Quantitative Methods

MM ZG515 / QM ZG515

BITS Pilani L6: Probability Distributions

Pilani | Dubai | Goa | Hyderabad Srinivas Kota
 BITS Pilani
Pilani | Dubai | Goa | Hyderabad

Random Variables
Random Variables
Experiment: Toss a Coin.
If the coin turns up Heads, we win Rs.10; O/w we lose Rs.10

Event p X p
H 0.5 10 0.5
T 0.5 -10 0.5
A random variable is a numerical
description of the outcome of a random Discrete Random Variables
experiment. • # of dependents of an employee
• # of customers using an ATM in a day
A discrete random variable may assume • # of sixes in a T20 match
a countable number of values • # of owners who like the product

A continuous random variable may Continuous Random Variables

assume any numerical value in an interval • Life of a tire
• Time between calls at the call centre
The random variable inherits the • Volume of water in a 1 litre mineral
probabilities of the events of the random water bottle
experiment • % of owners who like the product

09/02/2020 Quantitative Methods MM ZG515 / QM ZG515 3
Probability Function of a Discrete Random Variable
# of Children (X) 0 1 2 3
Probability (P(x)) 0.1 0.4 0.4 0.1

The Probability Function lists the possible outcomes and their probabilities

Note:
0 ≤ P(x) ≤ 1 & ∑P(x) = 1
Like frequency distributions, probability distributions have descriptive measures

Common Probability Functions

∞
Discrete Uniform Distribution Poisson Distribution Bionomial Distribution
Probability Distribution of a Continuous Random
Variable
• Probabilities assigned to intervals of numbers

• Let X: The time spent by a car at the toll booth

• A Histogram can be developed for the data.
• A line joining the top of each rectangle at the center will
generate the empirical Probability Density Function.

• As earlier, such probability distributions have descriptive

measures: μ, σ etc

Uniform f(x) Exponential

f(x)

x x

• X can assume any value in an interval on the real line or in an interval.
• P(X = a) = 0 for any number a. 
• P(a < X < b) = P(a ≤ X < b) = P(a < X ≤ b) = P(a ≤ X ≤ b) 
• P(a < X < b) is the area under the graph of the probability density function between a and b
 BITS Pilani
Pilani | Dubai | Goa | Hyderabad

Discrete Probability Distribution

Discrete Random Variables & Probability Distributions

X: # of customers serviced by the ATM in a day
Y: # of defective items in the consignment

Both X and Y take discrete values
Both are random variables

1. Until the day ends, X is unknown
2. Until all the items are tested, Y is unknown

• The probability function provides  the probability for each value of the random 
variable. 
• The required conditions for the probability  function are: f(x) ≥ 0 & ∑f(x) = 1

• The expected value, or mean, of a random variable is a measure of its central 
location. E(X) = μ = ∑x*f(x) 

• The variance summarizes the variability in the values of a random variable.
• Var(x) = V(X) = σ2 = ∑(x ‐ μ)2 f(x)

• The standard deviation, σ, is defined as the positive square root of the variance
09/02/2020 Quantitative Methods MM ZG515 / QM ZG515 7
Example: Constructing the Empirical Distribution

Table 1 gives the past data on AC sales.

Table 2 presents the probability function of the discrete random variable X
The graphical representation of the probability distribution is shown on the right

TABLE 1 TABLE 2
Probability Function
Units Number 0.35
Sold of Days x f(x) 0.3

Probability
0 10 0 0.1 0.25
0.2
1 20 1 0.2 0.15
2 10 2 0.1 0.1
0.05
3 30 3 0.3 0
4 30 4 0.3 0 1 2 3 4
Random Variable X
∑x 100 ∑x 1.00
Example: Computing Expected Value (μ) & Variance (σ2)

X f(X) X*f(X) (X-μ) f(X)*(X-μ) (X-μ)2 f(X)*(X-μ)2

0 0.1 0 -2.5 -0.25 6.25 0.625
1 0.2 0.2 -1.5 -0.30 2.25 0.45
2 0.1 0.2 -0.5 -0.05 0.25 0.025
3 0.3 0.9 0.5 0.15 0.25 0.075
4 0.3 1.2 1.5 0.45 2.25 0.675
∑ 1.0 2.5 0.0 1.85

Mean daily sales = 2.5 AC

Variance of daily sales = σ2 = 1.85

Standard deviation of daily sales = 1.36 AC

Example: Computing Expected Value (μ) & Variance (σ2) of -3X

x f(x) Y=-3X f(Y) Y*f(Y) (Y-μ) f(Y)(Y-μ) (Y-μ)2 f(Y)(Y-μ)2

0 0.1 0 0.1 0 7.5 0.8 56.3 5.625
1 0.2 -3 0.2 -0.6 4.5 0.9 20.3 4.05
2 0.1 -6 0.1 -0.6 1.5 0.2 2.25 0.225
3 0.3 -9 0.3 -2.7 -1.5 -0.5 2.25 0.675
4 0.3 -12 0.3 -3.6 -4.5 -1.4 20.3 6.075
∑

μ 2.5 -7.5
σ2 1.85 16.65
σ 1.36

E(X) = E(X) &

V(X) = 2V(X)
A Bivariate Discrete Probability Distribution

A probability distribution involving two random variables is called a bivariate

probability distribution.

HR ran a survey among the 2000-strong staff on Job Satisfaction & Work Stress.
The cross-tabulation of the data is given below.

