Hello Sean,
It appears that you can fetch it using:
summary(a)$rsq
Full code:
require(biglm)
data(trees)
ff<-log(Volume)~log(Girth)+log(Height)
a <- biglm(ff,trees)
summary(a)$rsq
summary(lm(ff,trees))$r.squared # we get the same result
To see how it is computed, have a look at:
getAnywhere
Thanks for these various tips.
Sarah, this is not a howework, but a simplified dataset speecificly for
this question.
Laura
.
2011/11/14 Dennis Murphy
> Groupwise data summarization is a very common task, and it is worth
> learning the various ways to do it in R. Josh showed you one way to
> u
Hello Bernhard:
Thank you for your kindly help. Actually, I have tried to read the
source code, but I can not understand it clearly. But with your
recommendation, I do think you are right.
I guess, when I use the criterion of "BIC" in CADFtest, I set the
max.lag.y=14. It seems to reduce t
Hello. I had been struggling with running linear regression using
lm() primarily because my data has a few categorical variables with at
least a thousand levels.
I tried the biglm() function and it worked.
My problem now is that i don't know how to get the R2 results. Could
someone help?
Thank
Thanks for reply,
tried as sudo, but error still persist.
Andrej
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minima
Perhaps something like:
sapply(1:40, function(n) c(gauss.quad(n)$nodes, rep(NA, 40-n)))
sapply(1:40, function(n) c(gauss.quad(n)$weights, rep(NA, 40-n)))
You'll have to decide how you want the records combined but this
should get you going in the right direction
Michael
PS -- it's polite to say
The easiest thing is almost certainly going to be to redefine
print.aov as desired. You can get it at by typing stats:::print.aov.
Copy the code edit and then reassign it to print.aov in the global
environment and voila!
Michael
On Mon, Nov 14, 2011 at 11:49 PM, Sverre Stausland
wrote:
> Hi R us
What exactly is it that's worrying you? It's a problematic regression
for a few reasons, but ultimately it seems pretty ok, though I'd be
ever so slightly worried about the R^2 value being misinterpreted.
Michael
On Mon, Nov 14, 2011 at 10:49 PM, Miles Yang wrote:
> Hi all,
> I wrote a r program
It might be better to post it to the LyX mailing list
(lyx-us...@lists.lyx.org) since you are using LyX. Anyway, the problem
came from Sweave: you did not tell us your R version, and I suppose
you are using the latest version of R (2.14.0). There are two ways of
telling Sweave your UTF8 encoding (s
I'm not aware of a way that one can have "blank" data.frame elements
in Rsomething about this seems mighty suspicious...
For the NA's, if you wish to omit them, I might suggest na.omit()
I don't know if you've seen this, but you should have a look at the
apropos() command. Very helpful
Micha
On 15/11/11 14:21, Giuseppe wrote:
I often use Lyx/Sweave and I typically write in english.
Today I had to write a document in Italian and, as many of you know,
many italian popular words use è, ù, é. ò, etc.
Note that you can render these in LaTex as \`{e}, \`{u}, \'{e},
and \`{o}, respective
Hi,
I want to remove the entire row from the dataset if any of the row contains
blank or NA
my dataset look like
State YearY X2 X3 X4 X5 X6
State1 196027.8397.5 42.250.778.365.8
State2 196029.9413.3 38.152 79.266.9
Hi all,
I wrote a r program as below:
x <- 1:10
y <- c(3,3,3,3,3,3,3,3,3,3)
fit <- lm(log(y) ~ x)
summary(fit)
And I expect to get some error message from R, because "y" is constant.
But, I got the message as below:
> summary(fit)
Call:
lm(formula = log(y) ~ x)
Residuals:
Min 1
Duncan,
Thank you for your reply. I was not clear about the Internet access. I do
have access, just at times I don't, hence the need to produce the manuals from
latex rather than simply using the Internet.
Please pardon my lack of knowledge around your response. You said I'd have to
inst
Hi,
I wrote a small patch to make it possible to get colored output from R
running in a Linux terminal emulator. It's a dirty patch. I hope that
someone with better knowledge of R source code and C programming will
improve it. To force the use of Rstd_WriteConsoleEx function
(src/unix/sys-std.c) I
Thanks, Dennis. Yes, I can do that, but that locks the physical units
to locations of the labels. I had hoped that there might be something a
bit more flexible, like a subtitle or more general text.
