views:

2773

answers:

4

i've been looking around, but i'm not sure how to do it.

i've found this page which, in the last paragraph, says:

A simple generator for random numbers taken from a Poisson distribution is obtained using this simple recipe: if x1, x2, ... is a sequence of random numbers with uniform distribution between zero and one, k is the first integer for which the product x1 · x2 · ... · xk+1 < e

i've found another page describing how to generate binomial numbers, but i think it is using an approximation of poisson generation, which doesn't help me.

For example, consider binomial random numbers. A binomial random number is the number of heads in N tosses of a coin with probability p of a heads on any single toss. If you generate N uniform random numbers on the interval (0,1) and count the number less than p, then the count is a binomial random number with parameters N and p.

i know there are libraries to do it, but i can't use them, only the standard uniform generators provided by the language (java, in this case).

+15  A: 

Poisson distribution

Here's how Wikipedia says Knuth says to do it:

init:
     Let L ← e^(−λ), k ← 0 and p ← 1.
do:
     k ← k + 1.
     Generate uniform random number u in [0,1] and let p ← p × u.
while p > L.
return k − 1.

In Java, that would be:

public static int getPoisson(double lambda) {
  double L = Math.exp(-lambda);
  double p = 1.0;
  int k = 0;

  do {
    k++;
    p *= Math.random();
  } while (p > L);

  return k - 1;
}


Binomial distribution

Going by chapter 10 of Non-Uniform Random Variate Generation (PDF) by Luc Devroye (which I found linked from the Wikipedia article) gives this:

public static int getBinomial(int n, double p) {
  int x = 0;
  for(int i = 0; i < n; i++) {
    if(Math.random() < p)
      x++;
  }
  return x;
}


Please note

Neither of these algorithms is optimal. The first is O(λ), the second is O(n). Depending on how large these values typically are, and how frequently you need to call the generators, you might need a better algorithm. The paper I link to above has more complicated algorithms that run in constant time, but they are more than I'm willing to translate into Java for 15 rep points (sorry).

Kip
+1 very nice answer
dfa
+2  A: 

Commons math has a PoissonDistribution class and a BinomialDistribution class you can compare these sources with your classes.

Reading, studying and understaing other's people code is a very important activity for every serious developer.

dfa
+2  A: 

For this and other numerical problems the bible is the numerical recipes book.

There's a free version for C here: http://www.nrbook.com/a/bookcpdf.php (plugin required)

Or you can see it on google books: http://books.google.co.uk/books?id=4t-sybVuoqoC&amp;lpg=PP1&amp;ots=5IhMINLhHo&amp;dq=numerical%20recipes%20in%20c&amp;pg=PP1#v=onepage&amp;q=&amp;f=false

The C code should be very easy to transfer to Java.

This book is worth it's weight in gold for lots of numerical problems. On the above site you can also buy the latest version of the book.

Pablojim
The Numerical Recipes book isn't free. You need to have a password to unlock the PDF files.
Jay R.
+1  A: 

There are several implementations from CERN in the following library (Java code):

http://acs.lbl.gov/~hoschek/colt/

Concerning binomial random numbers, it is based on the paper from 1988 "Binomial Random Variate Generation", that I recommend to you since they use an optimized algorithm.

Regards

Miguel Ángel Martínez