## certified RNGs

Posted in Statistics with tags , , , , , , , on April 27, 2020 by xi'an

A company called Gaming Laboratories International (GLI) is delivering certificates of randomness. Apparently using Marsaglia’s DieHard tests. Here are some unforgettable quotes from their webpage:

“…a Random Number Generator (RNG) is a key component that MUST be adequately and fully tested to ensure non-predictability and no biases exist towards certain game outcomes.”

“GLI has the most experienced and robust RNG testing methodologies in the world. This includes software-based (pseudo-algorithmic) RNG’s, Hardware RNG’s, and hybrid combinations of both.”

“GLI uses custom software written and validated through the collaborative effort of our in-house mathematicians and industry consultants since our inception in 1989. An RNG Test Suite is applied for randomness testing.”

“No lab in the world provides the level of iGaming RNG assurance that GLI does. Don’t take a chance with this most critical portion of your iGaming system.”

## The answer is e, what was the question?!

Posted in Books, R, Statistics with tags , , , , , on February 12, 2016 by xi'an

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 restriction, it is straightforward to think of a Monte Carlo average that converges to e as the number of simulations grows to infinity. However, such methods like Poisson and normal simulations require some complex functions like sine, cosine, or exponential… But then someone came up with a connection to the great Russian probabilist Gnedenko, who gave as an exercise that the average number of uniforms one needs to add to exceed 1 is exactly e, because it writes as

$\sum_{n=0}^\infty\frac{1}{n!}=e$

(The result was later detailed in the American Statistician as an introductory simulation exercise akin to Buffon’s needle.) This is a brilliant solution as it does not involve anything but a standard uniform generator. I do not think it relates in any close way to the generation from a Poisson process with parameter λ=1 where the probability to exceed one in one step is e⁻¹, hence deriving  a Geometric variable from this process leads to an unbiased estimator of e as well. As an aside, W. Huber proposed the following elegantly concise line of R code to implement an approximation of e:

1/mean(n*diff(sort(runif(n+1))) > 1)

Hard to beat, isn’t it?! (Although it is more exactly a Monte Carlo approximation of

$\left(1-\frac{1}{n}\right)^n$

which adds a further level of approximation to the solution….)

## Buffon needled R exams

Posted in Books, Kids, R, Statistics, University life with tags , , , , , , , on November 25, 2013 by xi'an

Here are two exercises I wrote for my R mid-term exam in Paris-Dauphine around Buffon’s needle problem. In the end, the problems sounded too long and too hard for my 3rd year students so I opted for softer questions. So recycle those if you wish (but do not ask for solutions!)

## cannonball approximation to pi

Posted in Statistics with tags , , , , , on October 8, 2011 by xi'an

This year, my daughter started writing algorithms in her math class (she is in seconde, which could correspond to the 10th grade). The one she had to write down last weekend was Buffon’s neddle and the approximation of π by Monte Carlo (throwing cannon balls was not mentioned!). Here is the short R code I later wrote to show her the outcome (as the class has not yet learned a computer language):

n=10^6
counter=0
#uniforms over the unit square
ray=runif(n)^2+runif(n)^2
#proportion within the quarter circle
conv=cumsum((ray<1))/(1:n)
plot(conv,type="l",col="steelblue",ylim=c(pi/4-2/sqrt(n),
pi/4+2/sqrt(n)),xlab="n",ylab="proportion")
abline(h=pi/4,col="gold3")


and here is an outcome of the convergence of the approximation to π/4:

## Buffon versus Bertrand in R

Posted in R, Statistics with tags , , , on April 8, 2011 by xi'an

Following my earlier post on Buffon’s needle and Bertrand’s paradox, above are four outcomes corresponding to four different generations (among many) of the needle locations. The upper right-hand side makes a difference in the number of hits (out of 1000). The R code corresponding to this generation was made in the métro, so do not expect subtlety: Continue reading