Carlisle
On 11/14/11 6:03 PM, Dennis Murphy wrote:
You don't show code or a reproducible exam
To use the gauss.quad function: gauss.quad(n,type) which returns two lists
$nodes and $weights whose length will each equal n. I'd like to do this for
n=1 to 40 (type will not change) and have a dataset with 40 rows and 81
columns with all the nodes and weights. The first record would have N1 a
Hi, Marc,
Thank you very much for the reply. I'm using the gsDesign function to create an
object of type gsDesign. But the inputs do not include the 'ratio' argument.
Dongli
On Nov 14, 2011, at 5:50 PM, Marc Schwartz wrote:
> On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote:
>
>> I'm trying t
Hi R users,
I end up with a list object after running an anova:
> lm(speed ~ 1 + dist + speed:dist, data = cars) -> Int
> lm(speed ~ 1 + dist, data = cars) -> NoInt
> anova(Int, NoInt) -> test
> test <- test[c("Df", "F", "Pr(>F)")][2,]
> is.list(test)
[1] TRUE
> test
Df FPr(>F)
2 -1 18
On Mon, Nov 14, 2011 at 9:44 PM, Tyler Rinker wrote:
>
> R Community,
>
> I often am in need of viewing the reference manuals of packages and do not
> have Internet access. I have used the code:
>
> path <- find.package('tm')
> system(paste(shQuote(file.path(R.home("bin"), "R")),"CMD",
> "Rd2pd
On 11-11-14 9:44 PM, Tyler Rinker wrote:
R Community,
I often am in need of viewing the reference manuals of packages and do not have
Internet access. I have used the code:
path<- find.package('tm')
system(paste(shQuote(file.path(R.home("bin"), "R")),"CMD",
"Rd2pdf",shQuote(path)))
someone
R Community,
I often am in need of viewing the reference manuals of packages and do not have
Internet access. I have used the code:
path <- find.package('tm')
system(paste(shQuote(file.path(R.home("bin"), "R")),"CMD",
"Rd2pdf",shQuote(path)))
someone kindly provided from this help list to
Actually, Interval Analysis can be used to find _all_ optima (including the
global optimum) within a starting box. It's not particularly well-known in
statistical circles.
See this (for example):
http://bib.tiera.ru/ShiZ/math/other/Global%20Optimization%20Using%20Interval%20Analysis%20-%20E.%20H
Hi,
I am working with the following list of files:
[1] "study_chr1.one.phased.impute2.chunk1"
[2] "study_chr1.one.phased.impute2.chunk1_info"
[3] "study_chr1.one.phased.impute2.chunk1_info_by_sample"
[4] "study_chr1.one.phased.impute2.chunk1_summary"
[5] "study_ch
I often use Lyx/Sweave and I typically write in english.
Today I had to write a document in Italian and, as many of you know,
many italian popular words use è, ù, é. ò, etc.
I discovered that if I type in Italian (that is there is at least one
letter with accent) with the Sweave module selected
Hi,
On Mon, Nov 14, 2011 at 7:59 PM, Debs Majumdar wrote:
> Hi,
>
> I am working with the following list of files:
>
> [1] "study_chr1.one.phased.impute2.chunk1"
> [2] "study_chr1.one.phased.impute2.chunk1_info"
> [3] "study_chr1.one.phased.impute2.chunk1_info_by_sample"
> [4] "study_chr1.one.ph
On 14/11/2011 5:42 PM, Cem Girit wrote:
Hello all,
I received many emails to my post on this issue. None of the answers
were able to resolve all the issues experienced by many but helped me to
understand the issues. . But consıderıng the avaılable OSs to install on,
many packages to inst
You haven't really said much about your overall project, but if you
are subsetting by time, it seems like you might want to use the xts
time series class. It implements ISO8601 for quick subsetting, which
seems perfect for what you are doing.
