similar to: Which function can change RNG state?

On Wed, 19 Sep 2018 at 13:43, Duncan Murdoch <murdoch.duncan at gmail.com> wrote: > > I think the analyses are correct, but I doubt if a change to the default > is likely to be accepted as it would make it more difficult to reproduce > older results. I'm a bit alarmed by the logic here. Unbiased sampling seems basic for a statistical language. As a consumer of R I'd

Hi, Our department has detected a bug in the implementation of the Kinderman-Ramage generator for normal random variates in version 1.7.0, which can be seen from the below R session. (Consecutive calls for chisq.test(...) always gives p-values very close to 0.) We have already encountered this bug in version 1.6.2 The error is in file R-1.7.0/src/nmath/snorm.c Here is a patch for this file to

On 08/30/2016 06:29 PM, Duncan Murdoch wrote: > I don't see evidence of a bug. There have been several versions of the > MT; we may be using a different version than you are. Ours is the > 1999/10/28 version; the web page you cite uses one from 2002. > > Perhaps the newer version fixes some problems, and then it would be > worth considering a change. But changing the

On 7 February 2015 at 19:52, otoomet wrote: | random numbers. For instance, can I be sure that | set.seed(0); print(runif(1)); print(rnorm(1)) | will always print the same numbers, also in the future version of R? There Yes, pretty much. I've been lurking here over fifteen years, and while I am getting old and forgetful I can remember exactly one such change where behaviour was changed,

Unfortunately, RNGkind is buggy. It will not generate warnings except the full name "Buggy Kinderman-Ramage" is supplied for normal.kind. match.arg is supposed to be called before "==" comparison. ======================================== Shengqiao Li Research Associate The Department of Statistics PO Box 6330 West Virginia University Morgantown, WV 26506-6330

Whomever, I recently sent the "bug report" below toR-core at r-project.org and have just been asked to instead submit it to you. Although I am basically not an R user, I have installed version 3.3.1 and am also the author of a statistics program written in Visual Basic that contains a component which correctly implements the Mersenne Twister (MT) algorithm. I believe that it is

On 09/19/2018 10:03 AM, Ben Bolker wrote: ... > Balancing backward compatibility and correctness is a tough problem > here. I think improvements in the RNG is a situation where backward compatibility is not really going to be lost, because people can specify the old generator, they just will not get it by default. My opinion is that the default needs to generally be the best option

Hi All, I have k identical parallel pieces of code running, each using n.rand random numbers.? I would like to use the same RNG (for now), and set the seeds so that I can guarantee that there are no overlaps in the random numbers sampled by the k pieces of code.? Another side goal is to have reproducibility of my results.? In?the past I have used C with SPRNG for this task, but I'm hoping

I'm running into problems with set.seed--maybe I'm misunderstanding something. I'm running R 1.5.1 on Windows 2000. I'm basically trying to capture the random seed so that I can reproduce a simulation if it's necessary later. Using set.seed, I can certainly get reproducible results, but not the results I get on the first pass. Here's an example: # Generate a random

On 30 August 2016 at 18:29, Duncan Murdoch wrote: | I don't see evidence of a bug. There have been several versions of the | MT; we may be using a different version than you are. Ours is the | 1999/10/28 version; the web page you cite uses one from 2002. | | Perhaps the newer version fixes some problems, and then it would be | worth considering a change. But changing the default RNG

There seems to be a minor problem with reproducing numbers from rnorm with Box-Muller. The pattern suggests it might have something to do with the value that gets dropped when an odd number of numbers is requested. (Details below.) Also, could "user-supplied" be added as an option for normal.kind in RNGkind. I'm sure the Box-Muller in R is better than my own attempt, but I would

Hello everyone. If I do f <- function(n){max(rnorm(n))} plot(sapply(rep(5000,4000),f)) #[this takes my PC about 30 seconds] then I get something quite unexpected: gaps in the distribution. For me, the most noticable one is at about 3.6. Do others get this? Is it an optical illusion? It can't be right, can it? Or maybe I just don't understand the good ol' Gaussian very

Dear R-Aficionados: I realize that no random number generator is perfect, so what I report below may be a result of that simple fact. However, if I have made an error in my thinking I would greatly appreciate being corrected. I wish to illustrate the behavior of small samples (n=10) and so generate 100,000 of them. n.samples <- 1000000 sample.size = 10 p <- 0.0001 z.normal <- qnorm(p)

This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. ---559023410-851401618-1218751024=:15885 Content-Type: TEXT/PLAIN; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE I didn't describe the problem clearly. It's about the number of distinct=20 values. So just

I wonder how useful a (set of?) "time machine" functions which look up /infer things like this based on a date would be. Could ease the pain of changes generally, though not remove it completely. ~G On Wed, Aug 31, 2016 at 5:45 PM, Paul Gilbert <pgilbert902 at gmail.com> wrote: > > > On 08/30/2016 06:29 PM, Duncan Murdoch wrote: > >> I don't see evidence of

Hello! I am performing coupling of chains in MCMC and I need the same value of seed for two chains. I will show demo of what I want: R code, which might show my example is: niter <- 3 nchain <- 2 tmpSeed <- 123 for (i in 1:niter) { # iterations for (j in 1:nchain) { # chains set.seed(tmpSeed) a <- runif(1) cat("iter:", i, "chain:", j,

On Mon, Feb 26, 2018 at 3:25 PM, Gary Black <gwblack001 at sbcglobal.net> wrote: (Sorry to be a bit slow responding.) You have not supplied a complete example, which would be good in this case because what you are suggesting could be a serious bug in R or a package. Serious journals require reproducibility these days. For example, JSS is very clear on this point. To your question >

Dear all, Recently I am generating large random samples (10M) and any duplicated numbers are not desired. We tried several RNGs in R and found Wichmann-Hill did not produce duplications. The duplication problem is the interesting birthday problem. If there are M possible numbers, randomly draw N numbers from them, the average number of dupilcations D = N(N-1)/2/M. For Knuth-TAOCP and

Hello When loading a package, I'm wondering if it's frowned upon for the package to alter the state of the random number generator? I guess not, since the parallel package does it? > set.seed(6860) > old.seed <- .GlobalEnv$.Random.seed > library(parallel) > new.seed <- .GlobalEnv$.Random.seed > identical(old.seed, new.seed) [1] FALSE I ask

I sent this to R-devel early last month, but have received no response, so I guess it really is a bug. This looks like a bug to me, and is a bit hard to describe, but easy to reproduce. ? Basically, if RNGkind is saved as something other than the default, and if the first operation in a session is a set.seed(), the default is reverted to. ?Reproduce by: cafe-rozo> ?R --vanilla R version