I have a matrix of p-values for for each explanatory variable. Each row is an
area of the response variable and each column is an explanatory variable.
e.g.
PSA pval_DOY pval_PDSIconcurrent pval_PDSIantecedent_annual_average
pval_TMAXanomaly pval_FM100anomaly
1 NC06 0.96747495 0.60
On 03/22/2012 05:42 AM, Alaios wrote:
Would it be possible to change the axis at the end?
My data sets seem to be quite large so I was thinking for the plot and
the consequent lines to keep always
the current minimum and maximum like
plot(x)
minimum=min(x)
lines(x1)
minimum=c(minimum,x1)
lines(x2
Hello,
I would like to produce a few time series graphs with R. My data is
usually quarterly or monthly. I sometimes need to have two y-axes, one at
the left, the other right. Is there any toolbox producing nice looking time
series graphs?
Thanks,
miao
[[alternative HTML version d
I haven't had time to try using R for over a year, but have a colleage who
wants to.
We work with time series and our current version of our calendar-time
subroutines in
java converts both directions between linear time and calendar.
We have used calendar time since year 1965 starting out then wi
Does anyone know how to read or import a wiff (AB SCIEX windows interchange
file format) extension into R? Thanks a lot.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-pro
Mike Williamson writes:
> Thanks Sarah, All,
>
> I guess I never thought of a negative sign as an "operation", but
> knowing that it is considered an operation explains everything nicely.
> Somewhere in it's underbelly, I suppose -4 is represented as "0 - 4"?
Not exactly. Here is the list o
Dear fellow R-users,
I’m using the Glm function (gamma family of distributions) from the rms
package to compare 2 groups on costs data. Although the summary function
does provide the mean cost difference and standard errors, I believe these
values were in the (natural) log ratio format. Is there
Hi!
I'm using GLM, LDA and NaiveBayes for binomial classification. My training
set is 70 rows long with 32 features, and my test set is 30 rows long with
32 features.
Using Naive Bayes, I can train a model, and then predict the test set with
it like so:
ass4q1.dLDA = lda(ass4q1.trainSet[,1]~ass4
I'm very new to R having recently made the transition from SPSS and SAS.
In a dataset named t4, I have about 20 variables that are named in a
somewhat chronological order - (e.g., q100ayr, q101ayr, q102ayr, q103ayr,
etc.)
Each variable contains a 2 digit year designation (e.g., 73
Thanks a lot,
I tried one of the ways you guys showed me and it totally work. Just for
fun, I tried all the others and with some modifications here and there they
work fine too. It was time consuming but definitely worth as a good learning
experience. Thanks again
--
View this message in context
Hi
I want to overlay my raster and its boundary which is a shapefile.
When I used thise code separately, all is ok:
# Open raster
>Image<-read.table("C:\\Users\\Documents\\Nouveau\\Frequence.txt",sep="",dec=",",header=TRUE)
>
>testo<-rasterFromXYZ(Image)
>plot(testo)
>testo2 <- aggregate
Dear fellow R-users,
I’m using the Glm function (gamma family of distributions) from the rms
package to compare 2 groups on costs data. Although the summary function
does provide the mean cost difference and standard errors, I believe these
values were in the (natural) log ratio format. Is there
On Wed, Mar 21, 2012 at 5:21 PM, Mike Williamson wrote:
> Thanks Sarah, All,
>
> I guess I never thought of a negative sign as an "operation", but
> knowing that it is considered an operation explains everything nicely.
> Somewhere in it's underbelly, I suppose -4 is represented as "0 - 4"?
S
Thanks Sarah, All,
I guess I never thought of a negative sign as an "operation", but
knowing that it is considered an operation explains everything nicely.
Somewhere in it's underbelly, I suppose -4 is represented as "0 - 4"?
Either way, I'm glad it is consistent & accurate, so that I didn't
On 22/03/12 12:17, Sarah Goslee wrote:
It's order of operations, and a good reason to always use
parentheses: which is evaluated first, the unary minus or
the raising-to-powers?
