Hi all
i know this is probably a silly question but im wondering what is the
'reference' category when you run a binomal glm. that is my outcome/DV is
0,1 and i run a regression and get coefficients. do the coefficients refer
to the probability to get 0 or 1?
thanks so much in advance
Z
Dear David,
Thank you very much for you help, I really appreciate it.
I am not using the read.snps.long() or any other import function, as the
data is already in snpMatrix, so I cannot specify it at the input stepâ¦
I am reading the data as a snpMatrix, so using load() after having called
the
Dear R User,
I was wondering how I can unstack my data. For example I have following data set
data-structure(list(siteS = structure(c(3L, 3L, 3L, 4L, 4L, 5L, 5L,
5L, 5L, 5L, 1L, 1L, 1L, 2L), .Label = c(11a, 12d, 1a, 2v,
6a), class = factor), species = structure(c(1L, 2L, 3L, 1L,
4L, 1L, 4L,
Dear Sir/Madam,
It is possible to make grouped bar plots via barplot. But I want to add a
break in y axis for data that largely differs. However, this seems
complicated. Although gap.barplot may add a break in y asis, but the bars
are not grouped as I wanted. Could you help me with this
Hi Arun,
Thank you for your help, I have a few questions though if you don't mind.
I'm a bit confused about the following 2 lines of code:
col.tri.nb - tri2nb(coords, row.names=ind)
lapply(col.tri.nb,function(x) ind[x])[1:5]
## from what I understand in the first line determines the
On May 27, 2014, at 3:51 AM, Xebar Saram zelt...@gmail.com wrote:
Hi all
i know this is probably a silly question but im wondering what is the
'reference' category when you run a binomal glm. that is my outcome/DV is
0,1 and i run a regression and get coefficients. do the coefficients
On 27/05/2014 09:51, Xebar Saram wrote:
Hi all
i know this is probably a silly question but im wondering what is the
'reference' category when you run a binomal glm. that is my outcome/DV is
0,1 and i run a regression and get coefficients. do the coefficients refer
to the probability to get 0
Hi Kristi
It doesn't seem that unstack can do it for you. Here is one way:
library(reshape)
data.molten - melt(data, id = c(siteS, species))
cast(data.molten, siteS ~ species)
siteS sa sb sc sd se sg
1 11a 11 NA 37 NA NA 51
2 12d 15 NA NA NA NA NA
31a 31 55 62 NA NA NA
42v 42 NA
Hi Barnaby,
No problem.
If the function got masked by loading another package, you could do:
wt.aligned - wavelets::align(wt)
A.K.
Thank you
I spend more time looking into it since I placed the question and it seems that
there is a conflict between two or more packages when open jointly
On Tue, 27 May 2014 11:36:21 AM Wei Qin wrote:
...
#Then my questions is how to make a broken y axis in grouped
barplot
figures?
# In another words, how to combine the function of barplot and
gap.barplot?
Hi Wei,
The gap.barplot function doesn't do grouped bars (yet). You can probably
Jane,
Page 9 of the reference manual,
http://cran.r-project.org/web/packages/plotmo/plotmo.pdf, discusses this
error.
'The work-around is to simplify or standardize the way the model function
is called. Use a formula and a data frame, or at least explicitly name the
variables rather than passing
Hi all,
I thought it was all over, but when I started my R help (help.start()) to
check something, none of the help files in plotrix were available, each
displaying an error message that some 2-3 Gb of memory could not be
allocated. The same message appeared when I tried to get text help in
Jinsong,
When I use your code to create the abcd.emf file, and then copy and paste
it into Word, I end up with a 4 x 4 plot with 12 pt font, just as you
intended. I'm using R version 3.1.0, and Word 2010 version 14.0.7116.5000.
Not sure why it works differently for you.
