Concept of Random Variable:

For example, in a random experiment of tossing 3 coins, we get the following outcomes

Sample Points HHH HHT HTH THH HTT THT TTH TTT

For random variable, we are not interested in a particular sample point/ outcome of a random
experiment but we are interested to the numerical description of the outcome.

Suppose we are interested only in the number of heads which appear for the above example;
we assign one of the numbers (0, 1, 2, 3) to each non-numerical outcome corresponding to
the number of heads appearing.

Sample Points HHH HHT HTH THH HTT THT TTH TTT
X 3 2 2 2 1 1 1 0

Such a numerical quantity, whose value is determined by the outcomes of the random
experiment is called a random variable or stochastic variable or chance variable.

OR

“A random variable is a real valued function that takes a defined value for every point in the
sample space.”

Example: Suppose two balls are selected at random from a bag consisting red and green balls.

• Assume the random variable X represents the no: of green balls.

• If R and G represent red and green balls respectively, then the elements of the
sample space and the corresponding values of the random variable X will be:

Sample Points RR RG GR GG
X 0 1 1 2

A Sample Space, which contains a finite no: of sample points, is called a Discrete Sample
Space. A random variable defined over a discrete sample space is known as

Discrete Random Variable.

Discrete random variables represent countable data; e.g. no: of patients in a hospital, no: of
bomb blasts in a particular year, no of vehicles crossing Kotri Barrage on a certain day, etc.

If the elements in a Sample Space are uncountable infinite, the sample space is called a
Continuous Sample Space. A random variable defined over a continuous sample space is
known as Continuous Random Variable.

Continuous random variables represent measurable data; e.g. weight, distance, temperature
height, pressure, etc.

(Page No: 1) By: Muhammd Memon

Discrete Probability Distribution: The set of ordered pairs (x, f(x)) is called the
probability distribution of the discrete random variable x.

A discrete probability distribution may take the form of a table or a formula listing all
possible values that a discrete random variable can take on along with the associated
probabilities.

The probability function for a discrete random variable must possesses following properties:

1. 0 < f(xi) < 1

2. ∑f(xi) = 1

Two of the most important features of a random variable are:

• The values it can assume, and
• The probabilities which are associated with each of these possible values.

In case of tossing a coin 3 times, the variable X represents number of heads:

Sample Points HHH HHT HTH THH HTT THT TTH TTT
X 3 2 2 2 1 1 1 0

- the random variable X can assume the values 0,1,2,3

- the probabilities which are associated with each of these values:
o for value 3 (i.e. 3 head occurs), the probability is 1/8, because 1 of the 8
equally likely sample points results in 3 heads.
o for value 2 (i.e. 2 head occurs), the probability is 3/8, because 3 of the 8
equally likely sample points result in 2 heads and 1 tail.

- Assume equal probabilities for the possible outcomes in the above table, then
P(HHH) = 1/8 , P(HHT)= 1/8, ………………. P(TTT)=1/8

- For instance, the probability that no head occurs is 1/8 i.e. P(X=0)=P(TTT) = 1/8

The possible values x of X and their probabilities P(x) are shown below:

X 0 1 2 3
P(x) 1/8 3/8 3/8 1/8

Example: Find the probability distribution of the sum of numbers when a pair of fair dice is
rolled.

Solution: Pair of dice can result in (6) (6) =36 outcomes, each of with probability 1/36.

The points in sample space and their corresponding sums are:

(1,1) =2 (2,1) =3 (3,1) =4 (4,1) =5 (5,1) =6 (6,1) =7

(1,2) =3 (2,2) =4 (3,2) =5 (4,2) =6 (5,2) =7 (6,2) =8
(1,3) =4 (2,3) =5 (3,3) =6 (4,3) =7 (5,3) =8 (6,3) =9
(1,4) =5 (2,4) =6 (3,4) =7 (4,4) =8 (5,4) =9 (6,4) =10
(1,5) =6 (2,5) =7 (3,5) =8 (4,5) =9 (5,5) =10 (6,5) =11
(1,6) =7 (2,6) =8 (3,6) =9 (4,6) =10 (5,6) =11 (6,6) =12

In this random experiment, the sum of numbers are the values 2,3,4, …, 12 assumed by the
variable X, so in the probability distribution, we write the possible values of random variable
X and their corresponding probabilities:

(Page No: 2) By: Muhammd Memon

 X 2 3 4 5 6 7 8 9 10 11 12
f(x) 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36

Question: Find a formula for the probability distribution of the number of boys in a family
with four children assuming equal probabilities for boys and girls.

Solution: Child may be either girl or boy

Four children, therefore there are 24 = 16 sample points in the sample space
respecting equally likely outcomes; the denominator for all probabilities will be
16.

