Re: [R] split array into groups by value

One approach is: l <- c(1,1,1,1, 0,0,0,0,0, 1,1,1,1,1,1) r <- rle(l)$lengths split(l, rep(seq_along(r), r)) I hope it helps. Best, Dimitris On 3/6/2012 3:53 AM, pavlo wrote: I have an array l<- c(1,1,1,1, 0,0,0,0,0, 1,1,1,1,1,1) I would like to get a rugged array [[1]] 1,1,1,1 [[2]] 0,0,0

Re: [R] how I can explore the variable names in my covariance matrix?

I would do: QQ.frame <- data.frame(round(QQ,2)) name(QQ.Frame) <- paste("foo",seq(1:7)) foo 1 foo 2 foo 3 foo 4 foo 5 foo 6 foo 7 1 1 0 0 0 0 0 0 2 0 1 0 0 0 0 0 3 0 0 1 0 0 0 0 4 0 0 0 1 0

[R] Why aren't row names in a data frame unique?

I expected the row names to be unique but a data frame appears to be able to hold duplicate row names. This makes me thing that there must be circumstances when it is necessary. However, I cannot think of any. Please enlighten me. [[alternative HTML version deleted]] ___

Re: [R] split array into groups by value

Hello, pavlo wrote > > I have an array > l <- c(1,1,1,1, 0,0,0,0,0, 1,1,1,1,1,1) > > I would like to get a rugged array > [[1]] 1,1,1,1 > [[2]] 0,0,0,0,0 > [[3]] 1,1,1,1,1,1 > > catching every group of contiguous repeated values. Any help would be > greatly appreciated! > -Pavel > Is this

[R] Error on Startup: Error: 7:6: unexpected symbol 7: set the

I get this error before the prompt every time I start R version 2.14.2. Don't know if it is causing any problems, but it bugs me. Any one have any ideas? Running R 64 bit on Windows 7 Ultimate SP1. -- View this message in context: http://r.789695.n4.nabble.com/Error-on-Startup-Error-7-6-unex

Re: [R] index instead of loop?

Hello, > > Mar 05, 2012; 8:53pm — by Ben quant Ben quant > Hello, > > Does anyone know of a way I can speed this up? > Maybe, let's see. > > # change anything below. > # Yes. # First, start by using dates, not characters fdate <- function(x, format="%Y%m%d")

[R] split array into groups by value

I have an array l <- c(1,1,1,1, 0,0,0,0,0, 1,1,1,1,1,1) I would like to get a rugged array [[1]] 1,1,1,1 [[2]] 0,0,0,0,0 [[3]] 1,1,1,1,1,1 catching every group of contiguous repeated values. Any help would be greatly appreciated! -Pavel -- View this message in context: http://r.789695.n4.na

Re: [R] I want to fill a column in with 0 or 1 depending on another columns input

Hello, kevin123 wrote > > This is a portion of my data frame > > MemberIDSpecialty Surgery Internal > 1 42286978 Surgery NA NA > 2 97903248 Internal NA NA > 3 2759427 Interna

Re: [R] ggplot2

I found the addendum. http://cloud.github.com/downloads/hadley/ggplot2/guide-col.pdf -- View this message in context: http://r.789695.n4.nabble.com/ggplot2-tp4447745p4448150.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-pro

[R] Help with plot Grouped Bar Plot by using R

My input file: [code] Number of Z Number of Data1 Data1 % Number of Data2 Data2 % 0 704512099 99.74% 704423913 99.73% 1 1550142 0.22% 624685 0.09% 2 164297 0.02% 145942 0.02% 3 21515 0.00% 81941 0.01% 4 92380.00% 59188 0.01% 5

Re: [R] decision/classification trees with fewer than 20 objects

On 05/03/2012 20:52, patriciag...@aon.at wrote: Hi! I'm trying to construct and plot a decision tree to class a set of only 8 objects and tried to use the rpart and tree function, but get a error message both times: rpart: fit is not a tree, just a root tree: cannot plot singlenode tree I r

