example:
> e
> [[1]]
> [,1] [,2]
> [1,] 1 3
> [2,] 2 4
>
> [[2]]
> [,1] [,2]
> [1,] 1 4
> [2,] 2 5
> [3,] 3 6
>
> [[3]]
> [,1] [,2]
> [1,] 2 1
>
> I would l
Hello, after calculating a multinomial logit regression on my data, I
compared the output to an output retrieved with SPSS 18 (Mac). The
coefficients appear to be the same, but the logLik (and therefore fit)
values differ widely. Why?
The regression in R:
set.seed(1234)
df <- data.frame(
"y"=fa
On Jan 6, 2011, at 3:11 AM, thomas.car...@bnpparibas.com wrote:
> Hello,
>
> I have applied all tips (except moving to different DB lib) :
>
> move to R-2.12.1
> try R CMD INSTALL instead of install.packages('ROracle');
> run as root
> checked that I have full 32 bit env
>
> It still fails wit
Hello,
Can the x and y axis limits be specified in a density plot with the
mixtools package for a finite mixture model? Uncommenting the xlim2/
ylim2 lines in the plot command below generates 'not a graphical
parameter' warnings (and does not change the axis settings), and
uncommenting the xlim/y
1 - 100 of 144 matches
Mail list logo