(-4)^0.5
-(4^0.5)
sqrt(-4)
-sqrt(4)
If the OP *really* wants the square root of -4 he could do
sqrt(-4+0i) or (-4+0
It's order of operations, and a good reason to always use
parentheses: which is evaluated first, the unary minus or
the raising-to-powers?
(-4)^0.5
-(4^0.5)
sqrt(-4)
-sqrt(4)
Sarah
On Wed, Mar 21, 2012 at 7:09 PM, Mike Williamson wrote:
> Hi Everyone,
>
> I did a search through the archives
Hi Everyone,
I did a search through the archives and did not find an answer,
although I must admit it is a hard search to do ( ^0.5 is tough to
explicitly search for ).
I am sure there is some mathematically accurate reason to explain the
following, but I guess I either never learned it o
On Wed, Mar 21, 2012 at 11:31 AM, wrote:
>
> I'm trying to use sqldf to query for the earliest date of a blood test when
> patients have had multiple tests in a given year. My query looks like this:
>
> test11 <- sqldf("select CHILD_ID, min(SAMP_DATE)
> from lab
>
The first thing to do is update your rather old version of R. If the
2.14 binaries aren't available for your your version of Ubuntu in the
main repo, there are instructions here:
http://cran.r-project.org/bin/linux/ubuntu/
If that still doesn't work, please provide the list with details of
your sy
I'm using the fwdmsa package to identify deviant cases in a Mokken scale
analysis. I've run into a problem., separate from the one I posted
previously. The problem comes with items that are "easy" by IRT standards. A
good scale should include a range of difficulties; yet when I include "easy"
items
I'm using the fwdmsa package to identify deviant cases in a Mokken scale
analysis. I've run into a problem., separate from the one I posted
previously. The problem comes with items that are "easy" by IRT standards. A
good scale should include a range of difficulties; yet when I include "easy"
items
sorry I mistyped the "fs.MSA(by364.data)" in the previous post.
--
View this message in context:
http://r.789695.n4.nabble.com/small-scales-in-fwdmsa-tp4493479p4493490.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.o
I'm using the fwdmsa package to identify deviant cases in a Mokken scale
analysis. I've run into a problem. When I use scales comprising a few items,
iI tend to get an error:
Error in y[order(res[-msamp])][1:(length(samp) + 1 - length(msamp))] :
only 0's may be mixed with negative subscripts
I
Hello everyone,
I am probably not the only one having trouble with this package but here goes.
I want to install XML on Ubuntu. I installed libxml2-dev and
everything works out fine until I get the following:
Error in reconcilePropertiesAndPrototype(name, slots, prototype,
superClasses, :
No d
Hi Juliet,
First of all, cv.glmnet is used to estimate lambda based on
cross-validation. To get a glmnet prediction, you should use glmnet
function which uses all data in the training set. Second, you
constructed testX using a different data set (data.test.std) from one
for glmnet predict (data.te
Hello, all.
I'm investigating the rate at which skeletal joint surfaces pass
through a series of ordered stages (changes in morphology). Current
statistical methods in this type of research use various logit or
probit regression techniques (e.g., proportional odds logit/probit,
forward/backward c
Post this on the r-sig-mixed=models list rather than here.
However, fwiw, it is nonsense to estimate a random effect with a
sample size of 3. That's trying to estimate variance with a sample
size of 3. You can't do it with any meaningful precision. Whether or
not the effect really **is** conceptua
Dear all,
I am receiving the error below, I think because my n is exceeding the
allowable limit for a vector.
Can anyone confirm, and help with the following questions?
The function and error:
> stPte8 <- rtrunc(rnorm, nx * ny * nsimu, linf=0, mean=as.vector(PTmn),
> sd=as.vector(PTsd))
Error in
Hi David,
It's best to keep the mailing list in the loop so I'm cc-ing to R-help.
I've rethought your problem and propose a different solution.
The main problem is to create a vector of expressions to be used in
the legend.
(see https://stat.ethz.ch/pipermail/r-help/2011-February/270106.html)
Hi,
I need to write program to run some results from an experiment. i have the
results saved in 2 different files, named "tuesday" and "wednesday" (both
located within the same file). when i wrote the program for "tuesday" i had
no problem running it, but when i changed the work directory to wed
Hi,
I need to create a method for a class named 'simpleOLS' which I have created
that will compute the coefficients of predictors.