Here's a made up example:
X = xts(cumsum(rnorm(1e4)),
On Tue, 15 Nov 2011, Andrej Kastrin wrote:
I try to install the latest R version using checkinstall (v. 1.6.2) on Ubuntu
11.10.
mkdir: cannot create directory `/usr/local/share/man': No such file or
directory
Andrej,
This usually means that you don't have write permissions for that
direc
Dear all,
I try to install the latest R version using checkinstall (v. 1.6.2) on
Ubuntu 11.10. After solving all the dependencies (installed using
apt-get build-dep r-base) checkinstall fails to build and install R
package with the following error (the same commands build and install
R-2.13.2
You don't show code or a reproducible example, so I guess you want a
general answer. Use the draw.colorkey() function inside the
levelplot() call. It takes an argument key =, which accepts a list of
arguments, including space, col, at, labels, tick.number, width and
height (see p. 155 of the Lattic
On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote:
> I'm trying to use gsDesign for a noninferiority trial with binary
> endpoint. Did anyone know how to specify the trial with different sample
> sizes for two treatment groups? Thanks in advance!
Hi,
Presuming that you are using the nBinomial() fu
Hello all,
I received many emails to my post on this issue. None of the answers
were able to resolve all the issues experienced by many but helped me to
understand the issues. . But consıderıng the avaılable OSs to install on,
many packages to install, and the fact that R is a product of o
Hi All-
I have created a subset of my original csv for the times I am interested in
(9, 12, 3). I have a subset for all of those times then each individually. I
would like to have specific case studies to analyze individually for those
times. For example, I want to look at 2009/06/01-2009/06/10. I
Thanks Joshua for your prompt reply, and my apologies for my much delayed one.
I've only just been able to come back to this.
I need the epicalc package for the pyramid function, and so it seems I do have
to load the package.
I've contacted the package maintainer but in the meantime I've taken
I'm trying to use gsDesign for a noninferiority trial with binary
endpoint. Did anyone know how to specify the trial with different sample
sizes for two treatment groups? Thanks in advance!
[[alternative HTML version deleted]]
__
R-help@r-proje
Just to provide some closure:
I ended up dividing the IV by its max so that the input vector (IV) is
now between zero and one. I still used optim:
myopt <- optim(fn=myfunc, par=c(1,1), method="L-BFGS-B", lower=c(0,0))
I was able to get great fit, in 3 cases out of 10 I've beaten Excel
Solver, but
Thanks Michael,
But I can't see the dates on the NEWS so I have no idea what changed from
last version or from whichever version we actually have installed. Do you
see what I mean?
Thanks,
Xu
--
View this message in context:
http://r.789695.n4.nabble.com/changelog-for-MASS-tp4034473p4040941.ht
Haven't followed this thread, but...
1) IF you are on WIndows and
2) IF you like to open R and load .Rdata files by double clicking on the
files
THEN
if you right click on the file, the "Open With" dialog allows you to browse
to_particular_ RGui (presumably the latest) you wish to use and there i
On 14.11.2011 22:42, Gene Leynes wrote:
I have had similar problems.
I have several installations of R and now I have no control over which one
opens when I try opening a RData file. The RGUI is registered more than
once, but they all have the exact same appearance in the "choose programs"
menu
So far in 2011 JSS has published 4 (four !) special volumes. If you have
additional suggestions for special
volumes, let us know. Also, submit your JSS-adapted package vignettes.
If you like what you see, friend us at
http://www.facebook.com/jstatsoft
Tabelow and Whitcher, Guest Editors
Volu
I have had similar problems.
I have several installations of R and now I have no control over which one
opens when I try opening a RData file. The RGUI is registered more than
once, but they all have the exact same appearance in the "choose programs"
menu.
It's become particularly annoying now t
There is a difference between parsed functions and .R files. What you see when
you type the name of a function alone on the R command line is a text
representation of the parsed function that is ready to run in RAM. That has
none of the comments or whitespace from the function as you wrote it.
May I suggest you consult your local statistician. For reasons that (s)he
can answer, your request makes little sense.
Hint: Nonlinear regression is much different than linear regression: The
design matrix -- and hence the variance of estimators -- is a function of
the parameters being estimated.
Groupwise data summarization is a very common task, and it is worth
learning the various ways to do it in R. Josh showed you one way to
use aggregate() from the base package and Michael showed you one way
of using the plyr package to do the same; another way would be
ddply(df, .(Patient, Region),
How to add units (e.g. "cm") to the color key of a lattice levelplot?
