Hypergeometric Distribution - Order of Draws

Order of Draws

The probability of drawing any sequence of white and black marbles (the hypergeometric distribution) depends only on the number of white and black marbles, not on the order in which they appear; i.e., it is an exchangeable distribution. As a result, the probability of drawing a white marble in the draw is

This can be shown by induction. First, it is certainly true for the first draw that:

.

Also, we can show that by writing:

begin{align} P(W_{n+1}) & = {sum_{k=0}^n}P(W_{n+1}|k)f(k;N,m,n)\ & = {sum_{k=0}^n}frac{m-k}{N-n}f(k;N,m,n) \ & = {sum_{k=0}^n}frac{m-k}{N-n}frac{binom mk binom {N-m} {n-k}}{binom Nn} \ & = frac{1}{(N-n)binom Nn} left { msum_{k=0}^n binom mk binom {N-m} {n-k} - sum_{k=0}^n kbinom mk binom {N-m} {n-k}right } \ & = frac{1}{(N-n)binom Nn}left{ mbinom Nn - sum_{k=1}^n kfrac{m}{k} binom {m-1}{k-1} binom {N-m} {n-k}right } \ & = frac{m}{(N-n)binom Nn}left{ binom Nn - sum_{k=1}^n binom {m-1}{k-1} binom {N-1-(m-1)} {n-1-(k-1)}right } \ & = frac{m}{(N-n)binom Nn}left{ binom Nn - binom {N-1}{n-1}right } \ & = frac{m}{(N-n)binom Nn}left{ binom Nn - frac{n}{N}binom Nnright } \ & = frac{m}{(N-n)}left{ 1 - frac{n}{N} right} = frac{m}{N} end{align} ,

which makes it true for every draw.

A simpler proof than the one above is the following:

By symmetry each of the marbles has the same chance to be drawn in the draw. In addition, according to the sum rule, the chance of drawing a white marble in the draw can be calculated by summing the chances of each individual white marble being drawn in the . These two observations imply that if for example the number of white marbles at the outset is 3 times the number of black marbles, then also the chance of a white marble being drawn in the draw is 3 times as big as a black marble being drawn in the draw. In the general case we have white marbles and black marbles at the outset. So

.

Since in the draw either a white or a black marble needs to be drawn, we also know that

.

Combining these two equations immediately yields

.

Read more about this topic:  Hypergeometric Distribution

Famous quotes containing the words draws and/or order:

    “With crayons the child draws a rigid house
    and a winding pathway. Then the child
    puts in a man with buttons like tears”
    —Elizabeth Bishop (1911–1979)

    “However, the danger in [socially unbalanced relationships] is that the subjection of the woman temporarily calms the man’s jealousy but also renders it more demanding. He ends up making his mistress live like those prisoners on whom light is shone day and night in order for them to be better watched. And things always end in tragedy.”
    —Marcel Proust (1871–1922)