Jean
On Mon, May 26,
Hi Praveen,
Try this:
dat - read.table(text=INCOME
20100
26800
5
18,sep=,header=TRUE)
transform(dat,
INCOME_RANGE=as.character(cut(INCOME,breaks=c(0,25,50,100,150,180,Inf)*1e3,right=FALSE,labels=c(below
25,000, 25,000-49,999.99, 50,000-99,999.99, 1,00,000-1,49,999.99,
On Tue, 27 May 2014 14:01:56 +1000 Jim Lemon j...@bitwrit.com.au wrote:
On Mon, 26 May 2014 09:43:45 AM Ranjan Maitra wrote:
...
Though, I have to say I don't quite see how you managed to install R
without the above package (it is a required dependency on Fedora).
...
Hope the above
Thank you both for your kinds help
best
z.
On Tue, May 27, 2014 at 2:25 PM, Prof Brian Ripley rip...@stats.ox.ac.ukwrote:
On 27/05/2014 09:51, Xebar Saram wrote:
Hi all
i know this is probably a silly question but im wondering what is the
'reference' category when you run a binomal glm.
Dear Kehl and Greg,
Many thanks for your advice. I got it.
Best wishes,
Helen
On 23 May 2014 22:45, Kehl Dániel ke...@ktk.pte.hu wrote:
Hi,
the function is in the plotrix package, so you have to install and call
that package first.
After installing see example(addtable2plot).
HTH,
Dear all,
how can I install the Windows/R package
http://www.ssg.uab.edu/bhglm/files/BhGLM_1.0.zip
under Linux/R?
There is no CRAN package.
Simply, applying gunzip, tar -czvf, R CMD INSTALL *.tar.gz did not work.
Thanks in advance,
Will
Hi Monaly,
According to the description of ?tri2nb
The function uses the ‘deldir’ package to convert a matrix of
two-dimensional coordinates into a neighbours list of class ‘nb’
with a list of integer vectors containing neighbour region number
ids.
So, col.tri.nb is a list of
It may not be possible. Contact the maintainer described at
http://www.ssg.uab.edu/bhglm/ to ask for a source package.
---
Jeff NewmillerThe . . Go Live...
Hi,
I guess ?cast should work on the original dataset as it is in the long format
cast(data, siteS ~ species,value=abundance)
siteS sa sb sc sd se sg
1 11a 11 NA 37 NA NA 51
2 12d 15 NA NA NA NA NA
3 1a 31 55 62 NA NA NA
4 2v 42 NA NA 40 NA NA
5 6a 30 23 74 84 10 NA
#if you are
Hi Barry,
I don't think pam has a way to predict for test observations. However, this
questions was asked and answered earlier.
The approach is to take the medoids generated in pam and use them in a K-nn
algorithm as the training data with K = 1. This way, you can classify your
testing data by
Dear R help,
I cannot login to my account. I am keen to remove the posting I made to R
help from google web searches - see
http://r.789695.n4.nabble.com/R-software-installation-problem-td4659556.html
Thanks,
Andy
Dr Andy Siddaway
Registered Clinical Psychologist/
MRC Clinical Research
Hallo,
i try to draw a plot (plot.zoo) with a secondary y-axis.
Further I want to draw reference lines.
Unfortunately I do not manage to get control on the ticks, so that the
reference lines match both- primary and secondary y-axis.
Maybe someone already solved this problem??
It would be great.
Hi
cast(data, siteS~species)
gives you quite close result, only row ordering is different
Regards
Petr
-Original Message-
From: r-help-boun...@r-project.org [mailto:r-help-bounces@r-
project.org] On Behalf Of Kristi Glover
Sent: Tuesday, May 27, 2014 12:54 PM
To: R-help
Subject:
Dear R-listers,
I am using R 3.1, I amtrying to generate 40 patients in each treatment group
with 12 block, Equal number of treatment in each block ,using stratification
Variable age65(yes, no),surgery(yes ,no) and smoke (yes, no)
How can i creat like thislist in R.
block identifier
Dear Jim,
Thank you very much indeed for your quick reply and kind help.
The code you provided works perfectly, which is exactly what I want.
