similar to: Residual resampling for non linear reg model

Is there a hook that allows a graphics device to apply transformations to plotmath expressions *before* they are rendered? If there isn't one yet, would it be feasible to add one? The motivation for this hook is graphic devices that feed into something that already has support for math layout, such as the tikzDevice package (which has TeX downstream). Given text(x, y,

*August 12, 2012* ** *Postdoctoral Researcher working on spatial models of marine wildlife, using R. * Integrated Statistics is looking for a post doctoral scientist to work with the Passive Acoustics Research Group and Large Whale Research Group, part of the Protected Species Branch at the Northeast Fisheries Science Center in Woods Hole, Massachusetts

R-Devel, I note from the CHANGES log accompanying the Windows version of R-2.2.0 that the behaviour with respect to the Windows registry has changed. It says: "If the user chooses to register R during installation, a registry entry HKEY_LOCAL_MACHINE\Software\R-core\R\{version}\InstallPath will be added. Users require administrative privileges to create this key. For others, the same key

Dear R-Help List, I am using optim, with method=L-BFGS-B, to maximize a likelihood inside a large simulation exercise. This runs fine for most simulated data sets, but for some reason, about 1 out of 100 times, optim will just hang. Using a dumb approach to the problem (i.e. printing the parameter values each time the function being maximized is evaluated), I tracked down when this happens,

any news? ---------- Forwarded message ---------- From: Emin Hasanov <emin@hasanov.com> Date: May 10, 2006 11:50 AM Subject: Fwd: ?????????? To: Rovshan Baghirov <rovshanb@gmail.com> Rovshan, how would you estimate this work in terms of manhours? ---------- Forwarded message ---------- From: Anar Ibrahimov < anar@autostar.az> Date: May 10, 2006 11:22 AM Subject: ??????????

> On Feb 18, 2009, at 1:41 AM, Julien Lerouge wrote: > > > Yet another _fun_ way of doing this is to setup a buildbot slave just > > for that. The slave can fix minor stuff like tabs and trailing > > whitespaces on its own (checking the changes back in), and yell for > > things like 80-col violations and whatnot where the changes would > > not be > > so

From: Les Mikesell <lesmikesell at gmail.com> > I'm still wondering about that... If anyone except Linus himself > even suggested that changing kernel interfaces in a way that would > break device drivers was a good thing, I can't imagine the reaction. > I could see that the changes through 2.4 were improving things, but > is there anything that is measurably better in

Hello list, I was hoping I could get some help on something which is really giving me a headache. I am using R version 2.14.1 (2011-12-22) (Platform: x86_64-pc-mingw32/x64 (64-bit)) An object which is supposed to have times has a few elements listed as not times but NA's > ls() [1] "todelete" > class(todelete) [1] "POSIXlt" "POSIXt" > todelete [1]

Hi. I'm a math teacher, and I would like to use Geoplan/Geospace under wine (http://appdb.winehq.org/objectManager.php?sClass=application&iId=4002). Problem is, the (non modal) dialog box behave badly. For example, as explained on the db page, the window can't be selected, no mouse action on it does anything, and worse, the property dialog can't be opened without crashing the

Hi, Is it possible to compare two GAM objects created with the gam() function from the mgcv package. I use a slightly modified version of anova.glm() named anova.gam(), modified from John Fox (2002). It often gives me some aberant responses, especially with "F" test. I use a quasibinomial model and scale (dispersion) is calculated and used in the calculation of the F value. Does someone

Dear all, I'm trying to use the Pspline add-on package to fit a quintic spline (norder =3), but I keep running into a Singularity error. > traj.spl <- smooth.Pspline(time, x, norder=3 ) Error in smooth.Pspline(time, x, norder = 3) : Singularity error in solving equations > Playing around with the other parameters produces an "unused arguments" error: > traj.spl

Recently I have been deeply troubled by evidence revealing the degree to which U.S. based corporations (well actually all resident in any of the so-called 5-eyes countries) appear to have rolled over and assumed the position with respect to NSA inspired pressure to cripple public key encryption and facilitate intrusions into their software products. This has engendered in me a significant degree

I want to use caret to build a model with an algorithm that actually has no parameters to find. How do I stop it from repeatedly building the same model 25 times? library(caret) data(mdrr) LOGISTIC_model <- train(mdrrDescr,mdrrClass ,method='glm' ,family=binomial(link="logit") ) LOGISTIC_model 528

Hi, I have a time series (say "x") of 13 years showing an evident increase. I want to exclude two observations (the fourth and 10th), so I do: > trend.test(x[-c(4,10)]) where: > x[-c(4,10)] [1] 7 37 79 72 197 385 636 705 700 1500 1900 and I get: Spearman's rank correlation rho data: x[-c(4, 10)] and time(x[-c(4, 10)]) S = 4, p-value < 2.2e-16

Hello All, I have several soundfiles that are recorded ub 44100Hz, 16-bit Mono. What is the best way and right tools to use to downsample these to 8000Hz so that they can be used with Asterisk. I've tried using sox with the -r switch and Audacity on the mac and Goldwave on Windows and they all generate files that sound like a bad acid trip. I tried increasing the speed 551.25 percent after

I am some what of a newbie at icecast administration, however, I have looked over many docs, and cant quite get what I can from a collective opinion of some experience. I am part of an net radio station, and we want to be able to have an auto stream that can run if there isn't a live DJ. I have seen a few tools, and wanted to get an opinion of something that can be started and stopped

From Sept. 25 Oct. 23, Dr. Philip Good, a former traveling lecturer for the American Statistical Association, will be giving an online seminar on practical applications of the bootstrap and permutation tests. During this 4-week internet seminar, hosted by statistics.com, participants will do interval estimation, one- , two- and k-sample comparisons, correlation, and a number of other

Dear All, I was writing a small wrapper to bootstrap a classification algorithm, but if we generate the indices in the "usual way" as: bootindex <- sample(index, N, replace = TRUE) there is a non-zero probability that all the samples belong to only one class, thus leading to problems in the fitting (or that some classes will end up with only one sample, which will be a problem

Dear all, I sample without replacement elements of a vector and generate a new vector: kl<-c(1,1,1,1,1,2,2,2,2,2,3,3,3,3,3,4,4,4,4,5,5,5,5,5,6,6,6,6,6,7,7,8,8, 8,8,8,8,8,8,8) the_index<-c(sample(40,35)) for(fs in 1:length(the_index)){if(fs==1){s<-c(kl[the_index[fs]])}else{s<- append(s, kl[the_index[fs]], after = length(s))}} I am running in BATCH mode this script in a

Hi, I have a time series (say "x") of 13 years showing an evident increase. I want to exclude two observations (the fourth and 10th), so I do: > trend.test(x[-c(4,10)]) where: > x[-c(4,10)] [1] 7 37 79 72 197 385 636 705 700 1500 1900 and I get: Spearman's rank correlation rho data: x[-c(4, 10)] and time(x[-c(4, 10)]) S = 4, p-value < 2.2e-16