Chapter 1 : PROBABILITY DISTRIBUTION

Probability Distribution
Contents
Random variables
Discrete Probability Distribution
Special Discrete Probability Distribution:
Binomial Distribution
Poisson Distribution
Continuous Probability Distribution
Special Continuous Probability Distribution:
Normal Distribution

Topic 1.1 :Table of Contents

Leave blank

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.2 : Random variables

Leave blank

Random Variables
A random variable is a quantitative variable whose values is determined by the outcome of a
random experiment.
A random experiment is a process that result in different outcomes when the experiment is carried
out in the same manner several times.
Example : Random Experiment: Testing three electrical items.
Random variable: Number of defective items.
Let N denotes non defective item and D denotes defective item.
Outcomes of testing 3 electrical items

Number of defective items, X

NNN
NND
NDN
NDD
DNN
DND
DDN
DDD

0
1
1
2
1
2
2
3

In this example the random variable is denoted b X.

X can assumes any of the four possible values 0,1,2,3 .
Random variables are represented by capital alphabets such as X and Y while their values
are represented by lower case alphabets such as x and y.

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.2 : Random variables

Random variables are classified according to the set of values that they can take.
Discrete random variable assumes values that can be counted.
Continuous random variable assumes values contain in one or more intervals.
Examples of discrete random variables: Number of times a machine breaks down in a month, Number
of accidents occur in a factory yearly, Number of appointments scheduled in a month to see a
consultant.
Examples of continuous random variables: Time taken by a garage to service a car, the resistance of
an electrical component, length of iron bars produced by a machine .

Leave blank

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.3 : Probability Distributions of a discrete random variables

Leave blank

The Mean and Standard Deviation of a Discrete Random Variable

The mean of a discrete random variable, denoted by , is the value that is expected to
occur if an experiment is repeated a large number of times.
The mean is also called the expected value and is denoted by E(X).
The standard deviation of a discrete random variable, denoted by , measures the
spread of its probability distribution.
Let X be a discrete random variable with probability distribution p(x) .

Mean : xp( x )
Variance : 2 ( x ) 2 p( x ) x 2 p( x ) 2
Standard deviation : 2

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.3 : Probability distribution of a discrete random variables

Leave blank

Example
The probability distribution of X, the number of defective light bulbs purchased by a
shopkeeper is shown below.
Number of defective bulbs, X
P(X=x)

0.71

0.07

0.16

0.05

0.01

Find the mean and the standard deviation of the number of defective light bulbs purchased
by the shopkeeper.
x
0
1
2
3
4
P(x)

0.71

0.07

0.16

0.05

0.01

x P(x)

0.07

0.32

0.15

0.04

x P(x)=0.58

x2 P(x)

0.07

0.64

0.45

0.16

x2 P(x)=1.32

mean, xp( x ) 0.58

var iance, 2 x 2 p( x) 2 0.9836

var iance, 2 1.32 (0.58) 2 0.9836

Standard deviation : 0.9836 0.9918

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.4 : Binomial Distribution

Special Discrete Probability Distribution

The Binomial Distribution
The binomial distribution is applied to experiments that satisfy the conditions of a
binomial experiment.
Conditions of a Binomial Experiment
The experiment consists of a fixed number of trials, n.
Each trial results in one of two outcomes classified as a success and a failure .
The trials are independent.
The probability of success, p must be the same in each trial. The
probability of failure in a single trial is denoted by q and q = 1 p.
Some terminology:
A trial is an action which results in one of several outcomes
When one trial does not affect the outcome of another trial, they are said to be independent.

Leave blank

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.4 : Binomial Distribution

Examples of the Binomial Experiment

Example 1.
Throw a dice 4 times and record the random variable X , the number of times a 6 is
obtained.
The conditions of a binomial experiment are satisfied since
There is a fixed number of trials, n=4
(throw a die 4 times)
Each trial has two outcomes.
(getting a 6 is a success and any other outcome is a failure)
The trials are independent.
(The result of a throw does not affect the outcome of the next throw).
The probability of getting a 6 is the same for all the throws, p=1/6
Example 2.
Suppose a multiple choice quiz has 20 questions and each question has 4 possible
answers.
Let X= number of correct answers obtained by a student who answer all the 20
questions.
There is a fixed number of trials, n=20
Each trial has two outcomes.
(getting a correct answer is a success and a wrong answer is a failure)
The trials are independent.
(The result of a question does not affect the result of the other questions).
The probability of getting a correct answer in each question is the same, p= .

