0% found this document useful (0 votes)
33 views10 pages

Binomial and Poisson Probability Distributions

This document provides an overview of the binomial and Poisson probability distributions. It defines the binomial distribution as the probability of obtaining m successes in N trials of a Bernoulli process with probability p of success. Key properties discussed include the mean being Np and variance being Npq. The Poisson distribution is introduced as applying to rare events with a large number of trials and small probability p. It has a mean and variance both equal to λ, the expected number of occurrences. Examples are given comparing the binomial and Poisson distributions for different values of N and p/λ.

Uploaded by

M Jameel Mydeen
Copyright
© Attribution Non-Commercial (BY-NC)
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
0% found this document useful (0 votes)
33 views10 pages

Binomial and Poisson Probability Distributions

This document provides an overview of the binomial and Poisson probability distributions. It defines the binomial distribution as the probability of obtaining m successes in N trials of a Bernoulli process with probability p of success. Key properties discussed include the mean being Np and variance being Npq. The Poisson distribution is introduced as applying to rare events with a large number of trials and small probability p. It has a mean and variance both equal to λ, the expected number of occurrences. Examples are given comparing the binomial and Poisson distributions for different values of N and p/λ.

Uploaded by

M Jameel Mydeen
Copyright
© Attribution Non-Commercial (BY-NC)
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/ 10

Lecture 2 Binomial and Poisson Probability Distributions

Binomial Probability Distribution


l

Consider a situation where there are only two possible outcomes (a Bernoulli trial) H Example: u flipping a coin + head or tail u rolling a dice + 6 or not 6 (i.e. 1, 2, 3, 4, 5) H Label the possible outcomes by the variable k + find the probability P(k) for event k to occur H Since k can take on only 2 values we define those values as: k = 0 or k = 1 u let P(k = 0) = q (remember 0 q 1) u something must happen + P(k = 0) + P(k = 1) = 1 + P(k = 1) = p = 1 - q u write the probability distribution P(k) as: P(k) = pkq1-k (Bernoulli distribution) u coin toss: define probability for a head as P(1) + P(1) = 0.5 u dice rolling: define probability for a six to be rolled as P(1) + P(1) = 1/6 + P(0) = 5/6 (not a six)
K.K. Gan L2: Binomial and Poisson 1

What is the mean (m) of P(k)?


kP (k )
0 m = k= = 1 P (k ) k =0
1

0 q +1 p =p q+ p

What is the Variance (s2) of P(k)?

s 2 = k =0 - m 2 = 0 2 P (0) + 12 P (1) - m 2 = p - p 2 = p(1 - p) = pq 1 P (k )


Suppose we have N trials (e.g. we flip a coin N times) + what is the probability to get m successes (= heads)? Consider tossing a coin twice. The possible outcomes are: H no heads: P(m = 0) = q2 H one head: P(m = 1) = qp + pq (toss 1 is a tail, toss 2 is a head or toss 1 is head, toss 2 is a tail) = 2pq two outcomes because we don't care which of the tosses is a head 2 H two heads: P(m = 2) = p H P(0) + P(1) + P(2) = q2 + 2pq + p2 = (q + p)2 = 1 We want the probability distribution function P(m, N, p) where: m = number of success (e.g. number of heads in a coin toss) N = number of trials (e.g. number of coin tosses) p = probability for a success (e.g. 0.5 for a head)
k =0

k 2 P (k )