The plots looks fantastic, but it would be nice to indicate somewhere
near the end of the color key that the values associated with its colors
are in centimeters or some other physical units.
The only thing I find is the po
hello all R experts,
> how do I calculate the reliability between the two groups
> using the ICCs?
--
Sincerely,
Supreet kaur,
Biomedical research engineer,
Nationwide Childrens Hospital,
Columbus, OH
(614)355-3509
[[alternative HTML version deleted]]
__
If you don't want to go with the simple method mentioned by David and Ted, or
you just want some more theory, you can check out:
http://en.wikipedia.org/wiki/Fisher%E2%80%93Yates_shuffle and implement that.
--
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.s.
Since installing R 2.14.0 on my Mac (a Mac Pro running 10.6.8) an issue has
arisen when using the vi editor in conjunction with the edit() command. More
specifically, commented lines disappear from edited functions when using
[functionname.R] <- edit().
That is, if you have created a function c
Path manager has a nice feature. Thanks. While I can see that rcmd is in
the path setting, it is still not recognized as an internal command. That
is something really confuses me.
Jixiang Wu
On Mon, Nov 14, 2011 at 11:30 AM, Henrik Bengtsson wrote:
> FYI,
>
> you can use tools such as Path Mana
See R Windows FAQ 2.6
On Monday, 14 November 2011, R. Michael Weylandt
wrote:
> I haven't personally used it, but I think this might work:
> http://sourceforge.net/projects/rportable/
>
> Michael
>
> 2011/11/14 Francisca Soares dos Santos :
>> Hello,
>>
>> I would like to get help on the instala
Is there a library that provides power calculation and sample size
estimation for nonlinear regression?
The task is easy for linear regression with the "pwr" package, but I
can't find a method for nonlinear regression (estimated with the "nls"
package).
-- -- -- -- -- -- -- -- -- -- -- -- -
Do it in 2 steps:
z <- as.list( coef(am)[1:am$arma[2] + am$arma[1]])
names(z) <- paste("ma",seq_along(z), sep="")
-- Bert
On Mon, Nov 14, 2011 at 10:40 AM, Kevin Burton wrote:
> I can get an array of strings for the data that I want using 'paste()' as
> follows:
>
>
>
> paste('ma', 1:am$arma[2]
The one included in the standard R installation -- which can be
accessed by typing help.start() at your prompt -- is quite good for
beginners (and very conveniently located). If you tell us a bit more
about yourself, we can help direct you to others as well:
specifically,
1) Prior programming expe
I haven't personally used it, but I think this might work:
http://sourceforge.net/projects/rportable/
Michael
2011/11/14 Francisca Soares dos Santos :
> Hello,
>
> I would like to get help on the instalation of R.
> I have too few free space in my pc hard disk. So I wonder if it is possible
> to
I can get an array of strings for the data that I want using 'paste()' as
follows:
paste('ma', 1:am$arma[2], '=', coef(am)[1:am$arma[2] + am$arma[1]], sep='')
This results in a vector of strings like:
[1] "ma1=1.17760133668255" "ma2=0.649795570407939" "ma3=0.329456750858276"
What I
Hello,
I would like to get help on the instalation of R.
I have too few free space in my pc hard disk. So I wonder if it is possible
to install R on an external removable hard drive.
Can it be done? How should I proceed?
Thank you for your help.
best regards,
Francisca A. S. dos Santos Bronner
http://r.789695.n4.nabble.com/file/n4040429/model.jpg
Hi All
I need some help about construct MLE logit for Binary Autogressive Moving
Average model.
Please see the model in the PDF attach file.
This is what i did.
y<-c(0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1) # y
is
Thank you all!
It's working perfectly. I will have a look for an online guide.
--
View this message in context:
http://r.789695.n4.nabble.com/Very-simple-loop-tp4039895p4040291.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r
Hi,
Thanks for the help.
I have now sorted out the issue.
Somehow the text "C:\Progra~1\R\R-2.14.0\bin\x64\R" had got added to the end of
an environment variable called "comspec".