Re: [R] 632 estimator using boot package

Jim if I understand you, you are using the ordinary bootstrap instead of the Efron-Gong "optimism bootstrap". I don't think the ordinary bootstrap is applicable here. Frank Jin Minming wrote > > Hello Frank, > > Thanks for your advice. > > I also used the validation using rms package. The res

Re: [R] problems reading a large dta dataset in R

> -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] > On Behalf Of Francesco Sarracino > Sent: Monday, March 05, 2012 4:00 PM > To: r-help@r-project.org > Subject: [R] problems reading a large dta dataset in R > > Dear R listers, > > I have a si

Re: [R] Error in file(fname, "r") : invalid 'description' argument when running maptools' readAsciiGrid on a dataframe

What are surfA, surfB? There's nothing to suggest that difcount is vectorized so if they are vectors of length > 1 that could lead to your problem. Michael On Mon, Mar 5, 2012 at 2:07 PM, Colin Wren wrote: > Hi, > I'm trying to calculate a sum of differences between two ascii grids. > I have the

Re: [R] rm(list=ls())

No, it won't give the same result. If you load packages or have hidden variables / environments, they'll remain in the session or if you change global options they'll stay. It's a somewhat frequently asked question, but there's no way to get a "factory fresh" session without restarting R. You can g

Re: [R] Aggregate with Function List ?

On 2012-03-05 14:20, Michael Karol wrote: Thank you for the suggestion. Tried it as : MeansByDoseDayTime<- aggregate(as.double(PK04Sub$Concentration.ng.mL.), by = list(PK04Sub$Dose.Level, PK04Sub$Day, PK04Sub$HourNominal), FUN = function(x) c( mean(x, trim = 0, na.rm = T, weights=NULL)

Re: [R] obsolete(?) nls package

On 12-03-05 7:08 PM, John C Nash wrote: I am building some tools to carry out nonlinear least squares when the residuals are very small (something that nls specifically is NOT designed to do). However, I wanted to put a cross reference in the Rd file. Running R CMD check pkg gave a strange warn

Re: [R] I want to fill a column in with 0 or 1 depending on another columns input

On Mar 5, 2012, at 2:56 PM, kevin123 wrote: This is a portion of my data frame MemberIDSpecialty Surgery Internal 1 42286978 Surgery NA NA 2 97903248 Internal NA NA 3 2759427

[R] obsolete(?) nls package

I am building some tools to carry out nonlinear least squares when the residuals are very small (something that nls specifically is NOT designed to do). However, I wanted to put a cross reference in the Rd file. Running R CMD check pkg gave a strange warning Obsolete package(s) 'nls' in Rd xre

Re: [R] Filter/Ceiling for unwanted data - zoo

On Mon, Mar 5, 2012 at 3:33 PM, knavero wrote: > Here's my script: > > http://pastebin.com/zx3TCtXg > > I want to draw attention to the code block where the read in of the raw data > is located. Is there a function that filters out unwanted data with respect > to a ceiling limit. For example, I wa

[R] problems reading a large dta dataset in R

Dear R listers, I have a silly problem. I am trying to load a dta (Stata) file in R. The dta is about 650 MB and contains the integrated World Values Survey/ European Value Study data-set. My problem is that I don't manage to load the file. After almost 3 hours after I issued the following command

Re: [R] ggplot2

Hi Ryan, It is rather presumptuous to assume that old code not working is a bug. Checkout: https://github.com/djmurphy420/ggplot2-transition-guide for a transition guide detailing changes in the new ggplot2 0.9. Sincerely, Josh On Mon, Mar 5, 2012 at 1:24 PM, Ryan Garner wrote: > I just upda

Re: [R] Automating R script with Windows 7

Hi Jim, Please disregard my earlier post -- I have done some research and realized the space between after "program " was the the issue. I can now open RScript.exe from the command prompt using the abbreviated form: C:\PROGRA~1\R\R-2.11.1\bin\RScript.exe >From your earlier post, I understand the