Here is my code:
#-
Hi everyone!
I have some doubts about mixed effect models and I hope someone could help
me. I´m trying to analyze a dataset coming from samples of dung beetles in
the same forest fragments along 3 consecutive years (1994, 1995 and 1996)
and 14 years after (2010). I sampled dung beetles in 18 dif
thanks Michael and William,
I have resigned to moving the wednesday in to the tuesday file and keeping
tuesday as the work directory. this seemed to solve the problem, but i think
that also means that i do have permission to access the wednesday file. i
don't quite understand what went wrong, but
Hi,
I have troubles to assign names to the assets in the portfolio frontier plot
using frontierPlot() in fPortfolio package. Can anyone please help me? If I
use tailoredFrontierPlot in fPortfolio the assets assign names but I dont
want to plot capital market line e.t.c. Someone maybe know how to d
Michelle:
You need to work with someone locally who understands basic
statistics, as you are clearly out of your depth. Posting to this list
is highly unlikely to meet your needs, nor is this an appropriate
place or means to learn statistics -- it's for help on R. (Yes, they
do overlap, but it is
Hi there,
I migrated from Windows7 to Ubuntu (11.10) and am trying to get my R
back online.
I've switched from Tinn-R to RKWard which seems to work well.
My problem at the moment is that I'm no longer able to read in the data
file I was working on before.
> popafr <- read.table(file="~/Do
Oops. Coefficients are returned on the scale of the original data.
testX <- cbind(1,data.test)
yhat2 <- testX %*% beta
# works
plot(yhat2,yhat_enet)
On Wed, Mar 21, 2012 at 2:35 PM, Juliet Hannah wrote:
> All,
>
> For my understanding, I wanted to see if I can get glmnet predictions
> using
Would it be possible to change the axis at the end?
My data sets seem to be quite large so I was thinking for the plot and the
consequent lines to keep always
the current minimum and maximum like
plot(x)
minimum=min(x)
lines(x1)
minimum=c(minimum,x1)
lines(x2)minimum=c(minimum,x2)
then if there
All,
For my understanding, I wanted to see if I can get glmnet predictions
using both the predict function and also by multiplying coefficients
by the variable matrix. This is not worked out. Could anyone suggest
where I am going wrong?
I understand that I may not have the mean/intercept correct,
On Mar 21, 2012, at 11:27 , Marco Tommasi wrote:
> To whom it may concern
>
> I made some analysis with R using the command Anova. However, I found
> some problmes with the output obtained by selecting type II o type III
> sum of squares.
Well, it would primarily concern the maintainer of the
On Mar 21, 2012, at 1:07 PM, Justin Montemarano wrote:
Hi all:
I've got it... it appears that total.density was also defined in two
separate data frames (se.predict.data and dc.predict.data) with levels
order 16, 32, 8. Using relevel(), I moved 8 to the first position
and it's
solved the pl
Hi all:
I've got it... it appears that total.density was also defined in two
separate data frames (se.predict.data and dc.predict.data) with levels
order 16, 32, 8. Using relevel(), I moved 8 to the first position and it's
solved the plotting problem.
Ista's 'minimal' reproducible code request pr
list.dirs() will list the directories in that file exactly as R sees
them. If you are getting can't change working directory messages I can
only think of two reasons:
i) File permissions (though that's unlikely to get messed up unless
there's someone around who knows how to do that in the first pl
On Wed, Mar 21, 2012 at 12:48 PM, HJ YAN wrote:
> Thanks a lot Sarah, for your nice example and code.
>
> I know '==' can do the work. Just as a R beginer, sometimes really want to
> be more like a 'real programmer', if you know what I mean...
Being a "real programmer" means using one line of co
You'll also want to use dput() to send us an exact encoding of your
data when making that reproducible example: there might be something
subtle at play here that print methods won't show.
