Scribd
Upload
28 views12 pages

Discrete Distributions: 1. Bernoulli Distribution

This document summarizes four discrete probability distributions: the Bernoulli, binomial, geometric, and Poisson distributions. It defines each distribution and provides their possible values, parameters, probability mass functions, expected values, and variances. The Bernoulli distribution models a binary outcome with probability of success p. The binomial distribution models the number of successes in n independent Bernoulli trials with probability of success p. The geometric distribution models the number of Bernoulli trials until the first success, with probability of success p. Lastly, the Poisson distribution models the number of rare, independent events occurring in an interval of time with average rate λ.

Uploaded by

palak singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
28 views12 pages

Discrete Distributions: 1. Bernoulli Distribution

This document summarizes four discrete probability distributions: the Bernoulli, binomial, geometric, and Poisson distributions. It defines each distribution and provides their possible values, parameters, probability mass functions, expected values, and variances. The Bernoulli distribution models a binary outcome with probability of success p. The binomial distribution models the number of successes in n independent Bernoulli trials with probability of success p. The geometric distribution models the number of Bernoulli trials until the first success, with probability of success p. Lastly, the Poisson distribution models the number of rare, independent events occurring in an interval of time with average rate λ.

Uploaded by

palak singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

DISCRETE

DISTRIBUTIONS
1. Bernoulli distribution
X = 0 or 1

Generic name:

(pass / fail)
(ok / defective)
(no error / error)
(not infected / infected)
(transmitted / lost)
(successes / failures)

Called: Bernoulli trial (binary outcome)


X has Bernoulli pmf
p(0) = 1 p,

p(1) = p

So, there is a whole family of Bernoulli distributions,


Bern(p)
1

Discrete distributions

2. Binomial distribution
X = number of successes in n independent
Bernoulli trials
Possible values: X {0, 1, . . . , n}

Binomial pmf:

n x
p(x) = ( ) p (1p)nx,
x

x = 0, 1, ..., n
where
px = probability of x successes,
(1 p)nx = probability of (n x) failures,
n!
n
= number of outcomes
) =
x
x!(n x)!
with exactly x successes and (n x) failures
(

Binomial distribution

There is a family of Binomial distributions,


Bin(n,p)
n, p = parameters
n = number of trials
p = probability of success
Applications:
number of defective items in a sample
number of successful jobs
number of passing students
number of days without an accident
number of correct answers
3

Binomial distribution

Relation between Bern(p) and Bin(n,p)


If X1, ..., Xn are independent Bern(p) variables,
then
X=

Xk is Bin(n, p)

For n = 1, Bin(1,p) is Bern(p).

Discrete distributions

3. Geometric distribution
X1, X2, ... ... ... = independent Bernoulli trials
X = the first successful trial
= number of trials needed
to see the first success
X has Geometric distribution with pmf
p(x) = P {X = x}
= P {(x 1) failures, then 1 success}
p(x) = (1 p)x1p
x = 1, 2, 3, ...
Example: St. Petersburg paradox
5

Discrete distributions

4. Poisson distribution
X = number of rare events
(two events are unlikely to occur during a short
period)
Examples:
Number
Number
Number
Number
Number
Number

of
of
of
of
of
of

arrived jobs
telephone calls
claims
errors
accidents
customers

Poisson distribution

Poisson pmf:
x

p(x) = e
x!
x = 0, 1, 2, ...
= intensity parameter, average number of
events per unit of time

Poisson distribution

Poisson approximation of the Binomial


distribution
If p is small (< 0.05)
and n is large ( 30)
so that np = , then
Bin(n, p) P oisson()

If p > 0.95 then (1 p) < 0.05, and


Bin(n, 1 p) P oisson(n(1 p))

Mathematically,
lim

p0

n!
x
x
nx

p (1 p)
=e

x!(n x)!
x!

np
8

Poisson distribution

Examples
n = 2 mln. people in DFW area
{

p=P

a person calls NY
today

= 7.5 105

= np = 150
Then X = number of calls from DFW to NY
is
Bin(2 106, 7.5 105) P oisson(150)

Poisson distribution

X = number of accidents during rush hours


n = 10800 seconds during 3 evening rush hours
p = 0.00015 = probability of an accident during any given second
Then
X is P oisson(),
where = np = 1.62, the average number of
accidents

10

Summary of Discrete Distributions

Distribution
family

Description

Possible
values

Bernoulli

0 or 1,
success
or failure

0, 1

Binomial

Number of
successes in
n Bernoulli
trials

0, . . . , n

number
of trials
prob. of
p =
success

Number of
trials
until
success

1, 2, . . .

p =

prob. of
success

Number
of rare
events

0, 1, . . .

frequency
of events

Geometric

Poisson

Parameters

p =

prob. of
success

n =

Summary of Discrete Distributions

Distribution
family

P.M.F. P (x)

E(X)

Var(X)

Bernoulli

P (0) = 1 p
P (1) = p

p(1 p)

Binomial

n x
) p (1 p)nx
x
for x = 0, 1, . . . , n

np

np(1 p)

(1 p)x1p
for x = 1, 2, . . .

1
p

1p
p2

Geometric

Poisson

x!
for x = 0, 1, . . .

You might also like