Scribd
Upload
135 views4 pages

3.08 Binomial Distribution - Examples Moments PDF

The document provides information on the binomial distribution and its properties such as the mean, variance, and moment generating function (MGF). It includes the following key points: - The binomial distribution describes the number of successes in n independent yes/no experiments where the probability of success p is the same for each trial. - The mean of a binomial distribution is np. The variance is npq where q is 1-p. - The MGF of a binomial distribution is derived and used to calculate the mean and variance, verifying the formulas. - An example problem demonstrates calculating the probability, mean, variance, and MGF of the number of defective items found when randomly selecting a sample size.

Uploaded by

Deepak Chaudhary
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
135 views4 pages

3.08 Binomial Distribution - Examples Moments PDF

The document provides information on the binomial distribution and its properties such as the mean, variance, and moment generating function (MGF). It includes the following key points: - The binomial distribution describes the number of successes in n independent yes/no experiments where the probability of success p is the same for each trial. - The mean of a binomial distribution is np. The variance is npq where q is 1-p. - The MGF of a binomial distribution is derived and used to calculate the mean and variance, verifying the formulas. - An example problem demonstrates calculating the probability, mean, variance, and MGF of the number of defective items found when randomly selecting a sample size.

Uploaded by

Deepak Chaudhary
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/ 4

Examples (continued)

4. In a precision bombing attack, there is a 50% chance that any one bomb will strike the
target. Two direct hits are required to destroy the target completely. How many bombs
must be dropped to give atleast 99% chance of destroying the target?

Solution: Let X be the random variable denoting the number of strikes on the target

Now, P(a bomb strikes a target)=0.5

 X ~ B(n, p  0.5)

Let n number of bombs be dropped so that

P( X  2)  0.99 Then

 1  P( X  2)  0.99
 1   P( X  0)  P( X  1)   0.99
 0 n0 1 n1
 1 1 1 1   0.99......(1)
 1  nC      nC    
 02 2 1 2   2  
 

Solving for n using equality in (1) (using trial and error), we get n  11

Moment Generating Function and Moments of the Binomial distribution

Suppose X follows a Binomial distribution with parameters n and p i.e X ~ B(n, p)


We obtain the MGF of the Binomial distribution. We have,
M (t )  E (etX )
X
  etx px , ( X is a discrete r.v.)
x
n
  etx nC x p x q n x
x0
 
n x
  nCx pet q n x
x0
 
n n
 M (t )  q  pet (  a  b    nC x  b  a n x )
n x
X x0
Now,
d 
Mean  E ( X )  M (t ) 
dt  X t 0

 
d  n
  q  pet 
dt  t 0
 n1 t 

  n q  pet

pe    
t 0
 Mean  np
d2 
E( X 2 )   '  M (t ) 
2 dt 2  X t 0
d2 
i.e  ' 
2 dt 2  q  pet n

t 0

d  n1 

dt  
 n q  pet   
pet 
t 0
 n2 n1 

  n(n  1) q  pet

    
pet pet  n q  pet   
pet 
t 0
i.e  '  n(n 1) p 2  np
2
Therefore,

 
2
Variance     '   '
2 2 1
2
 n(n 1) p 2  np   np 
 Variance  np(1  p)
i.e. Variance  npq
Hence for a Binomial distribution with parameters n and p
 Mean  np

 Variance  npq

Solved Example:

1. Suppose that observation over a long period of time has disclosed that, on an average,
two out of 100 items produced by a process is defective. If 8 items are randomly
selected and tested from the production line, find the expectation and variance of the
number of defectives. Using the m.g.f of the distribution of the number of defectives,
find the mean and variance and verify your answer.

(What is important is to first identify the n, p and q.)


Since 2 out of 100 items are defective, the probability of an item being defective is 0.02.
Hence, p=0.02. It follows that q=1-p, hence q=0.98.
Since 8 items are selected, n=8.

(8 items are randomly selected from the production line. Hence it is possible that all 8
items can be defective, since the production line could have millions of these items. So
the random variable X can take the values 0,1,2,3,4,5,6,7,8.)