Michael
On Wed, Mar 21, 2012 at 12:28 PM, Ista Zahn wrote:
> On Wed, Mar 21, 2012 at 12:00 PM, Justin Montem
Hi Zack,
This works as expected on my machine:
tank_trunc <-
read.csv("http://r.789695.n4.nabble.com/file/n4492267/upton_tank_trunc_nabble.csv";)
michigan_map.df <- map_data('county', 'michigan')
ggplot() + geom_point(aes(lon, lat), data = tank_trunc, na.rm = T) +
geom_path(aes(long, lat, grou
Hi Ian,
I haven't read in details because you don't provide a reproducible
example (see ?dput) but you might want to take a look at the aggregate()
and doBy::summaryBy() functions.
HTH,
Ivan
--
Ivan CALANDRA
Université de Bourgogne
UMR CNRS/uB 6282 Biogéosciences
6 Boulevard Gabriel
21000 Di
If you are on a mac, you don't need to escape spaces within setwd():
e.g., on my machine, setwd("~/Desktop/Current Semester") works just
fine.
Michael
On Wed, Mar 21, 2012 at 12:08 PM, mela wrote:
> Hi,
>
> I need to write program to run some results from an experiment. i have the
> results sa
On Wed, Mar 21, 2012 at 12:00 PM, Justin Montemarano wrote:
> Ista:
>
> Your attached code did work for me; moreover, the facets were presented in
> the desired order with facet_wrap() and facet_grid(), which is what I'm
> using because I have a second factor used in facet_grid().
>
> Still, my pl
You probably want
mylist[[i]] = function(...)
in your loop.
Similarly, when you want them again later, you need to use double
square brackets.
I once heard a useful metaphor for understanding the difference
between [ and [[ when it comes to lists.
If x (a list) is a train, then x[2] is the sec
Scratch that -- while true, it doesn't seem to cause that error message.
Can you do this?
list.dirs("/Users/user/Desktop/Recorded results/")
Also, are you sure you have various access permissions to the Wednesday folder?
Michael
On Wed, Mar 21, 2012 at 12:25 PM, R. Michael Weylandt
wrote:
> I
Use
mylist[[i]] = function(...)
mylist[i] and mylist[[i]] are two different things.
On Wed, Mar 21, 2012 at 11:08 AM, David Zastrau wrote:
> Hello dear R-users,
>
> I am currently trying to fill some datasatructure (array, list, hash...)
> with matrices that are calculated by a function and do v
Hi again,
As a follow-up question... If I need to calculate a risk difference with a
CI, I imagine the solution would be similar? Here's how I would get the
point estimate:
x1 <- factor(rbinom(100,1,.5),levels=c(0,1))
x2 <- factor(round(runif(100,1,2)),levels=c(1,2),labels=c("cat1","cat2"))
outco
Hi,
I need to write program to run some results from an experiment. i have the
results saved in 2 different files, named "tuesday" and "wednesday" (both
located within the same file). when i wrote the program for "tuesday" i had
no problem running it, but when i changed the work directory to wedn
The first block of code should be reproducible.
For the second block, you need only a data.frame. I've included a few rows
from the one I'm working with.
Two required libraries: maps, ggplot2.
http://r.789695.n4.nabble.com/file/n4492267/upton_tank_trunc_nabble.csv
upton_tank_trunc_nabble.csv
--
As long as == is an appropriate test for your data, why not just use
R's innate ability to handle matrices/data frames?
> x1 <- matrix(1:20, ncol=4)
> x2 <- ifelse(x1 > 18, 22, x1)
> x1
[,1] [,2] [,3] [,4]
[1,]16 11 16
[2,]27 12 17
[3,]38 13 18
[4,]4
Hello dear R-users,
I am currently trying to fill some datasatructure (array, list, hash...)
with matrices that are calculated by a function and do vary in size:
mylist = list()
for(i in 1:n)
mylist[i] = function(...) # returns a matrix
print(mylist[1]) # prints only the first element of
Dear Ellison,
Many thanks for your reply.
