Sunday, September 19, 2010

Some Discrete Random Variables

From Introduction to Probability.


Discrete Uniform over [a,b]
When X can take any value from a to b(both inclusive) with equal probability.

pX(k) = 1b-a+1 if k = a, a+1, a+2, ..., b-1, b
pX(k) = 0 otherwise

E[X] = a+b2

var(X) = (b-a)(b-a+2)12


Bernoulli with Parameter p
It describes the success or failure in a single trial. For example, we can say that X = 1 if a toss results in HEAD or else X = 0 if the toss results in TAIL and probability of HEAD is p.

pX(k) = p if k = 1
pX(k) = 1-p if k = 0

E[X] = p

var(X) = p(1-p)


Binomial with Parameters p and n
It describes the number of successes in n independent bernoulli trials. For example, total number of HEADs obtained in n tosses.

pX(k) = nkpk(1-p)n-k, if k = 0,1,2,...n

E[X] = np

var(X) = np(1-p)

Also, we can use bernoulli random variables to model binomial random variable as follow.
Let X1,X2,....Xn are n independent Bernoulli Random variables with parameter p. Then
Binomial Random Variable, X = X1+X2+...+Xn


Geometric with Parameter p
It describes the number of trials until the first success, in a sequence of independent Bernoulli trials. For example, the number of tosses required to get first HEAD.

pX(k) = (1-p)k-1p, if k = 1,2,....

E[X]] = 1p

var(X) = 1-pp2


Poisson with Parameter λ
It approximates the binomial PMF when n is large and p is small and λ = np

pX(k) = e-λλkk!, k = 0,1,2...

E[X] = λ = var(X)

1 comment:

  1. Its easy to learn random and discrete variable theory but their numerical poses problem.Displacement Formula

    ReplyDelete