To obtain the number of ways of getting 2 boys, for example, we divide 4

outcomes/ children into two cells; 2 boys assigned to one cell and two girls
assigned to other.
 4
This can be done in   ways.
 2
It means the number of ways of getting 2 boys out of 4 children is
 4 4! 4  3  2!
  = = =6
 2  2!(4 − 2)! 2!2!
 4
 
6  2 
and the probability of 2 boys out of 4 children is =
16 16

 4
In general, x boys and 4 − x girls can occur in   ways,
 x
Where x can be 0, 1,2,3,4

Thus the required probability distribution f ( x) = P( X = x) is

 4
 
f ( x) =   , for x = 0, 1,2,3,4
x
16

(Page No: 3) By: Muhammd Memon

The administration of a sugar testing clinic uses past patients’ records of 100 days which
indicate that the daily range of the patients from 100 to 115 come for the test.
Number of Number of days
Patients Tested This level was observed
100 1
101 2
102 3
103 5
104 6
105 7
106 9
107 10
108 12
109 11
110 9
111 8
112 6
113 5
114 4
115 2
100

Suppose the administration of a sugar testing clinic wants to know that how many patients to
come tomorrow for the test.
This is the expected value regarding the patients to come for test, but not sure.
Expected Value is a weighted average of the outcomes someone expects in future. Expected
Value weights each possible outcome by the frequency with which it is expected to occur.
To obtain the expected value of a discrete random variable, multiply each value that a
random variable can assume by the probability of occurrence of that value and then sum these
products.
Probability that the
Number of
random variable will
Patients Tested (1)  (2)
take on these values
(1)
(2)
100 0.01 1.00
101 0.02 2.02
102 0.03 3.06
103 0.05 5.15
104 0.06 6.24
105 0.07 7.35
106 0.09 9.54
107 0.10 10.70
108 0.12 12.96
109 0.11 11.99
110 0.09 9.90
111 0.08 8.88
112 0.06 6.72
113 0.05 5.65
114 0.04 4.56
115 0.02 2.30
Expected Value → 108.02
Expected value of the random variable is 108.02 and noted that it can have significant value
to decision makers.

(Page No: 4) By: Muhammd Memon

Use of Expected Value in Decision Making:

Suppose a fruit and vegetable wholesaler who sells tomatoes. This product has a very limited
useful life. If not sold on day of delivery, it is worthless. In a case, it costs Rs. 20 per peti and
selling price is Rs. 50 per peti. He has to decide how many peti of tomatoes per day he may
purchase for sale in order to get optimal result.

He can not specify the number of peti customers will call for on any one day, but his analysis
of past records has produced the information in the following table:

Sales during 100 days:

Probability of
Daily Sales No of days
each number
(Peti) sold
being sold
10 15 0.15
11 20 0.20
12 40 0.40
13 25 0.25
100 1.00

Optimal Solution: is that action, which can minimize expected losses or maximize expected
profits.

Obsolescence and opportunity losses

Obsolescence losses, caused by stocking too much tomato on any one day and having to
throw it (spoiled tomatoes) away the next day

Opportunity losses, caused by being out of tomatoes any time that customer’s call for them.

Conditional Loss Table:

Possible Possible Stock Options

requests (Peti) 10 11 12 13
10 Rs. 0 20 40 60
11 30 0 20 40
12 60 30 0 20
13 90 60 30 0

(Page No: 5) By: Muhammd Memon

Calculating Expected Losses:

Examining each possible stock action, we can compute the expected loss.

Expected loss from stocking 10 Peti

Possible Conditional Prob of this Expected
requests (Peti) Loss many requests Loss
10 Rs. 0  0.15 = Rs. 0.00
11 30  0.20 = 6.00
12 60  0.40 = 24.00
13 90  0.25 = 22.50
1.00 52.50

Expected loss from stocking 11 Peti

Possible Conditional Prob of this Expected
requests (Peti) Loss many requests Loss
10 Rs. 20  0.15 = Rs. 3.00
11 0  0.20 = 0.00
12 30  0.40 = 12.00
13 60  0.25 = 15.00
1.00 30.00

Expected loss from stocking 12 Peti

Possible Conditional Prob of this Expected
requests (Peti) Loss many requests Loss
10 Rs. 40  0.15 = Rs. 6.00
11 20  0.20 = 4.00
12 0  0.40 = 0.00
13 30  0.25 = 7.50
1.00 17.50

Expected loss from stocking 13 Peti

Possible Conditional Prob of this Expected
requests (Peti) Loss many requests Loss
10 Rs. 60  0.15 = Rs. 9.00
11 40  0.20 = 8.00
12 20  0.40 = 8.00
13 0  0.25 = 0.00
1.00 25.00

On the basis of this analysis, he may decide to stock 12 peti of tomatoes each day, because at
this point the expected loss is minimized at Rs. 17.50.