K.K. Gan

L2: Binomial and Poisson

If we look at the three choices for the coin flip example, each term is of the form: CmpmqN-m m = 0, 1, 2, N = 2 for our example, q = 1 - p always! H coefficient Cm takes into account the number of ways an outcome can occur regardless of order H for m = 0 or 2 there is only one way for the outcome (both tosses give heads or tails): C0 = C2 = 1 H for m = 1 (one head, two tosses) there are two ways that this can occur: C1 = 2. l Binomial coefficients: number of ways of taking N things m at time N! CN ,m = N m = m!( N - m )! H 0! = 1! = 1, 2! = 12 = 2, 3! = 123 = 6, m! = 123m H Order of things is not important u e.g. 2 tosses, one head case (m = 1) n we don't care if toss 1 produced the head or if toss 2 produced the head H Unordered groups such as our example are called combinations H Ordered arrangements are called permutations H For N distinguishable objects, if we want to group them m at a time, the number of permutations: N! PN ,m = ( N - m )! u example: If we tossed a coin twice (N = 2), there are two ways for getting one head (m = 1) u example: Suppose we have 3 balls, one white, one red, and one blue. n Number of possible pairs we could have, keeping track of order is 6 (rw, wr, rb, br, wb, bw): 3! P3,2 = =6 (3 - 2)! n If order is not important (rw = wr), then the binomial formula gives 3! C3,2 = =3 number of two-color combinations 2!(3 - 2)! K.K. Gan L2: Binomial and Poisson 3
l

( )

Binomial distribution: the probability of m success out of N trials: N! m N -m P (m, N , p) = CN ,m p m q N -m = N = p m q N -m m p q m!( N - m )! u p is probability of a success and q = 1 - p is probability of a failure u Consider a game where the player bats 4 times: H probability of 0/4 = (0.67)4 = 20% 1 3 H probability of 1/4 = [4!/(3!1!)](0.33) (0.67) = 40% H probability of 2/4 = [4!/(2!2!)](0.33)2(0.67)2 = 29% 3 1 H probability of 3/4 = [4!/(1!3!)](0.33) (0.67) = 10% H probability of 4/4 = [4!/(0!4!)](0.33)4(0.67)0 = 1% H probability of getting at least one hit = 1 - P(0) = 0.8

( )

0.40

0.14

0.30
P (k , 7, 1/3)

Expectation Value m = np = 7 * 1/3 = 2.333...


P (k , 50, 1/3)

0.12 0.10 0.08 0.06 0.04 0.02

Expectation Value m = np = 50 * 1/3 = 16.667...

0.20

0.10

0.00 0 2 4 k 6 8 10

0.00 0 5 10 15 k 20 25 30

K.K. Gan

L2: Binomial and Poisson

To show that the binomial distribution is properly normalized, use Binomial Theorem:
( a + b) =
N k k l=0 N

( )a
k l N m

k -l l

P (m, N , p) =
m=0
+ l

m=0

( )p
N

m N -m

= ( p + q)N = 1

binomial distribution is properly normalized Mean of binomial distribution:


mP (m, N , p)
N 0 m = m= = mP (m, N , p) = m N m=0 P (m, N , p) m=0
H

( )p
N m

m N -m

A cute way of evaluating the above sum is to take the derivative: N N m N -m m p q = 0 p m=0

m=0

( )

m
m=0

( )p
N m

m-1 N - m

-
m=0 N m

( )p
N m m

( N - m )(1 - p) N -m-1 = 0
N -m

-1

m
m=0

( )p
N m

m N -m

= N (1 - p)

-1

m=0

( )p

(1 - p)

- (1 - p)

-1

m
m=0

( )p
N m

(1 - p) N -m

p -1m = N (1 - p)-1 1 - (1 - p)-1 m m = Np

K.K. Gan

L2: Binomial and Poisson

Variance of binomial distribution (obtained using similar trick):

s 2 = m=0

(m - m )2 P (m, N , p) P (m, N , p)
m=0 N

= Npq

Example: Suppose you observed m special events (success) in a sample of N events u measured probability (efficiency) for a special event to occur: m e= N u error on the probability ("error on the efficiency"): Npq s Ne (1 - e ) e (1 - e ) se = m = = = N N N N + sample (N) should be as large as possible to reduce uncertainty in the probability measurement H Example: Suppose a baseball player's batting average is 0.33 (1 for 3 on average). u Consider the case where the player either gets a hit or makes an out (forget about walks here!). probability for a hit: p = 0.33 probability for no hit: q = 1 - p = 0.67 u On average how many hits does the player get in 100 at bats? m = Np = 1000.33 = 33 hits u What's the standard deviation for the number of hits in 100 at bats? s = (Npq)1/2 = (1000.330.67)1/2 4.7 hits + we expect 33 5 hits per 100 at bats
H

