Revise Smart

The poisson distribution

Posted in Maths, Statistics 2
Contents

The poisson distribution is a probability distribution for the number of occurrences of a rare event. In general, the probability of a variable X, which is modelled by the poission distribution, being equal to the value r is given by:

Dynamic image 0

Where Dynamic image 1 is the mean[/expr]$

The poission distrubution can be used to model situations where the occurences are independent and random and there is a known mean for the occurences

Notation

If the random variable X is modelled by the Poisson distribution with a mean Dynamic image 1 then it is notated as:

Dynamic image 3

As an approximation to the binomial distribution

The poission distribution can be used an approxmiation to the binnomial distribution, B(n, p) when n is large and p is small.

Mean

To mean of the poission distribution approximation of a binomial distribution is Dynamic image 4

Variance

The variance for the binomial distribution, B(n, p) is given by npq where q is (1 - p). Generally p is small enough such that q = 1 and hence the variance is just np. Therefore the variance is the same as the mean, np.

Cumulative probabilities

When finding a cumulative probability, for example P(X ≤ 4) you can either find and add together P(X = 0), P(X = 1) ... (P = 4). Alternatively you can use the poisson probability tables. Using these you find the value of (P ≤ 4) straight away by finding the value corresponding to the column of the mean and row of your value r.

To find, for example, P(X ≥ 5) simply find 1 - P(X ≤ 4)

Sum of poisson distributions

The sum of two or more poisson distributions is also a poisson distribution, with the mean being the sum of the all the other means:

Dynamic image 5

© 2009 Revise Smart