- This problem can be solved by taking an alternative approach, that is, maximizing
expected gain (Rs. 50 – Rs. 20) instead of minimizing expected loss.
- The answer, 12 peti have been the same.

(Page No: 6) By: Muhammd Memon

Probability Distribution of Persons per Household
The Statistical Abstract of the United States is published annually. Using census information about the entire
population, the following table summarizes the data regarding the number of persons living in the household.
Develop the probability distribution of the random variable defined as the number of persons per household.

Solution:

The probability of each value of X, the number of persons per household, is computed as the relative frequency.
We divide the frequency for each value of X by the total number of households, producing the following
pprobability distribution.

The probability that a randomly selected household has four or more persons is
P(X ≥ 4) = P(4) + P(5) + P(6) + P(7 or more)
= .140 + .062 + .023 + .012 = .237

(Page No: 7) By: Muhammd Memon

There is a shortcut calculation that simplifies the calculations for the population variance. This formula is not
an approximation; it will yield the same value as the formula above.

Question: Find the mean, variance, and standard deviation for the population of the
number of persons per household:

(Page No: 8) By: Muhammd Memon

Probability Distribution of the Number of Sales

A mutual fund salesperson has arranged to call on three people tomorrow. Based on past
experience, the salesperson knows there is a 20% chance of closing a sale on each call.

Determine the probability distribution of the number of sales the salesperson will make.

The tree exhibits each of the eight possible outcomes and their probabilities. We see that
there is one outcome that represents no sales, and its probability is P(0) = .512.
There are three outcomes representing one sale, each with probability .128, so we add these
probabilities.
Thus, P(1) = .128 + .128 + .128 = 3(.128) = .384
The probability of two sales is computed similarly: P(X) = 3(.032) = .096
There is one outcome where there are three sales: P(3) = .008

Therefore, Probability Distribution of the Number of Sales will be:

(Page No: 9) By: Muhammd Memon

Describing the Population of Monthly Profits
The monthly sales at a computer store have a mean of $25,000 and a standard deviation of
$4,000. Profits are calculated by multiplying sales by 30% and subtracting fixed costs of
$6,000. Find the mean and standard deviation of monthly profits.

(Page No: 10) By: Muhammd Memon

ASSIGNMENT OF PROBABILITY DISTRIBUTION
7.2 The distance a car travels on a tank of gasoline is a random variable.
a. What are the possible values of this random variable?
b. Are the values countable? Explain.
c. Is there a finite number of values? Explain.
d. Is the random variable discrete or continuous? Explain.

7.4 The mark on a statistics exam that consists of 100 multiple-choice questions is a random variable.
a. What are the possible values of this random variable?
b. Are the values countable? Explain.
c. Is there a finite number of values? Explain.
d. Is the random variable discrete or continuous? Explain.
7.8 Using historical records, the personnel manager of a plant has determined the probability
distribution of X, the number of employees absent per day. It is

a. Find the following probabilities.

(i) P (2 ≤ X ≤ 5) (ii) P(X > 5) (iii) P(X < 4)
b. Calculate the mean of the population.
c. Calculate the standard deviation of the population.
7.20 The number of pizzas delivered to university students each month is a random variable
with the following probability distribution.
x 0 1 2 3
P(x) .1 .3 .4 .2
a. Find the probability that a student has received delivery of two or more pizzas this month.
b. Determine the mean and variance of the number of pizzas delivered to students each month.

7.21 Refer to Exercise 7.20. If the pizzeria makes a profit of $3 per pizza, determine the mean
and variance of the profits per student.
7.26 A survey of Amazon.com shoppers reveals the following probability distribution of the
number of books purchased per hit.
x 0 1 2 3 4 5 6 7
P(x) .35 .25 .20 .08 .06 .03 .02 .01
a. What is the probability that an Amazon.com visitor will buy four books?
b. What is the probability that an Amazon.com visitor will buy eight books?
c. What is the probability that an Amazon.com visitor will not buy any books?
d. What is the probability that an Amazon.com visitor will buy at least one book?
7.34 You have been given the choice of receiving $500 in cash or receiving a gold coin that
has a face value of $100. However, the actual value of the gold coin depends on its gold
content. You are told that the coin has a 40% probability of being worth $400, a 30%
probability of being worth $900, and a 30% probability of being worth its face value.
Basing your decision on expected value, should you choose the coin?
7.38 After an analysis of incoming faxes, the manager of an accounting firm determined the
probability distribution of the number of pages per facsimile as follows:
x 1 2 3 4 5 6 7
P(x) .05 .12 .20 .30 .15 .10 .08

Compute the mean and variance of the number of pages per fax.

(Page No: 11) By: Muhammd Memon