Leave blank

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.4 : Binomial Distribution

Leave blank

The Binomial Distribution

The discrete random variable, X that represents the number of successes in n trials of a binomial
experiment is called a binomial random variable.
If X follows a binomial distribution, we write X~Bin (n,p) where p is the probability of a success in a
single trial and n is the fixed number of trials.
The probability of x successes in n trials is given by

n
P( X x ) nC x p x q n x p x (1 p ) n x
x
for x 0,1,2,...n.
n!
Recall nC x
x! ( n x )!
with n! n ( n 1)( n 2)...( 2)1

and 0! 1.

P(X=x) can also be obtained from the table of cumulative binomial probabilities.

Chapter 1 : PROBABILITY DISTRIBUTION

Topic 1.4 : Binomial Distribution

The Mean and Standard Deviation of the Binomial Distribution

For a binomial experiment with n trials and probability of success, p in a single
trial, the mean and standard deviation of the binomial distribution is given by

Mean
Mean:: np
np
22 npq
Variance
:

Variance : npq
Standard
Standard deviation
deviation:: npq
npq

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.4 : Binomial Distribution

Example
The probability that a patient recovers from a rare flu disease is 0.4. It is known that 20 people
have contracted this disease, what is
a)the probability that exactly 5 survive?
b)the probability that at least 3 survive?
c)the probability that from 3 to 8 survive?
d)the probability that at most 3 do not survive?
e) the expected number of survivors and the
standard deviation?
Note:
The problem can be modeled by a binomial distribution because
i)There are 2 outcomes: success=a patient survive ( recover) failure=a patient did not survive.
ii)Fixed number of trials, n= 20 patients
iii)The trials are independent and probability of success is the same for each trial (patient), p=0.4

Leave blank

Chapter 1 : Study work order instructions

Topic 1.2 : Computer system unit components

Finding Probabilities Using Cumulative Binomial Probabilities Table

Table 1 give the cumulative probabilities

n x
p (1 p ) n x
x r x
n

P ( X r )

for selected values of n and p.

Example 1
Use Table 1 to find P(X2) where n=5 p=0.06
Find column marked p=0.06.
Find the row marked n=5 and r=2
Hence obtain the value 0.0319.
So P(X2)=0.0319.

RULES for using Binomial and Poisson Table ( P X r )

a)P( X r ) = table
b) P( X r ) = 1 - P( X r + 1 )
c) P( r X s ) = P( X r ) - P( X s + 1 )
d) P( X = r ) = P( X r ) - P( X r + 1 )

Leave blank

Chapter 1 : Study work order instructions

Topic 1.2 : Computer system unit components

Example 2
Consider X~Bin( 10, 0.07) and using Table 1, we can find the following
probabilities:
a)P(X3)
b)P(X>3)
c)P(X<3)
d)P(X3)
e)P(X=3)
f)P(1<X 4)

Leave blank

Chapter 1 : Study work order instructions

Topic 1.2 : Computer system unit components

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.4 : Poisson Distribution

The Poisson Probability

Distribution
Suitable to model data that represent the number of occurrences
of a specified event in a given unit of time or space.
Examples of Poisson variable
a)number of accidents per year in a factory.
b) number of cars per hour passing through a bridge.
c) number of faults in a meter long of cable
d) number of typing errors made in one page.

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Leave blank

Topic 1.4 : Poisson Distribution

The Poisson Probability

Distribution
If an event is randomly scattered in time (or space) and
has a mean number of occurrences, in a given interval
of time(or space) and if X=no of occurrences in the given
interval then we write X~Po() .
The probability that the number of occurrence equals x is
given by
x

P X x e

; x 0,1,2,....
x!

The Poisson distribution has

Mean=
Standard deviation=
P(X=x) can also be obtained from the table of cumulative
Poisson probabilities.

Various Poisson Distributions

p(x)

=1
=3
=6
x

Chapter 1 : Study work order instructions

Topic 1.2 : Computer system unit components

Cumulative Poisson Probabilities Table

The tabulated values in Table 2 are the probabilities

P X r e
x r

mx
x!

for x 0,1,2,....

for various values of m, the mean number of

occurrence of the event per interval.
Finding Probabilities using Cumulative Poisson
Probabilities Table
Consider X~Po(0.8).
To obtain P(X2) using Table 2:
Look up column m=0.8 and row r=2 we obtain
0.1912
Hence P(X2)=0.1912

