Publications by xi'an
The answer is e, what was the question?!
A rather exotic question on X validated: since π can be approximated by random sampling over a unit square, is there an equivalent for approximating e? This is an interesting question, as, indeed, why not focus on e rather than π after all?! But very quickly the very artificiality of the problem comes back to hit one in one’s face… With no ...
2129 sym 10 img
new version of abcrf
Version 1.1 of our R library abcrf version 1.1 is now available on CRAN. Improvements against the earlier version are numerous and substantial. In particular, calculations of the random forests have been parallelised and, for machines with multiple cores, the computing gain can be enormous.Filed under: R, Statistics, University life Tagged:...
815 sym 6 img
Гнеде́нко and Forsythe [and e]
In the wake of my earlier post on the Monte Carlo estimation of e and e⁻¹, after a discussion with my colleague Murray Pollock (Warwick) Gnedenko’s solution, he pointed out another (early) Monte Carlo approximation called Forsythe’s method. That is detailed quite neatly in Luc Devroye’s bible, Non-uniform random variate generation (a fre...
2336 sym R (418 sym/1 pcs) 8 img
R colours
As I am always fishing for colour names in R, I looked for an easy summary of those names and found this table on New Energy Research blog, which I reproduce here for [my] future access. Filed under: pictures, R Tagged: colors(), colours(), R Related To leave a comment for the author, please follow the link and comment on their blog: R –...
642 sym 6 img
more e’s [and R’s]
Alex Thiéry suggested debiasing the biased estimate of e by Rhee and Glynn truncated series method, so I tried the method to see how much of an improvement (if any!) this would bring. I first attempted to naïvely implement the raw formula of Rhee and Glynn with a (large) Poisson distribution on the stopping rule N, but this took ages. I then r...
2967 sym R (1034 sym/5 pcs) 10 img
twilight zone [of statistics]
“I have decided that mixtures, like tequila, are inherently evil and should be avoided at all costs.” L. Wasserman Larry Wasserman once remarked that finite mixtures were like the twilight zone of statistics, thanks to the numerous idiosyncrasies associated with such models. And George Casella had similar strong reservations about mixture es...
4996 sym 16 img
Amazonish warning
As in previous years, I want to repost a warning to ‘Og readers that all http links to Amazon.com [and much more rarely to Amazon.fr] products found on this ‘Og are actually susceptible to reward me with an advertising percentage if a purchase is made by the reader in the 24 hours following the entry on Amazon through this link, thanks to the...
1907 sym 4 img
preserving frequencies without resampling
An interesting question came up on X validated a few days ago: given a probability vector p=(p¹,…,p⁷), is there a way to pick 5 values in {1,…,7} without replacement and still preserve the probability repartition in the resulting sample? In other words, is there a sampling without replacement strategy that leads to for i=1,…,7..? Unless...
2170 sym R (207 sym/1 pcs) 10 img
Le Monde puzzle [#952]
A quite simple Le Monde mathematical puzzle again with Alice and Bob: In a multiple choice questionnaire with 50 questions, Alice gets a score s such that Bob can guess how many correct (+5 points), incorrect (-1 point) and missing (0 point) Alice got when adding that Alice could not have gotten s-2 or s+2. What is Alice’s score? A first poin...
1322 sym R (161 sym/2 pcs) 6 img
Le Monde puzzle [#954]
A square Le Monde mathematical puzzle: Given a triplet (a,b,c) of integers, with a? Can you find the triplet (a,b,c) that produces the sum a+b+c closest to 1000? This is a rather interesting challenge and a brute force resolution does not produce interesting results. For instance, using the function is.whole from the package Rpmfr, the R functi...
1280 sym R (772 sym/4 pcs) 6 img