Removing the extraneous text solved the problem - so the only mystery now is
how I managed to paste the text into
On Nov 14, 2011, at 1:16 PM, Chris82 wrote:
Dear R users,
Is it possible to plot 2 different fields with image.plot().
There is an add parameter described on the helop page. Have you tried?
For example at first a digitale elevation model and overlying
another data
field, where NA values
Hi Martyn,
I would not expect you to need directories besides Rversion\bin\x64.
That is all I normally have in my path...perhaps because I do a
complete install?
I do not really know how or why it works, so I do not have any great
insight---just my experience. Perhaps someone else will chime in
Dear R users,
Is it possible to plot 2 different fields with image.plot().
For example at first a digitale elevation model and overlying another data
field, where NA values are transparent, so that the digitale elevation model
is still visble at this areas.
Maybe there is another plotting optio
See if
Rcmd check --help
works.
I've always been use that form (I'm on Win7 64-bit).
/Henrik
On Mon, Nov 14, 2011 at 9:06 AM, Martyn Byng wrote:
> Hi Josh,
>
> Thanks for that, which directory needs to be in the path?
>
> There is a file called R.exe in
>
> C:\Program Files\R\R-2.14.0\bin
>
FYI,
you can use tools such as Path Manager 1.1.1 (GPL) on Windows:
http://www.softpedia.com/get/System/System-Miscellaneous/Path-Manager.shtml
to list, modify (add, remove, reorder, remove duplicates, normalize)
your PATH environment variable. For each directory it identifies in
PATH it will
Dear David,
You do not need a loop. The vectors are equaly sized, so sum them and then
plot the vector with the sums:
total <- A+B+C+D+E+F+G
plot (total, type="l")
Regards,
Emilio
2011/11/14 Davg
> I'm very new to R and am trying to create my first loop.
>
> I have:
>
> x <-c(0:200)
> A <- dpo
Bert,
I think there is a misunderstanding here.
Some data is censored, but I want to fit the data with a distribution
in the interval [0,24] only. Also, please note that I have other
datasets having values larger than 1000.
Cheers,
Michele
On 14 Nov 2011, at 18:28, Bert Gunter wrote:
A n
Hi Josh,
Thanks for that, which directory needs to be in the path?
There is a file called R.exe in
C:\Program Files\R\R-2.14.0\bin
C:\Program Files\R\R-2.14.0\bin\x64
and
C:\Program Files\R\R-2.14.0\bin\i386
I currently have
C:\Program Files\R\R-2.14.0\bin\x64
in the path (which is, I'm gues
On Nov 14, 2011, at 4:20 AM, Michael Griffiths wrote:
Good morning R list,
My apologies if this has *already* answered elsewhere, but I have
not found
the answer that I am looking for.
I have a character string, i.e.
form<-c('~ A + B + C + C / D + E + E / F + G + H + I + J + K + L * M')
Hi Martyn,
My guess is that you need to add the directory where R is located to
your Windows PATH variable. It sounds like Windows just doesn't know
where to find R.
HTH,
Josh
On Mon, Nov 14, 2011 at 8:48 AM, Martyn Byng wrote:
> Hi,
>
> I've just downloaded and installed R 2.14.0 using the w
Hi,
I've just downloaded and installed R 2.14.0 using the windows binary on
a 64bit windows machine running windows 7.
Rterm / RGui work as expected, as does
R CMD --help
and
R CMD BATCH --help
however
R CMD check --help
returns no information and I seem to be unable to check a package.
Va
I took a stab at this using ddply() from the plyr package. How's this
look to you?
x<- textConnection("Col Patient Region Score Time
11 X19 28
21 X20 126
31 X22 100
41 X25 191
52 Y121
62 Y
But the awesome thing is you don't need a for loop at all thanks to
the magic of R's vectorization!