Re: [R] Trouble with a loop

Hi Kerry, Right now at each iteration, you just overwrite everything. If you want a matrix, you need to instantiate Score as a matrix and then assign the results into each element of it. That said, I do not think you really need a loop. rpois() is vectorized, so you can in one pass generate a l

Re: [R] Automating R script with Windows 7

You are looking to run R in batch mode see How to run R in batch mode [1] and the Quick-R on Batch Processing [2] [1] http://turing.une.edu.au/~stat356/Rbatch.html [2] http://www.statmethods.net/interface/batch.html On Mon, Mar 5, 2012 at 8:55 AM, vincent.deluard wrote: > > Hi R-users, > > I a

Re: [R] Issue with using rcom on windows 7

Thanks professor. I am following up with the statconn team now. I will try create.post function as well. Apologies for incorrect post here. Regards, Alok Please follow the attached hyperlink to an important disclaimer http://www.credit-suisse.com/asiapac/legal/securities/ -Original Mes

Re: [R] Can't find all levels of categorical predictors in output of zeroinfl()

Thank you Achim and Petr for your quick replies. My apologies, but I'm quite new to statistical modeling (and the language surrounding it) as well. I'm not sure exactly what was meant by "making the model identifiable" but I think I understand the purpose... Yes, I think this means that the fa

Re: [R] Automating R script with Windows 7

Hey Jim, Thanks for the help. It took me a little bit of research but I got your solution to work. For everybody who has the same problem (1) remember to use the abbreviated names (no space) in folder paths: ex: 'C:\PROGRA~1\R\R-2.11.1\bin\RScript.exe' (2) put the folder with the R script to ru

Re: [R] How to choose a button and scrape the website data

That website uses javascript to submit the form (and doesn't work in Chrome). You could build a javascript interpreter in R, have parse the page, and then use the various javascript to submit the form. R just isn't the right tool for that type of interaction. Performing the task you want--as descr

Re: [R] row names of a heatmap on left hand side

bump -- View this message in context: http://r.789695.n4.nabble.com/row-names-of-a-heatmap-on-left-hand-side-tp4426353p4447786.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailm

[R] ggplot2

I just updated to R 2.14 with ggplot2 0.9 and am finding bugs. > ggplot2 "GPL-2" "2.14.0" This example is taken from pg 101 in the ggplot book. > plot <- qplot(date, psavert, data = economics, geom = "line") + > ylab("Personal savings rate") + geom_hline(xintercept = 0, colour

Re: [R] Filter/Ceiling for unwanted data - zoo

thinking of using an "ifelse" statement, curious if there's a more elegant way of going about this -- View this message in context: http://r.789695.n4.nabble.com/Filter-Ceiling-for-unwanted-data-zoo-tp4447595p4447791.html Sent from the R help mailing list archive at Nabble.com. _

[R] Filter/Ceiling for unwanted data - zoo

Here's my script: http://pastebin.com/zx3TCtXg I want to draw attention to the code block where the read in of the raw data is located. Is there a function that filters out unwanted data with respect to a ceiling limit. For example, I want to remove any value over 500 kW in the rawCool variable.

[R] [R-pkgs] New package: OpenStreetMap 0.2

OpenStreetMap is a new package that accesses raster open street maps from Mapnik, and satellite imagery from Bing. Some features: 1. Uses multiple map tiles stitched together to create high quality images. 2. No files are created or stored on the hard drive. 3. Tiles are cached,

[R] [R-pkgs] ggmap : ggplot2 and RgoogleMaps

Dear useRs - ggmap v1.2 is now available on CRAN. ggmap is a relatively new package which combines the power of ggplot2 with the spatial contextual information in Google Maps or OpenStreetMaps (via RgoogleMaps) to provide an easy, consistent and modular framework for spatial graphics. For e

[R] Error in file(fname, "r") : invalid 'description' argument when running maptools' readAsciiGrid on a dataframe

Hi, I'm trying to calculate a sum of differences between two ascii grids. I have the file names of the two grid files in a data.frame along with other data. I'm then trying to add a new column to the data.frame with the result of that calculation. eg. library(maptools) difcount <- function(surfA,