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.4 : Poisson Distribution

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.4 : Poisson Distribution

Leave blank

Poisson distribution as an approximation to the Binomial distribution

When n is large (n> 50) and p is small (p<0.1)
the binomial distribution X~Bin(n,p) can be approximated using
a Poisson distribution with the mean =np.
The approximation gets better as n gets larger and p gets smaller.
Example .
A large lot of items is known to contain 4% defective items. If a sample of 100 is randomly drawn from
the lot, use the Poisson approximation to find the probability it will contain
a) no defective
b) more than 5 defectives.
Solution
Let X = number of defective items in a sample of 100 items.
X~Bin(100, 0.04)
Using Poisson approximation, =100 x 0.04 = 4
X~Po(4)
0
4 4
00183.
a) P X 0 e
0!
b) P(X>5) =P(X6)=0.2149 (using Poisson table)

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.5 : Continuous Probability Distribution

Leave blank

Continuous Probability Distribution

A smooth curve describes the probability distribution of a
continuous random variable.
The probability distribution of a continuous random variable,
X is described by a mathematical formula f(x) known as the
probability density function or simply density function.

P ( a X b)

The function f(x) is the probability density function of a

continuous random variable X if
1.

f (x) 0

for all real values of x.

2.

f ( x)dx 1

, The area under the curve is equal to 1.

The probability that X assumes values in the interval a to b is

b
given by

P( a X b) f ( x )dx
a

Note: P(a X b) P(a X b) P(a X b) P(a X b)

There is no probability attached to any single value of x.
Example: P(X = a) = 0.

f(x)

Topic 1.6 : Normal Distribution

Chapter 1 : PROBABILITY
DISTRIBUTION

Leave blank

The Normal Distribution

One important continuous random variable is the
normal random variable.
The normal or Gaussian distribution has a probability
density function

f x

1
e
2

1 x

Approximate percentage area under the

normal curve

, where - x

The parameters of the normal distribution are its

mean and standard deviation .
If the random variable X has a normal distribution
with parameters and , we write X ~ N ( , 2 ).

99.7%
95%

68%

Features of the Normal curve

1.Bell shaped curve and is symmetric about the
mean.
2.Total area under the curve is 1.
3.The curve never touches the x axis.
4.The mean, median and mode are equal.

The range of the distribution is approximately 6

standard deviations.

Chapter 1 : PROBABILITY
DISTRIBUTION

The Normal
Distribution
The shape
and location
of the normal
curve
changes as
the mean
and standard
deviation
change.

Topic 1.6 : Normal Distribution

Leave blank

Topic 1.6 : The Normal Distribution

Chapter 1 : PROBABILITY
DISTRIBUTION

Leave blank

The Standard Normal Distribution

b

To find P(a < X < b), we need to evaluate f ( x )dx

where

f x

1
e
2

1 x

, where - x

This integral is difficult to evaluate.

f(z)

To simplify the evaluation of the integral, we transform

variable x to z where
.

Z is known as the standard normal variable.

The probability distribution of Z is the standard normal
distribution with mean, =0 and standard deviation =1 . We
write Z ~ N ( 0,1 ).

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.6 : Normal Distribution

The Standard Normal Distribution

The probability function of Z is

1 12 z 2
f z
e , for z
2
Features of the standard normal curve
1.Bell shaped curve and is symmetric about z=0.
2.Total area under the curve is 1.
3.Values of z to the left of the centre is negative and to
the right of the centre is positive.
4.Mean=0, standard deviation =1.
The Standard Normal Table
Areas under the standard normal curve are
tabulated in a standard normal table.
Hence to find P(a < X < b), we use standard
normal table.

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

The Standard Normal Table

Table 3 gives the values of P(Z>z) for z>0
which is the area under the z curve to the
right of a particular value of Z.
To find P( Z > 1.24 ) from the Table 3, we go
to the row in the table written 1.2 and look at
the value in the column headed 0.04, so
P ( Z > 1.24 ) = 0.1075

Topic 1.6 : Normal Distribution

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.6 : Normal Distribution

Finding Probabilities Using The Standard Normal Table

Example
1.

Let Z be a standard normal random variable. Find the following :

a)P(Z<-1.65)
b)P(Z<1.65)
c)P(1.8<Z< 2.3)
d) P(-1.8<Z< 2.3)
2.

Let Z be a standard normal random variable. Find the constant k such that
a) P(Z < k)=0.1423
b) P(Z > k)=0.9082
c) P(-0.5 < Z < k)= 0.5822

Leave blank

Chapter 1 : PROBABILITY
DISTRIBUTION

Topic 1.6 : Normal Distribution

Problem Solving involving The Normal Distribution

Example
1.Suppose the lengths of iron rods produced by a factory are normally distributed with a mean
of 120 cm and a standard deviation of 10 cm.
a) What is the probability that an iron rod will have a length within 5 cm of the mean?
b) Rods shorter than k cm are rejected. Estimate the value of k if 9 % are rejected
c) In a sample of 500 rods, estimate the number having a length over 126cm

Leave blank