This will do it (and much faster than an R level loop would):
x = 0:200 # Note that you don't need a c() since you aren't
concatenating 0:200 with anything
A <- dpois(x,exp(4.5355343))
B <- dpois(x
x <-c(0:200)
dat <- data.frame(
A = dpois(x,exp(4.5355343)),
B = dpois(x,exp(4.5355343 + 0.0118638)),
C = dpois(x,exp(4.5355343 -0.0234615)),
D = dpois(x,exp(4.5355343 + 0.0316557)),
E = dpois(x,exp(4.5355343 + 0.0004716)),
F = dpois(x,exp(4.5355343 + 0.056437)),
G = dpois(x,exp(4.53
x <-c(0:200)
A <- dpois(x,exp(4.5355343))
B <- dpois(x,exp(4.5355343 + 0.0118638))
C <- dpois(x,exp(4.5355343 -0.0234615))
D <- dpois(x,exp(4.5355343 + 0.0316557))
E <- dpois(x,exp(4.5355343 + 0.0004716))
F <- dpois(x,exp(4.5355343 + 0.056437))
G <- dpois(x,exp(4.5355343 + 0.1225822))
total <- A +
Hi,
On Mon, Nov 14, 2011 at 10:59 AM, Davg wrote:
> I'm very new to R and am trying to create my first loop.
>
> I have:
>
> x <-c(0:200)
> A <- dpois(x,exp(4.5355343))
> B <- dpois(x,exp(4.5355343 + 0.0118638))
> C <- dpois(x,exp(4.5355343 -0.0234615))
> D <- dpois(x,exp(4.5355343 + 0.0316557))
Hello,
I am using a grid.layout for combining multiple ggplot-plots.
So far I am doing it this way to get a pdf/eps:
pdf("/path/to/my/file.pdf") #or postscript("/path/to/my/file.eps")
grid.newpage()
pushViewport(viewport(layout = grid.layout(nrow=2, ncol=2,
widths = unit(c
I'm very new to R and am trying to create my first loop.
I have:
x <-c(0:200)
A <- dpois(x,exp(4.5355343))
B <- dpois(x,exp(4.5355343 + 0.0118638))
C <- dpois(x,exp(4.5355343 -0.0234615))
D <- dpois(x,exp(4.5355343 + 0.0316557))
E <- dpois(x,exp(4.5355343 + 0.0004716))
F <- dpois(x,exp(4.5355343
Hi Laura,
You were close. Just use range() instead of min/max:
## your data (read in and then pasted the output of dput() to make it easy)
dat <- structure(list(Patient = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 6L,
A non-helpful reply on a "language" issue.
"Truncated" data are quite different than "censored" data and require
different methodologies to analyze. You -- and many others in their
postings -- have appeared to confuse the two here.
-- Bert
On Mon, Nov 14, 2011 at 8:20 AM, Michele Mazzucco wro
David,
here is the smallest dataset
# Bid Price SurvivalCensored
0.030.029 1 1
0.030.029 11 1
0.030.029 10 1
0.030.029 9 1
0.030.029 8 1
0.030.029 7 1
0.030.029 6 1
0.030.029 5 1
0.030.02
I am sorry to ask this group but the maintainer of this package did not
leave an email address.
Has anyone used or is using the 'rugarch' package with time-series data
(ts)? I try to fit a GARCH model to my data using the following:
> gf <- ugarchfit(data=l[["MEN"]]$series, spec=spec)
Hi Laura,
This looks suspiciously like homework. Nonetheless, you may wish to
check out ?cbind.
Sarah
On Mon, Nov 14, 2011 at 11:10 AM, B Laura wrote:
> dear R-team
>
> I need to find the min, max values for each patient from dataset and keep
> the output of it as a dataframe with the following
I am also using statConn so I will let you know if I hear anything new.
-Original Message-
From: Cem Girit [mailto:gi...@comcast.net]
Sent: Monday, November 14, 2011 8:52 AM
To: 'Kevin Burton'
Cc: r-help@r-project.org
Subject: RE: [R] Upgrade R?
Hello Kevin,
Thank you. I will de
dear R-team
I need to find the min, max values for each patient from dataset and keep
the output of it as a dataframe with the following columns
- Patient nr
- Region (remains same per patient)
- Min score
- Max score
Patient Region Score Time
11 X19 28
21
On Nov 14, 2011, at 6:11 AM, Michele Mazzucco wrote:
Hello David,
thanks for your answer.
I have done as you told me, however the fit is very poor, much worse
than that obtained from using the whole dataset (without upper bound).
Any idea?
Counter questions in the absence of data:
??? Is
This caught me learning R, and no doubt thousands of others.