Re: [R] 632 estimator using boot package

Hello Frank, Thanks for your advice. I also used the validation using rms package. The results from rms indicate that the linear model used in my project is overfitted around 0.1 in terms of R2. But, the results from using ordinary boot method in boot package suggest the mean of R2 is even hi

[R] decision/classification trees with fewer than 20 objects

Hi! I'm trying to construct and plot a decision tree to class a set of only 8 objects and tried to use the rpart and tree function, but get a error message both times: rpart: fit is not a tree, just a root tree: cannot plot singlenode tree I read in the post 'question regression trees' that r

[R] I want to fill a column in with 0 or 1 depending on another columns input

This is a portion of my data frame MemberIDSpecialty Surgery Internal 1 42286978 Surgery NA NA 2 97903248 Internal NA NA 3 2759427 Internal NA

Re: [R] svm with GRASS GIS

Hi Ethienne, we (me and Gab) would like to thank you ! Finally we got what we were looking for but we did it without use the "raster" packagebut we are going to try also with it to see if it allow to have faster computation or data manipulation, If you're interested we can show you the code we

Re: [R] Automating R script with Windows 7

I created a txt file with R commands in it and then a batch file to process the txt file. The batch file could be scheduled. The batch file is: REM on Microsoft Windows (adjust the path to R.exe as needed) "C:\Program Files\R\R-2.13.2\bin\x64\R.exe" CMD BATCH "C:\Users\Frank\Documents\R\Sc

[R] Trouble with a loop

I am trying to run this loop but it keeps coming up with the following error: 'Error: no function to return from, jumping to top level' n.simul <- 1000 A <- {for(i in 1:12){{ nT <- rpois(n.simul, T[i]) nP <- rpois(n.simul, P[i]) nD <- rpois(n.simul, D[i]) nC <- rbinom(n.simul, nT, C[i]) Score <-

[R] rm(list=ls())

R-2.14.2, Win7 x64 Dear list, I have the habit of including rm(list=ls()) at the top of most of my scripts. However, I wonder whether rm(list=ls()) gives the exact same result as closing R and starting again fresh. In other words, is it possible that there will be differences on how a script

Re: [R] source for function sample() in package base?

On Mar 5, 2012, at 4:44 PM, kv wrote: Hi all, were can i find the sources for the function sample() (the one from the base package) thanks in advance, Dear kv/ user189035 Please note that cross-posting is frowned upon in the R mailing lists and especially so when you do not give notice th

Re: [R] source for function sample() in package base?

It's an internal function so you have to look into the C sources: it's here under do_sample, but you'll have to follow all sorts of other functions down the rabbit hole if you want to understand the whole thing. http://svn.r-project.org/R/trunk/src/main/random.c Michael On Mon, Mar 5, 2012 at 4:

Re: [R] Aggregate with Function List ?

Thank you for the suggestion. Tried it as : MeansByDoseDayTime <- aggregate(as.double(PK04Sub$Concentration.ng.mL.), by = list(PK04Sub$Dose.Level, PK04Sub$Day, PK04Sub$HourNominal), FUN = function(x) c( mean(x, trim = 0, na.rm = T, weights=NULL), sd(x, na.rm=TRUE),

[R] source for function sample() in package base?

Hi all, were can i find the sources for the function sample() (the one from the base package) thanks in advance, -- View this message in context: http://r.789695.n4.nabble.com/source-for-function-sample-in-package-base-tp4447796p4447796.html Sent from the R help mailing list archive at Nabble.c

Re: [R] How to choose a button and scrape the website data

Thank you, Tyler. Just have a quick read on automa.to and sikuli.org, seems very promising. Since I anticipate there many other cases where a similar issue can arise, I don't mind spending sometime to learn something that is very efficient for the purpose. any suggestions? ___