Kind regards,
Wei
On 27 May 2014 14:11, Jim Lemon j...@bitwrit.com.au wrote:
On Tue, 27 May 2014 11:36:21 AM Wei Qin wrote:
...
#Then my questions
Jean,
Thank you for checking the problem. I have the same software with you.
If I created plot with
windows(width = 4, height = 4, pointsize = 10)
plot(1:10)
Then I copy as metafile and paste it into Word. I can get the correct
size.
However, if I select save as metafile and save it as
Dear all,
I would like to know how to plot the results of a regression where various
predictors resulted significant. Further, I would like how to add the
regression line. Is that possible?
For instance, I have run POLS=plm() where 6 coefficients resulted
significant; then I would like to use
On May 27, 2014, at 4:46 AM, Andy Siddaway andysidda...@googlemail.com wrote:
Dear R help,
I cannot login to my account. I am keen to remove the posting I made to R
help from google web searches - see
http://r.789695.n4.nabble.com/R-software-installation-problem-td4659556.html
Thanks,
On Tue, May 27, 2014 at 8:02 AM, Bastian Pöschl bstan0...@gmail.com wrote:
Hallo,
i try to draw a plot (plot.zoo) with a secondary y-axis.
Further I want to draw reference lines.
Unfortunately I do not manage to get control on the ticks, so that the
reference lines match both- primary and
Thanks David,
I try and I wish I could benefit.
Sorry I'm too stupid to learn much the documentation.
There is so much of it and its interrelations not
easily determined and I can't figure out where to look.
It's hard to understand, but I try.
Hard for my friends too.
Now I have a quite nice
What does Word think the object's size is? Is it 4x4 scaled at 133% ? Or is
it 5.33 x 5.33 scaled at 100%?
B.
On May 27, 2014, at 12:28, Jinsong Zhao jsz...@yeah.net wrote:
Jean,
Thank you for checking the problem. I have the same software with you.
If I created plot with
On 2014/5/27 10:32, Boris Steipe wrote:
What does Word think the object's size is? Is it 4x4 scaled at 133% ? Or is
it 5.33 x 5.33 scaled at 100%?
B.
Thanks for pointing me the scaling factor.
I checked them. For the plot pasted into Word, i.e., 4x4, the plot is
scaled at 75%. The original
Well, the short answer is don't do that (resize after the fact). Resize your
graphic window first and then re-tune your annotations for that size.
The longer answer is that the lattice and ggplot2 packages were developed in
part in response to the limitations of base graphics. They don't
I thought so. The behaviour differs when inserting and pasting. See:
http://support.microsoft.com/kb/926317
Googling for how to turn this autoscaling nonsense off did not yield an obvious
result. This probably means that you'll need to adjust your workflow instead,
e.g. by increasing the
On 2014/5/27 11:06, Boris Steipe wrote:
I thought so. The behaviour differs when inserting and pasting. See:
http://support.microsoft.com/kb/926317
Googling for how to turn this autoscaling nonsense off did not yield an
obvious result. This probably means that you'll need to adjust your
Hi,
Please post in plain text and show the example using ?dput.
Assuming that you wanted a data.frame and not a list
May be this helps:
set.seed(428)
dat1 - data.frame(`block identifier`=rep(1:40,each=12),`block
size`=12,`sequence within block`=rep(1:12,40), treatment=sample(paste(Group,
Hello,
I have a big dataframe, and want to average two specific cells of two
specific rows and then replace those two rows with one row which contains
the averaged cells. Example (row 3 and 4: Cells2 and Cells3 averaged and
replaced)
NameC1 C2 C3
1 A 3 3 5
2 B 2 7 4
3 C 4 3
Look at the aggregate function. As long as you have a column like
Name that indicates which rows should be averaged together it will
work (technically it will average the other rows as well, but since
the average of 1 number is that number you will not see a difference).