Job Work Stress (y) Total

Satisfaction Low Medium High
Low 260 280 40 580
Medium 200 480 320 1000
High 40 240 140 420
Total 500 1000 500 2000

09/02/2020 Quantitative Methods MM ZG515 / QM ZG515 11
A Bivariate Discrete Probability Distribution

From the cross-tabulation of the data, HR created the Joint and Marginal probabilities.

Job Work Stress (y) Total

Satisfaction Low Medium High
Low 0.13 0.14 0.02 0.29
Medium 0.10 0.24 0.16 0.50
High 0.02 0.12 0.07 0.21
Total 0.25 0.50 0.25 1.00

P(Job Satisfaction = Low & Work Stress = High) = 0.02

P(Job Satisfaction = Low) = 0.29

09/02/2020 Quantitative Methods MM ZG515 / QM ZG515 12
Computing the Joint Distribution of Two Independent Random
Variables

• Ace Ad agency is a small start up with only two clients, represented by X and Y,
operating in different industries. For the two clients, Ace places ads in the local
paper’s classified section of the Saturday edition.

• X weekly ad spends in Rs.’000 is 0, 1, 2, 3, 4 (with some rounding off). Similarly,

Y weekly ad spends in Rs.’000 is 0 and 1.

• Based on past data, Ace has created the frequency distribution and subsequently
the probability distributions for X and Y.

x f(x) Y f(Y) x f(x) Y f(Y)

0 10 0 70 0 0.1 0 0.7
1 20 1 30 1 0.2 1 0.3
2 10 2 0.1
3 30 3 0.3
4 30 4 0.3
Computing the Joint Distribution of two Independent Random
Variables
• Since X and Y operate in different industries , we may assume that the ad spends
are independent of each other. That is, we will assume that X and Y are
independent variables.
• In which case, P(X = a & Y = b) = P(X = a) * P(Y = b)
• Using this fact, we can create
• The joint distribution of X and Y
• Any linear function of X and Y
x f(x) Y f(Y) X X+Y P
0 0.1 0 0.7 0 1 2 3 4 0 0.07
1 0.2 1 0.3 0 0.07 0.14 0.07 0.21 0.21 1 0.17
Y
2 0.1 1 0.03 0.06 0.03 0.09 0.09 2 0.13
3 0.3 3 0.24
4 0.3 4 0.30
5 0.09
Computing Expected Value (μ) & Variance (σ2) of (X+Y)

μ σ2
X 2.50 1.85
Y 0.30 0.21

R=X+Y P R*P (R-μ)*P (R-μ)2*P

0 0.07 0.00 -0.20 0.55
1 0.17 0.17 -0.31 0.55
2 0.13 0.26 -0.10 0.08
3 0.24 0.72 0.05 0.01
4 0.30 1.20 0.36 0.43
5 0.09 0.45 0.20 0.44
SUM 2.80 0.00 2.06

E(X + Y) = E(X) + E(Y)

If X & Y are independent, V(X+ Y) = 2V(X) + 2E(Y)

Mean and Variance of Distributions
E(X ± c) = E(X) ± c Var(X ± c) = Var(X)
Example: Suppose X managed to convince Ace to reduce the charges on every order
by Rs.100.

E(X) =  E(X) Var(αX) = 2 Var(X)

Example: X gets a 10% discount on all orders. In the above equation  = 0.9

Consider two random variables X and Y: E(X + Y) = E(X) + E(Y).

• E(X – Y) = E(X) – E(Y)

• If the random variables are independent, V(X+ Y) = 2V(X) + 2V(Y).

• For example V(X – Y) = V(X) + V(Y)
Summary

Random Variables
Discrete & Continuous Random Variables
Probability Distributions
• Probability Function
• Probability Density Function
Discrete Random Variables
Probability Functions
Mean and Standard Deviation of Random Variables
Bivariate Distributions
Linear Sum of Random Variables
 BITS Pilani
Pilani | Dubai | Goa | Hyderabad

Uniform & Poisson Distributions

Uniform Probability Distribution

• You are about to launch a new product. The product was test marketed, but
preference for body colour was not.

• There are six colours: Violet (1), Blue (2), Green (3), Yellow (4), Orange (5) and Red
(6). Initially it must be assumed that each body colour is equally preferred.

• The probability function f(x) = 1/6

08/02/2020 Quantitative Methods MM ZG515 / QM ZG515 19
Poisson Probability Distribution

• A Poisson distributed random variable is used in estimating the number of

occurrences in a specified interval of time or space

• Application
Sizing the size of operations at a bank/call centre/service centre/petrol bunk, …

• Examples
# of vehicles arriving at a toll booth in one hour
# of patients arriving in an emergency room between 11 and 12 pm
# of typos in a page

• Requirements
• Events occur independently
• Two events cannot occur at exactly the same instant
• The probability of an event in an interval is proportional to the length of the
interval

09/02/2020 Quantitative Methods MM ZG515 / QM ZG515 20
Poisson Probability Function

I: The specified interval

x = the number of occurrences in an interval
f(x) = the probability of x occurrences in an interval
μ = mean number of occurrences in an interval

X ~ Π(μ)

P(X = x) =
!

μ = E(X) = V(X)
Poisson Probability Distribution

Employees visit the ATM at the average rate of 6 per hour in the post-lunch period.
What is the probability of 2 arrivals in 30 minutes in the post-lunch period.
What is the expected # of arrivals? Variance?

Mean
X 2.9 3 3.1
0 0.0550 0.0498 0.0450
1 0.1596 0.1494 0.1397
2 0.2314 0.2240 0.2165
3 0.2237 0.2240 0.2237
4 0.1622 0.1680 0.1733
5 0.0940 0.1008 0.1075