The information you typed is clear and now I know what to do. Your
suggestion about finding some coffee while running simulation is so good =)
Regards
-
Best regards
Ufuk
--
View this message in context:
http://r.789695.n4.nabble.com/glm-fit-fitt
when fitting an autoregressive time series model to the data i.e. in function
ma(x, order, centre=TRUE)
i attached file (time series data)
http://r.789695.n4.nabble.com/file/n4491858/tinku.txt tinku.txt
how to decide best order for a good time series model
which would be valuable for arma() proces
Dear all,
I am having a hard time attempting to do a multinomial logit modeling in R.
I am trying to analyze a dataset whereby there are 3 scenarios with 4
difference choice parameters. In particular – I am having a hard time
arranging this into a .csv format. What sorts of headings should I pu
solved grrr
I had to set JAVA_HOME to point to the jdk directory not the parent.
This had to be done as root not user otherwise the rJava is fails.
At the end of the day its installed.
--
View this message in context:
http://r.789695.n4.nabble.com/rJava-RCMD-javareconf-fails-tp4488961p44
What if the model isn't nested, i.e. I want to test y=x+w vs y=x+z+v. Is
there a valid test/method to compare these (other than comparing R squared
values)? They are both multiple regression models.
--
View this message in context:
http://r.789695.n4.nabble.com/anova-lm-F-test-confusion-tp44
Dear R-user,
I'm trying to compare two sets of results and wanted to find out which
element in the two data frame/matrix are different.
I wrote the following function and it works ok, and gives me a long list of
"good" as outcomes.
CHECK<-
function (x = "file1", y = "file2")
{
for (i in 1:n
Hi
Thank you Bert and Thomas for your help, I did what I wanted with this code.
>test<-c(4,8,9,6,7)
>barplot(test,density =20,angle=45)
But I want to cross the lines in each bar.
Please, how to do it?
Thank you in advance.
--
View this message in context:
http://r.789695.n4.nabble.com/Not-colo
Dear all,
I am having a hard time attempting to do a multinomial logit modeling in R.
I am trying to analyze a dataset whereby there are 3 scenarios with 4
difference choice parameters. In particular – I am having a hard time
arranging this into a .csv format. What sorts of headings should I pu
Hello R users,
When trying to fit a nonlinear mixed model to a respiration time series,
I get the following error message:
Error in recalc.varFunc(object[[i]], conLin) :
dims [product 30] do not match the length of object [34]
In addition: Warning message:
In conLin$Xy * varWeights(object) :
> ts<-ts(bhavar$V1)
> decompose(ts)
Error in decompose(ts) : time series has no or less than 2 periods
> HoltWinters(ts)
Error in decompose(ts(x[1L:wind], start = start(x), frequency = f),
seasonal) :
time series has no or less than 2 periods
is it true that order of ar(ts) function is p-value
To whom it may concern
I made some analysis with R using the command Anova. However, I found
some problmes with the output obtained by selecting type II o type III
sum of squares.
Briefly, I have to do a 2x3 mixed model anova, wherein the first factor
is a between factor and the second factor
Hello Everyone,
I have just started with deSolve package, I have a set of ODE equation with
few parameters, for example
dy/dx = a1*Y*(1-Y/Ymax) - a2*(Y+0.001)
and
dz/dt = a3*Y- a4*Z;
I have the initial values of Y, Z and a1,a2,a3 are my parameters,
Now my main objective is to find the solve the eq
Ista:
Your attached code did work for me; moreover, the facets were presented in
the desired order with facet_wrap() and facet_grid(), which is what I'm
using because I have a second factor used in facet_grid().
Still, my plots with total.density as a facet are coming out in 16, 32, 8,
and I'm no
Hello R Community,
I don't post to these things often so excuse me if I stumble on my forum
etiquette. This is a complex problem for me, which may require two forum
entries, but I will try my best to be concise. Also, I am a self taught
coder, so if my code is not to convention, your constructi
Hi Justin,
this gives the correct order (8, 16, 32) on my machine:
total.density <-
c(8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32)
total.density <- f
On 21-Mar-2012 S Ellison wrote:
>> I get the errors;
>> glm.fit: fitted probabilities numerically 0 or 1 occurred and
>> glm.fit: algorithm did not converge
>> .
>> Is there any way to to
>> fix this problem?
>
> There are two separate issues.