On Tue, May 27, 2014 at
Hello,
Try the following.
dat - read.table(text =
Name C1 C2 C3
1 A 3 3 5
2 B 2 7 4
3 C 4 3 3
4 C 4 4 6
5 D 5 5 3
, header = TRUE)
str(dat)
aggregate(dat[, -1], list(dat$Name), mean)
Hope this helps,
Rui Barradas
Em 27-05-2014 21:06, Verena Weinbir escreveu:
Hi,
I am running beta mixture regressions using the betamix() command from the
package 'betareg' (3.0-4). I In order to inform the choice about the number
of latent classes I took a look at the various information criteria (AIC,
BIC, ICL) and learnt that the integrated completed likelihood (ICL)
On 28/05/14 01:28, will.ea...@gmx.net wrote:
Dear all,
how can I install the Windows/R package
http://www.ssg.uab.edu/bhglm/files/BhGLM_1.0.zip
under Linux/R?
There is no CRAN package.
Simply, applying gunzip, tar -czvf, R CMD INSTALL *.tar.gz did not work.
Don't
On 28/05/14 00:48, Jim Lemon wrote:
Hi all,
I thought it was all over, but when I started my R help (help.start()) to
check something, none of the help files in plotrix were available, each
displaying an error message that some 2-3 Gb of memory could not be
allocated. The same message appeared
Dear R family,
I have this matrix say
AAA-matrix(sample(1:240),ncol=2)
I first want to combine every 13th row in both columns. precisely, starting
from row-1 1,13,25,37,49, then starting from row-2
2,14,26,38,50 also 3,15,27,39,51 and similarly starting from row 4, row number
5, row 6...
On May 27, 2014, at 1:51 AM, Xebar Saram wrote:
Hi all
i know this is probably a silly question but im wondering what is the
'reference' category when you run a binomal glm. that is my outcome/DV is
0,1 and i run a regression and get coefficients. do the coefficients refer
to the
On May 27, 2014, at 3:54 AM, Kristi Glover wrote:
data-structure(list(siteS = structure(c(3L, 3L, 3L, 4L, 4L, 5L, 5L,
5L, 5L, 5L, 1L, 1L, 1L, 2L), .Label = c(11a, 12d, 1a, 2v,
6a), class = factor), species = structure(c(1L, 2L, 3L, 1L,
4L, 1L, 4L, 5L, 2L, 3L, 1L, 6L, 3L, 1L), .Label =
Hi Eliza,
May be this helps:
lapply(split(seq_len(nrow(AAA)),((seq_len(nrow(AAA))-1)%%12)+1),function(i)
AAA[i,])
A.K.
On Tuesday, May 27, 2014 6:48 PM, eliza botto eliza_bo...@hotmail.com wrote:
Dear R family,
I have this matrix say
AAA-matrix(sample(1:240),ncol=2)
I first want to combine
Forgot, about the mean:
lapply(split(seq_len(nrow(AAA)),((seq_len(nrow(AAA))-1)%%12)+1),function(i)
colMeans(AAA[i,]))
A.K.
On , arun smartpink...@yahoo.com wrote:
Hi Eliza,
May be this helps:
lapply(split(seq_len(nrow(AAA)),((seq_len(nrow(AAA))-1)%%12)+1),function(i)
AAA[i,])
A.K.
On
Hi,
You can also try:
dat - read.table(text=Name C1 C2 C3
1 A 3 3 5
2 B 2 7 4
3 C 4 3 3
4 C 4 4 6
5 D 5 5 3,sep=,header=TRUE,stringsAsFactors=FALSE)
library(plyr)
ddply(dat,.(Name),numcolwise(mean,na.rm=TRUE))
A.K.
On Tuesday, May 27, 2014 4:08 PM, Verena
Hola,
Si al final vas a usar rattle, realmente RStudio te va a aportar poco,
casi te dirÃa que tendrás más problemas a la hora de visualizar resultados.
Algunos aparecerán en la propia consola gráfica de rattle y otros en la de
RStudio...
Prueba directamente a arrancar rattle desde la
51 matches
Mail list logo