K.K. Gan

L2: Binomial and Poisson

Poisson Probability Distribution


l l

A widely used discrete probability distribution Consider the following conditions: H p is very small and approaches 0 u example: a 100 sided dice instead of a 6 sided dice, p = 1/100 instead of 1/6 u example: a 1000 sided dice, p = 1/1000 H N is very large and approaches u example: throwing 100 or 1000 dice instead of 2 dice H product Np is finite Example: radioactive decay H Suppose we have 25 mg of an element + very large number of atoms: N 1020 H Suppose the lifetime of this element l = 1012 years 5x1019 seconds + probability of a given nucleus to decay in one second is very small: p = 1/l = 2x10-20/sec + Np = 2/sec finite! + number of counts in a time interval is a Poisson process Poisson distribution can be derived by taking the appropriate limits of the binomial distribution N! P (m, N , p) = p m q N -m m!( N - m )! N! N ( N - 1) ( N - m + 1)( N - m )! = = Nm ( N - m )! ( N - m )!
q
N -m

= (1 - p)

N -m

p 2 ( N - m )( N - m - 1) ( pN )2 = 1 - p( N - m ) + + 1 - pN + + e- pN 2! 2!
L2: Binomial and Poisson 7

K.K. Gan

N m m - pN P (m, N , p) = p e m! Let m = Np e -m m m P (m, m ) = m!

Poisson distribution is normalized m ! m ! m=0 m=0 u m is always an integer 0 u m does not have to be an integer H It is easy to show that: m = Np = mean of a Poisson distribution mean and variance are the same number s2 = Np = m = variance of a Poisson distribution l Radioactivity example with an average of 2 decays/sec: H Whats the probability of zero decays in one second? e-2 2 0 e-2 1 -2 p(0,2) = = = e = 0.135 13.5% 0! 1 H Whats the probability of more than one decay in one second? e-2 2 0 e-2 21 p(> 1,2) = 1 - p(0,2) - p(1,2) = 1 = 1 - e-2 - 2e-2 = 0.594 59.4% 0! 1! H Estimate the most probable number of decays/sec? P (m, m ) = 0 m m*
K.K. Gan L2: Binomial and Poisson 8

m= e -m m m

=e

-m

m= m m

= e -m e m = 1

To solve this problem its convenient to maximize lnP(m, m) instead of P(m, m). e-m m m ln P (m, m ) = ln = -m + m ln m - ln m! m! In order to handle the factorial when take the derivative we use Stirling's Approximation: ln m! m ln m - m ln P (m, m ) = (-m + m ln m - ln m!) m m (-m + m ln m - m ln m + m ) m 1 = ln m - ln m - m + 1 m =0
m* = m The most probable value for m is just the average of the distribution If you observed m events in an experiment, the error on m is s = m = m This is only approximate since Stirlings Approximation is only valid for large m. Strictly speaking m can only take on integer values while m is not restricted to be an integer.

+ +

u u

K.K. Gan

L2: Binomial and Poisson

Comparison of Binomial and Poisson distributions with mean m = 1

0.5 0.4

0.4 0.35

Probability

Probability

0.3 0.2 0.1 0 0 1

poisson m=1 binomial N=3,

0.3
p=1/3

0.25 0.2 0.15 0.1 0.05

binomial N=10,p=0.1 poisson m=1

Not much difference between them!

2 m 3

0.0

1.0

2.0

3.0

4.0

5.0

6.0

7.0

For large N: Binomial distribution looks like a Poisson of the same mean

K.K. Gan

L2: Binomial and Poisson

10

You might also like