> One is the appearance of fitted values at 0 or
I'm trying to use sqldf to query for the earliest date of a blood test when
patients have had multiple tests in a given year. My query looks like this:
test11 <- sqldf("select CHILD_ID, min(SAMP_DATE)
from lab
group by CHILD_ID
having extract (ye
I think I understand, but I believe my original interest is in the order of
levels(total.density), since ggplot appears to be using that to order the
facets. Thus, I'm still getting three graphs, ordered (and displayed as)
16 to 32 to 8, rather than the more intuitive, 8 to 16 to 32. I'm sorry if
Ah, you're missing something crucial:
> levels(total.density)
[1] "8" "16" "32"
is giving you the *labels* of the factor, as *strings*, and what you
get if you use order() on them has nothing to do with the order of the
factor levels, and everything to do with the string sort order for
your loca
Le 21/03/2012 10:56, Patrick Giraudoux a écrit :
Hi,
Using lme from the package nlme 3.1-103, I meet a strange warning. I
am trying to compare to models with:
library(nlme)
lmez6=lme(lepus~vulpes,random=~1|troncon/an,data=ika_z6_test)
lmez60=lme(lepus~1,random=~1|troncon/an,data=ika_z6_test)
Actually I've try that too, Sarah
The test is to run order(levels(total.density)), which I need to be 1 2 3,
not 2 3 1, and your solution still gives me 2 3 1.
I also don't know how to reply to this thread with the previous message
below...
-
Justin Montemarano
Graduate Student
Kent State Uni
Is this what you need?
> total.density <-
+
c(8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32)
> total.density <- factor(total.density, levels=c(8, 16, 3
Hi all:
I'm attempting to create a faceted plot with ggplot2 and I'm having issues
with a factor's order that is used to define the facet_grid().
The factor (named total.density) has three levels - 8, 16, and 32 - and I
would like them presented in that order. Running
order(levels(total.density)
On 03/21/2012 06:30 AM, Vito Muggeo (UniPa) wrote:
It appears that glmnet(), when "selecting" the covariates entering the
model, skips from K covariates, say, to K+2 or K+3. Thus 2 or 3
variables are "added" at the same time and it is not possible to obtain
a ranking of the covariates according t
> -Original Message-
> Okay, try this:
>
> result <- with(data,
> aggregate(data[,-(1:2)], by=list(ID), FUN=diff))
>
> This assumes that the dataframe is sorted as in your example.
> If that's not the case, then use order to arrange it first:
A caveat: order and s
Hello,
I'm still hoping my issue is preventable and not worthy of a bug/crash
report, hence my post is in 'help'. Anyway, I'd like to know how to reset
the console so it is clear of all residual effects caused by previous
scripts. Details:
I run a script once and it runs successfully (but very sl
thanks Arne and Achim
will surely use the forum on systemfit at RForge for further clarification
regrads
Priya
.
From: Arne Henningsen
To: Achim Zeileis , priya.s...@zycus.com,
r-help@r-project.org
Date: 21-03-2012 18:35
Subject:Re: [R] How to do 2SLS in R
On
Hello All,
Tried some more Internet searches and came to the conclusion that one probably
does need to create a "timevar" before reshaping from long to wide. Below is
some code that creates the "timevar" and transposes the data.
connection <- textConnection("
005 1 Gemcitabine
005 2 Erlotinib
On 21 March 2012 09:32, Achim Zeileis wrote:
> On Wed, 21 Mar 2012, priya.s...@zycus.com wrote:
>> Hi List
>> I want to carry out structural mode. Following Example l have taken from
>> Basic Econometrics- Damodar Gujarati :
>
> Look at the "systemfit" package. For an introduction see the accompan
vinod1 gmail.com> writes:
> I am trying fit certain data into Beta distribution. I get the error saying
> "Error in fitdist(discrete_random_variable_c, "beta", start = NULL, fix.arg
> = NULL) : the function mle failed to estimate the parameters, with the
> error code 100"
>
> Below is the so
Here's the plyr way I should have thought of earlier:
require(plyr)
ddply(data, "ID", numcolwise(diff))
Still requires your data to be ordered.