[R] changing the drawing context using Cairo and RGtk2

I am not too familiar with Cairo and RGtk2 and have the following problem: I have a container with two GTK drawing areas converted into Cairo devices. I know that I can set the current drawing context e.g. using dev.set(). But this is tedious. How can I set the context using the objects da1 or da2

Re: [R] cauchy process

On 06/03/12 02:09, MATEMATIK ISTATISTIK wrote: Hi, How can be Cauchy process construct in R? is there any code or algorithm? thanks a lot What do you mean by "Cauchy process"? A sequence of i.i.d. Cauchy random variables could be considered to be a Cauchy process, and that is readily produced

[R] 3rd attempt R2 and Q2 from pls regression

Greetings R users, I have been hoping someone would be familiar with this topic. I understand fully everything on this list is from the good graces of those who wish to help. Thanks to those who have helped in multiple circumstances. However, I wanted to post this question once more. I hope so

[R] index instead of loop?

Hello, Does anyone know of a way I can speed this up? Basically I'm attempting to get the data item on the same row as the report date for each report date available. In reality, I have over 11k of columns, not just A, B, C, D and I have to do that over 100 times. My solution is slow, but it works

Re: [R] package.skeleton only exports the first 73 lines of code

Copying the code as text into the incomplete .r file worked, good idea. I still don't know why the export didn't work though. Thanks, Jeff -- View this message in context: http://r.789695.n4.nabble.com/package-skeleton-only-exports-the-first-73-lines-of-code-tp4447061p4447374.html Sent from the

Re: [R] How to identify a matrix which causes memory limit?

Hi Thomas, I found a package called Rprofmem(). Is it the one you are referring to? Thanks. Sincerely, Jialin Huang On Mon, Mar 5, 2012 at 1:34 PM, Thomas Lumley wrote: > On Tue, Mar 6, 2012 at 7:14 AM, jim holtman wrote: > > Learn some basic debugging for R. There are several functions (d

Re: [R] How to identify a matrix which causes memory limit?

On Tue, Mar 6, 2012 at 7:14 AM, jim holtman wrote: > Learn some basic debugging for R.  There are several functions (debug, > browser, ...) that can help.  Put the following in your Startup > script: > > options(error=utils::recover) > > or at least execute it manually.  This will give you the tra

Re: [R] How to identify a matrix which causes memory limit?

David, Thanks for your advice. I appreciate it. Sincerely, Jialin Huang On Mon, Mar 5, 2012 at 12:14 PM, jim holtman wrote: > Learn some basic debugging for R. There are several functions (debug, > browser, ...) that can help. Put the following in your Startup > script: > > options(error=uti

Re: [R] Running Total

Modifying the method others have already proposed:   x <- c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L

Re: [R] Running Total

Edward Patzelt writes: > Actually in looking at this I need it to only add if a 0 occurs instead of > a 1. cumsum(1-x) > > On Mon, Mar 5, 2012 at 12:57 PM, jim holtman wrote: > >> cumsum >> >> is probably what you want: >> >> > x <- c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L,

Re: [R] Running Total

cumsum(1-x) cumsum(x==0) Michael On Mar 5, 2012, at 1:59 PM, Edward Patzelt wrote: > Actually in looking at this I need it to only add if a 0 occurs instead of > a 1. > > On Mon, Mar 5, 2012 at 12:57 PM, jim holtman wrote: > >> cumsum >> >> is probably what you want: >> >>> x <- c(1L, 1L,

Re: [R] Running Total

Actually in looking at this I need it to only add if a 0 occurs instead of a 1. On Mon, Mar 5, 2012 at 12:57 PM, jim holtman wrote: > cumsum > > is probably what you want: > > > x <- c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, > + 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L,

Re: [R] Running Total

cumsum is probably what you want: > x <- c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, + 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, + 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, + 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L,

Re: [R] Running Total

Edward Patzelt writes: > I'm am trying to create a vector that has a running total that adds each > time a 1 occurs. here's the code and data > > c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, > 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, > 0L, 1L, 1L, 1L, 1L,

Re: [R] 632 estimator using boot package

Thanks a lot, I will check that. Jim --- On Mon, 5/3/12, Angelo Canty wrote: > From: Angelo Canty > Subject: Re: [R] 632 estimator using boot package > To: r-help@r-project.org > Date: Monday, 5 March, 2012, 18:19 > There is an example of calculating > the 0.632 prediction error estimator in

[R] Running Total

I'm am trying to create a vector that has a running total that adds each time a 1 occurs. here's the code and data c(1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 1L, 1L, 1L, 1L,

Re: [R] How to identify a matrix which causes memory limit?

