Discrete Probability Distributions Flashcards
Conditions of Poisson distribution
- events occur randomly, independently, and at a uniform average rate
E(X) and Var(X) in a poisson distriution
E(X) = lambda
Var(X) = lambda
Bernoulli trial
A random experiment with only two possible outcomes, success or failure.
The binomial distribution is a suitable modelling distribution if the following hold:
- each trial has only two possible outcomes, success or failure (bernouli trial)
- n is fixed
- p is fixed throughout all trials
- trials are independent of one another
Mean/expectation and variance of a binomial distribution
Mean=np
Variance=npq
When can we use a Poisson distribution to approximate the corresponding binomial distribution?
When n is large and p is small
What does the random variable Y~Geo(p) represent
The number of independent binomial trials necessary for the first success
Formula for P(X=x) for geometric distribution
p(1-p)^x-1
E(X) when x is distributed geometrically
1/p
Var(X) when X is distributed geometrically
1-p/p^2
Discrete uniform probability
Each of a finite number of values has an equal probability of occurence.
P(X=x) for discrete uniform distribution
1/n
E(X) for discrete uniform distribution
1/2 x (n+1)
Var(X) for discrete uniform distribution
1/12 x (n^2 -1)