Peter Ehlers
On 2012-03-21 04:51, Eik Vettorazzi wrote:
Hi Sylvain,
assuming your data frame is ordered by ID and TIME, how about this
aggregate(c
On 2012-03-20 06:09, "ECOTIÈRE David (Responsable d'activité) - CETE
Est/LRPC de Strasbourg/6 Acoustique" wrote:
Hi,
I'd like to make a legend with a mix of mathematical symbol (tau),
numeric variable and character variables.I have tried :
types<-c("Type 1","Type 2","Type 2")
tau<-c(1,3,2)
leg
Hi Sylvain,
assuming your data frame is ordered by ID and TIME, how about this
aggregate(cbind(X,Y)~ID,data, function(x)(x[2]-x[1]))
#or doing this for all but the first 2 columns of data:
aggregate(data[,-(1:2)],by=list(data$ID), function(x)(x[2]-x[1]))
cheers.
Am 21.03.2012 09:48, schrieb wph
> I get the errors;
> glm.fit: fitted probabilities numerically 0 or 1 occurred and
> glm.fit: algorithm did not converge
> .
> Is there any way to to
> fix this problem?
There are two separate issues.
One is the appearance of fitted values at 0 or 1.
The other is the lack of convergence.
Okay, try this:
result <- with(data,
aggregate(data[,-(1:2)], by=list(ID), FUN=diff))
That's it !! I didn't knew the "diff" function. Your solution works
perfectly.
Thanks Peter for this !
Sylvain
Le 21/03/12 12:01, Peter Ehlers a écrit :
On 2012-03-21 03:37, wphantomf
On 2012-03-21 03:37, wphantomfr wrote:
Thanks peter for your fast answer.
your is really nice but if I have say 20 variables I have to write 20
statements like "DIF.X = X[TIME=="T2"] - X[TIME=="T1"]".
Does someone has a trick to avoid this ? It may not be easily possible.
Okay, try this:
r
Thanks peter for your fast answer.
your is really nice but if I have say 20 variables I have to write 20
statements like "DIF.X = X[TIME=="T2"] - X[TIME=="T1"]".
Does someone has a trick to avoid this ? It may not be easily possible.
Regards
Sylvain Clément
Le 21/03/12 11:03, Peter Ehle
dear all,
It appears that glmnet(), when "selecting" the covariates entering the
model, skips from K covariates, say, to K+2 or K+3. Thus 2 or 3
variables are "added" at the same time and it is not possible to obtain
a ranking of the covariates according to their importance in the model.
On t
On Mar 21, 2012, at 09:04 , Rolf Turner wrote:
> On 21/03/12 20:19, Gerrit Eichner wrote:
>> Dear Ben, or anybody else, of course,
>>
>> I'd be grateful if you could point me to a reference (different from ch. 4
>> "Linear models" in "Statistical Models in S" (Chambers & Hastie (1992)))
>> reg
On 21-03-2012, at 08:10, sagarnikam123 wrote:
> i am new to time series,whatever i know up till now,from that
> i have uploaded time series file & what to build arma model,but for that i
> want p & q values(orders)
> tell me how to calculate best p & q values to find best AIC values for model
>
On 2012-03-21 01:48, wphantomfr wrote:
Dear R-help Members,
I am wondering if anyone think of the optimal way of computing for
several numeric variable the difference between 2 levels of a factor.
To be clear let's generate a simple data frame with 2 numeric variables
collected for different
Hi,
Using lme from the package nlme 3.1-103, I meet a strange warning. I am
trying to compare to models with:
library(nlme)
lmez6=lme(lepus~vulpes,random=~1|troncon/an,data=ika_z6_test)
lmez60=lme(lepus~1,random=~1|troncon/an,data=ika_z6_test)
Both have the same number of observations and gr
On 03/21/2012 06:35 AM, bobo wrote:
> Thank you. I was able to get it loaded however when I tried to run
>
> mod1<-lm(Pat2006~FHouse)
> I got
> Error in eval(expr, envir, enclos) : object 'Pat2006' not found
>
> What exactly is occurring here?
>
> --
> View this message in context:
> http://r.7896
1 - 100 of 113 matches
Mail list logo