𝑃(𝑋 = 𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 𝑥 = 0,1,2, … 8

𝑃(𝑋 = 0) = 8𝐶0 (0.02)0 (0.98)8 = 0.8508

𝑃(𝑋 = 1) = 8𝐶1 (0.02)1 (0.98)7 = 0.1389

𝑃(𝑋 = 2) = 8𝐶2 (0.02)2 (0.98)6 = 0.0092

𝑃(𝑋 = 3) = 8𝐶3 (0.02)3 (0.98)5 = 0.0004

𝑃(𝑋 = 4) = 8𝐶4 (0.02)4 (0.98)4 = 0.00001

𝑃(𝑋 = 5) = 8𝐶5 (0.02)5 (0.98)3 = 0.00000016

𝑃(𝑋 = 6) = 8𝐶6 (0.02)2 (0.98)6 = 0.0000000017

𝑃(𝑋 = 7) = 8𝐶7 (0.02)7 (0.98)1 = 0.00000000001

𝑃(𝑋 = 8) = 8𝐶8 (0.02)8 (0.98)0 = 0.00000000000256

Hence, the probability distribution is given by

X 0 1 2 3 4 5 6 7 8
P(X=x) 0.8508 0.1389 0.0092 0.0004 0 0 0 0 0

For Mean and Variance –

X 0 1 2 3 4 5 6 7 8
P(X=x) 0.8508 0.1389 0.0092 0.0004 0 0 0 0 0
𝑥𝑃𝑥 0 0.1389 0.0184 0.0012 0 0 0 0 0
𝑥 2 𝑃𝑥 0 0.1389 00.0368 0.0036 0 0 0 0 0

Using the definition of expectation, 𝐸(𝑋) = ∑ 𝑥𝑃𝑥


𝐸(𝑋) = 0.1389 + 0.0184 + 0.0012 = 0.1585
𝐸(𝑋 2 ) = ∑ 𝑥 2 𝑃𝑥 = 0.1389 + 0.0368 + 0.0036 = 0.1793
𝑉(𝑋) = 𝐸(𝑋 2 ) − (𝐸(𝑋))2 = 0.1793 − (0. 1585)2 = 0.1542

For Mgf

X 0 1 2 3 4 5 6 7 8
P(X=x) 0.8508 0.1389 0.0092 0.0004 0 0 0 0 0
𝑡
𝑒 𝑡𝑋 1 𝑒 𝑒 2𝑡 𝑒 3𝑡 𝑒 4𝑡 𝑒 5𝑡 𝑒 6𝑡 𝑒 7𝑡 𝑒 8𝑡
𝑒 𝑡𝑋 𝑃𝑥 0.8508 0. 1389𝑒 𝑡 0.0092𝑒 2𝑡 0.0004𝑒 3𝑡 0 0 0 0 0

𝑀𝑋 (𝑡) = ∑ 𝑒 𝑡𝑋 𝑃𝑥

𝑀𝑋 (𝑡) = .8508 +. 1389𝑒 𝑡 +. 0092𝑒 2𝑡 +. 0004𝑒 3𝑡 is the mgf


To find mean and variance, we differentiate the mgf
𝑑
𝑀𝑒𝑎𝑛 = 𝜇1′ = [𝑀 (𝑡)] 𝑎𝑡 𝑡 = 0
𝑑𝑥 𝑋

𝑑
[𝑀 (𝑡)] = 0.1389𝑒 𝑡 + 0.0184𝑒 2𝑡 + 0.0012𝑒 3𝑡
𝑑𝑥 𝑋
𝜇1′ = 0.1585
𝑑2
𝐸(𝑋 2 ) = 𝜇2′ = 2 [𝑀𝑋 (𝑡)] 𝑎𝑡 𝑡 = 0
𝑑𝑥
𝑑2
[𝑀 (𝑡)] = 0.1389𝑒 𝑡 + 0. 0368𝑒 2𝑡 + 0. 0036𝑒 3𝑡
𝑑𝑥 2 𝑋
𝜇2′ = 0.1793

𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝜇2′ − (𝜇1′ )2 = 0.1542

Exercise

The probability of a man hitting a target is 1/3. How many times must he fire so that the
probability of his hitting the target atleast once is more than 90%?

You might also like