Learn some basic debugging for R. There are several functions (debug, browser, ...) that can help. Put the following in your Startup script: options(error=utils::recover) or at least execute it manually. This will give you the trace of the stack when the error happens and may help you identify

Re: [R] Trouble with strwrap function

On 05.03.2012 01:49, Aimee Jones wrote: Hi all, I am formatting some graphs and adding text to them. When using the strwrap function in the code below, it properly cuts the main title into sizeable chunks and pastes the second line below that of the first. The subtitle however, is all pasted o

Re: [R] how to send text output to its own window

Sounds like a question for the RStudion people? Uwe Ligges On 05.03.2012 12:35, Robert Kinley wrote: platform: R 2.14.2 -Windows XP - Rstudio When I use cat() or print() in a script, the output text is of course mixed up with the lines of the script. I can sink() the output to

Re: [R] installing package tkrplot

On 05.03.2012 17:26, henk harmsen wrote: package tkrplot worked, but has broken while installing from R 2.11 to 2.14.2. it does not want to be installed anymore on a linux debian squeeze 64 system. have tried: - installing from source R: CMD INSTALL tkrplot_0.0-23.tar.gz - via synaptic: packag

[R] How to choose a button and scrape the website data

hi all, I'm working on scrapping some website data to build a database. Under most cases, I can use package XML to get the dataset. However, some of the website doesn't give a explicit address of the downloaded tables. To be more specific, for example, I'm interested in the website http://et

Re: [R] package.skeleton only exports the first 73 lines of code

On 05.03.2012 19:30, jeff_hawkes wrote: Hi all, apologies for the ignorance I'm about to describe: I'm trying to create a .r file for a function I've written (~300 lines of code). The function is called 'total' and I've entered the most simple package.skeleton: package.skeleton(name="test",

Re: [R] Automating R script with Windows 7

"vincent.deluard" writes: > I am trying to automate the daily running of a simple R script from Windows > 7. >>From previous posts, I understand that this needs to be done with the task > scheduler. That is correct. > I can schedule my laptop to automatically open R at a certain time, but not >

[R] package.skeleton only exports the first 73 lines of code

Hi all, apologies for the ignorance I'm about to describe: I'm trying to create a .r file for a function I've written (~300 lines of code). The function is called 'total' and I've entered the most simple package.skeleton: package.skeleton(name="test", list=c("total")) The export works fine (it

Re: [R] Automating R script with Windows 7

Just save your R script as a plain text file. Here is a copy of a file that I will show you how to execute; it is saved as \temp\test.r cat('this is my R script executing\n', format(Sys.Date())) Here is the command that I execute at the 'CMD' prompt and that you would have scheduled by Windows:

Re: [R] 632 estimator using boot package

Sorry, the final sentence should say sim="parametric" Angelo Canty wrote: There is an example of calculating the 0.632 prediction error estimator in Chapter 6 of Davison & Hinkley (Practical 6.5) I'm not sure what you mean by leave-one-out bootstrapping. If you actually mean the jackknife the

Re: [R] 632 estimator using boot package

There is an example of calculating the 0.632 prediction error estimator in Chapter 6 of Davison & Hinkley (Practical 6.5) I'm not sure what you mean by leave-one-out bootstrapping. If you actually mean the jackknife then look at the empinf function. If you mean subsampling, this can be impleme

Re: [R] p-value from GLM

Dear Peter, Many thanks for the reply. Sure, this is just an example and it makes zero sense! Regards, Dunia 2012/3/4 peter dalgaard > > On Mar 4, 2012, at 12:21 , Dunia Scheid wrote: > > > Dear all, > > > > I am fitting a GLM similar to > > > > library(MASS) > > anorex.1 <- glm(Treat~Postwt+

