Cutting the tail

Markiyan Hirnyk — Thu, 08 Sep 2011 00:55:39 Z

How about this?
> T := proc (N, p, q) [seq((x-1)*q^(x-2)*(p^2+(2-2*p-2*q)*p)+
binomial(x-1, x-3)*q^(x-3)*((1-p-q)^3+(1-p-q)^2*p), x = 2 .. N),
1-(sum((x-1)*q^(x-2)*(p^2+(2-2*p-2*q)*p)+
binomial(x-1, x-3)*q^(x-3)*((1-p-q)^3+(1-p-q)^2*p), x = 2 .. N))] end proc:
#We cut the tail of an infinite table.

> T(50, .3, .6): T(50, .3, .6)[50];

0.
> with(Statistics):
> d := Distribution(ProbabilityTable(T(50, .3, .6))):

> R := RandomVariable(d);

_R2
> Sample(R, 10);

Vector[row](10, {(1) = 2, (2) = 1, (3) = 4, (4) = 1, (5) = 3, (6) = 2, (7) = 1, (8) = 2, (9) = 7, (10) = 1})

MaplePrimes - answers and comments on Question, Generating Samples from a New Probability Distribution.

Cutting the tail