When would one ever want the results of fitted() or residuals() to NOT match
the data frame rows which went into the model? Certainly making shrinking the
results the default is not what 99% of user will want if they need to access
1. Post this on the R-sig-mixed-models list, not here.
2. (The following "advice" should be treated cautiously): Forget it! With
only 5 bats, you have too little information to estimate variance
components. Treat the bats as fixed effects and fit via lm (or glm if some
of your responses are not ga
If you want fitted() to return NAs in the positions where
there were NA's in data, use na.action=na.exclude in your
call to lm(). E.g.,
> z <- data.frame(y=1:5, x=c(1,NA,3,3,5))
> fitted(lm(y~x, data=z))
1345
1.25 3.25 3.25 5.25
> fitted(lm(y~x, data=z, na.action=na.exc
Hi,
On Mon, Nov 14, 2011 at 8:54 AM, Michael Griffiths
wrote:
> Thank you Sarah,
>
> Your reply was very helpful. I have the added difficulty that I am not only
> dealing with single A-Z characters, but quite often have the following
> situation:
>
> form<-c('~Sentence+LEGAL+Intro+Intro/Intro1+In
Dear all,
I am working on a 64 bits Linux system.
I issue the following R commands:
> rm(list=ls()) # To remove all objects in the workspace.
> gc() # To free memory.
used (Mb) gc trigger (Mb) max used (Mb)
Ncells 124250 6.7 35 18.7 35 18.7
Vcells 124547 1.0 786432 6.0 476934 3.7
> gc(
Dear all,
I have the following dataset with results from an experiment with individual
bats that performed two tasks related to prey capture under different
conditions:
X variables:
indiv - 5 individual bats used in the experiment; all of which performed both
tasks
task - 2 tasks that each ind
Hello Kevin,
Thank you. I will delete the folder and run an application called
CCleaner (free). That will remove all the broken registry entries.
There should be a problem free update path for R installation. As
you rightfully mentioned the R- manual is not clear about package upd
Hi
r-help-boun...@r-project.org napsal dne 14.11.2011 14:54:05:
> Thank you Sarah,
>
> Your reply was very helpful. I have the added difficulty that I am not
only
> dealing with single A-Z characters, but quite often have the following
> situation:
>
> form<-c('~Sentence+LEGAL+Intro+Intro/Intr
Glad it worked! The one "gotcha" is that it does not handle missing
values, so for example:
> cumsum(c(1, 2, 3, NA, 4))
[1] 1 3 6 NA NA
both the NA, and everything after it become NA (missing). If you find
yourself working with tables and frequencies and the like, you may
also like (if you h
You need to explicitly pass th to your function with the ... argument
of integrate.
E <- function(th){
integrate(function(x,th) x*g(x, th), 0, Inf, th)$value
}
Also, it's value, not Value, which might be producing errors of another sort.
Michael
On Mon, Nov 14, 2011 at 9:16 AM, Gerrit Drais
Hello.
I just installed R 2.14.0 and then did
> install.packages("splm", repos="http://R-Forge.R-project.org";)
in order to replicate your problem.
It worked "almost" fine. The only problem I had was with some missing
packages: being a fresh install, all suggested and required packages had
to b
Thank you Sarah,
Your reply was very helpful. I have the added difficulty that I am not only
dealing with single A-Z characters, but quite often have the following
situation:
form<-c('~Sentence+LEGAL+Intro+Intro/Intro1+Intro*LEGAL+benefit+benefit/benefit1+product+action+mean+CTA*help')
and again
Try this:
EV <- function(lamb){
fnc <- function(x) x * dexp(x, lamb)
integrate(fnc, 0, Inf)$value
}
Your problem is that there's nothing to translate th to lambda in your
code for E.
Michael
On Mon, Nov 14, 2011 at 5:32 AM, Gerrit Draisma wrote:
> Hallo,
> I am trying to define expec
David's answers were correct. You are looking deep into the code when
there is no reason to to so.
1. h(t|(X=x,Z=z)) = exp(Beta0 + XZBeta1)
Most statisticians will tell you that this is an unwise model. The
reason is that if you replace X with "X+1" the fit changes, which is
almost never desira
1 - 100 of 140 matches
Mail list logo