Re: [R] VAR with GARCH effect

On Mar 5, 2012, at 10:51 AM, mamush bukana wrote: Dear John, Thanks for your prompt response. But I can't get "rmgarch" package. http://www.rseek.org/?cx=010923144343702598753%3Aboaz1reyxd4&q=rmgarch&cof=FORID%3A11 Rather I got some package, "rugarch", in my search to "rmgarch". This pack

Re: [R] How to identify a matrix which causes memory limit?

On Mar 5, 2012, at 10:23 AM, huang jialin wrote: Hello, I am running a simulation on an old computer with memory of 512M. I constantly received a warning of "cannot allocate a vector of ...". How can I identify the matrix causing the problem? Is there any way to fix this issue? ?object.

[R] Automating R script with Windows 7

Hi R-users, I am trying to automate the daily running of a simple R script from Windows 7. >From previous posts, I understand that this needs to be done with the task scheduler. I can schedule my laptop to automatically open R at a certain time, but not to execute a script. Secondary question: h

Re: [R] Nagelkerke R2

R^2 has nothing to do with helping with collinearity. You might also entertain a true geospatial comprehensive model instead of doing 250 model fits. There's probably a lot of background reading you need to do before launching analyses. I assume you've had at least 4 stat courses, also. Frank

Re: [R] 632 estimator using boot package

Bootstrapping does not leave one out. As for .632 this is implemented in the rms package's validate and calibrate functions. Note however that any claimed advantages of .632 over the ordinary optimism bootstrap seem to be a result only of the use of a discontinuous improper scoring role (proporti

Re: [R] new to repeated measures anova in R

Dear Peter, On Mon, 5 Mar 2012 17:28:32 +0100 peter dalgaard wrote: > > On Mar 5, 2012, at 16:05 , Tamre Cardoso wrote: > > > Thank you. > > > > I have attached the data: > > The list software seems to have scrubbed it though... > > > The error message from Anova is: > > > >> pressure.ao

[R] 632 estimator using boot package

Dear All, Anyone has some idea how to implement 632 estimator and leave-one out bootstraping method by using boot package. I know the bootstrap package has this function, but it sounds not very flexible for my project. Thanks, Jim __ R-help@r-proj

Re: [R] new to repeated measures anova in R

On Mon, 5 Mar 2012 07:05:16 -0800 Tamre Cardoso wrote: > Thank you. > > I have attached the data: Dear Tamre, You have only 10 observations but 24 repeated measures. Anova() starts with a multivariate repeated-measures ANOVA and thus can't complete the analysis. Techically, you should be a

[R] installing package tkrplot

package tkrplot worked, but has broken while installing from R 2.11 to 2.14.2. it does not want to be installed anymore on a linux debian squeeze 64 system. have tried: - installing from source R: CMD INSTALL tkrplot_0.0-23.tar.gz - via synaptic: package r-cran-tkrplot - via terminal: sudo apt-get

Re: [R] new to repeated measures anova in R

On Mar 5, 2012, at 16:05 , Tamre Cardoso wrote: > Thank you. > > I have attached the data: The list software seems to have scrubbed it though... > The error message from Anova is: > >> pressure.aov = Anova(multmodel, idata=fact.idata, idesign = ~Shoe * Region, >> type="III") > Error in lin

[R] Having a problem with R installation as a shared library

Hello All, I suspect I am having a problem with my R installation, something that has to do with "--enable-R-shlib". Can someone explain if this is something that I can fix using apt-get? More specifically: I am having trouble getting installing the RHive package. I Installed R from scratch, fo

Re: [R] strange behaviour of "POSIXlt" "POSIXt" object

1L is the literal integer one, the same value as the result of as.integer(1.0). 1 is a literal double precision ("numeric") one, the same as 1.0. Bill Dunlap Spotfire, TIBCO Software wdunlap tibco.com > -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-pro

Re: [R] VAR with GARCH effect

Dear John, Thanks for your prompt response. But I can't get "rmgarch" package. Rather I got some package, "rugarch", in my search to "rmgarch". This package (rugarch), however, does not solve my problem. My question specifically is to estimate and simulate model like: x_t = A1*x_{t-1} + A2*x_{t-2

Re: [R] strange behaviour of "POSIXlt" "POSIXt" object

It means to interpret the literal as an integer rather than a double. Michael On Mar 5, 2012, at 9:41 AM, ikuzar wrote: > Hi, > I'd like to know what "L" means in "1L" in the instruction below: > for(i in 1:20){ z$mday <- z$mday + 1L ; cat(is.na(z), ": ");print(z)} > > The result : > FALSE

[R] How to identify a matrix which causes memory limit?

Hello, I am running a simulation on an old computer with memory of 512M. I constantly received a warning of "cannot allocate a vector of ...". How can I identify the matrix causing the problem? Is there any way to fix this issue? I would very appreciate your inputs. Thank you very much. Sincerel

Re: [R] Fitting & evaluating mixture of two Weibull distributions

The contribution of each observation to the logliklihood is log(p*f1(x) + (1-p)*f2(x)) where f1 and f2 are the two density functions. Just sum. The standard likelihood ratio test is problematic here, as there are two parametrizations that reduce the mixture model to a single compone

Re: [R] strange behaviour of "POSIXlt" "POSIXt" object

Hi, I'd like to know what "L" means in "1L" in the instruction below: for(i in 1:20){ z$mday <- z$mday + 1L ; cat(is.na(z), ": ");print(z)} The result : FALSE : [1] "2009-02-26 06:30:00" FALSE : [1] "2009-02-27 06:30:00" FALSE : [1] "2009-02-28 06:30:00" FALSE : [1] "2009-03-01 06:30:00" FALSE :

Re: [R] new to repeated measures anova in R

Thank you. I have attached the data: The error message from Anova is: > pressure.aov = Anova(multmodel, idata=fact.idata, idesign = ~Shoe * Region, > type="III") Error in linearHypothesis.mlm(mod, hyp.matrix, SSPE = SSPE, idata = idata, : The error SSP matrix is apparently of deficient

Re: [R] Random and fixed effect in linear model

Homework? We don't do homework here. Otherwise, I suggest that you continue to use SPSS, as you do not seem willing to make the effort to learn R. -- Bert On Mon, Mar 5, 2012 at 3:23 AM, Fernando Pistón wrote: > Hello everybody, > > >  This is my firth question in this mailing list. The questio

[R] Nagelkerke R2

Dear R community. I´m working with a generalized linear model which the response variable is a categorical one and the predictive variables are weather conditions. I have 250 different places where I need to fit the model. In some of these places I have strong correlations between some of the var

Re: [R] new to repeated measures anova in R

Dear Tamre, You didn't include your data, nor show the error produced with Anova() in car by idesign = ~Shoe*Region. Your data appear to have the same structure as the O'Brien-Kaiser example in ?Anova, but without the between-subject design. I have no trouble producing a two-way within-subject ANO

Re: [R] 回复： Bayesian Hidden Markov Models

Dear james, There is an argument to RJaCGH() named var.equal that sets equal variances to each hidden state. The default is TRUE, so you might want to set it as FALSE. Cheers, Oscar On 3/3/12 02:20, "monkeylan" wrote: > Dear Oscar, > > I have used the the following codes to perform a Bayes

[R] cauchy process

Hi, How can be Cauchy process construct in R? is there any code or algorithm? thanks a lot [[alternative HTML version deleted]] __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide ht

Re: [R] Vector errors and missing values

Hi Petr, Thank you so much for your help. You're right, the issue was that I needed to center my predictors by adding the code 'na.rm=T': verbal.ability_C <- verbal.ability - mean(verbal.ability, na.rm=T) That removed the NA values from being included in my centering and allowed me to run the r

  1   2   >