Random Variable Analysis

Unit 3
Part 1

Topics to be Covered
• Probability: Meaning and need,
• Conditional probability,
• Bayes’ theorem,
• Random Variable
• Discrete and continuous.
• Probability Distribution: Meaning, characteristics
(Expectation and variance) of Binomial, Poisson,
Exponential and Normal distribution,
• z-score,
• Chebyshev and empirical rule,
• Central limit theorem.
 Readings
• Statistics for Management & Economics by
Keller, G.
(Chapter 6,7,8)
• Statistics for Management by Levine & Rubin
(Chapter 4,5,7,8)

MEANING

• Probability is the chance that something will occur. We

usually use probability when we have to make decisions in
case of uncertain circumstances.
• For example students want admission in reputed colleges as
this would ensure them a safe and secure future,
• manager of the company would invest in advertising and
promotion more as he believes that this will increase the
sales of the products,
• we decide to take umbrella to work if there is a 70 per cent
chance of raining today,
• the coach of Indian cricket team would include a player for
the upcoming match by evaluating his batting average.
• All these decisions are made in face of uncertainty.
• Probability takes values between 0 and 1 such
that a probability of 0 means that something
can never occur, whereas a probability of 1
indicates that something will occur for sure.
• They are usually displayed in fractions or
decimals.

EXPERIMENT

• An Experiment refers to an activity which

results in one and only one of several possible
outcomes which are subject to uncertainty.
• Example: Tossing a fair coin and observing the
face thus appeared, measuring rainfall on a
particular day, drawing a card from a deck of
52 cards, rolling a fair die and observing the
number thus obtained.
 SAMPLE SPACE

TRIAL AND EVENT

• Trial: When an experiment is conducted once,

it is known as a trial.
• Example: Tossing a fair coin once is known as
a trial.
 Event
•

SIMPLE AND COMPOUND EVENTS

•
 Example
3 vehicles take a particular freeway exit, a Left
(L) or a Right (R)
S = {(LLL), (RLL), (LRL), (LLR), (LRR), (RLR), (RRL),
(RRR)}

SIMPLE EVENT- total 8, i.e. E1= LLL & E8= RRR

COMPOUND EVENT-
A = Exactly 1 vehicle turns right =
{(RLL),(LRL),(LLR)}
B= All 3 vehicles turn in the same direction =
{(LLL),(RRR)}
 BASICS OF SET THEORY

SET THEORY

• A set is well defined collection of objects with

certain properties and are specified according
to a well-defined rule. The objects comprising
a set are known as elements. A set is usually
represented using a capital letter.
• Example: First ten natural numbers, letters in
English alphabet, vowels in English, colleges
offering B.Com in Delhi University are all
examples of a set.
 DIFFERENT FORMS OF SETS
•

SUB-SET:
•
•

TWO EQUAL SETS:

•
 OPERATIONS ON SETS

INTERSECTION:
•
 DISJOINT SETS:
•

COMPLEMENT:
•
 DIFFERENCE:
•

Example
•
 MUTUALLY EXCLUSIVE EVENTS

•
 COLLECTIVELY EXHAUSTIVE EVENTS

INDEPENDENT EVENTS

•
 AXIOMS OF PROBABILITY
• Given an experiment & sample Space,
objective of probability is to assign to each
event A, a number P(A), called probability of
an event A, which will give a precise measure
of chance that A will occur.

All assignments should satisfy the

following axioms (basic properties) of
probability-
•
 Proposition
• P(ɸ) = 0
Where ɸ is a null event (containing no outcome
at all)
Example- A fair coin is tossed,
P(H) = 0.5
P(T) = 0.5
P(S) = P(H) +P(T) = 1

Interpreting probability
If experiment is performed ‘n’ times, at times A
will occur, at times A will not occur.
Let n(A) = Number of replications on which A
occurs
Then, n(A)/n = Relative frequency of occurrence
of event A in sequence of ‘n’ replications.
 More Probability Properties
•
 Addition theorem for mutually
exclusive events A and B
•

Addition theorem for three events A, B

and C
•
 Example:
• If a card is drawn at random from a deck of 52
cards. What is the probability that the card
drawn is either a diamond or an ace?

•
 Example for Three events
Question. Three types of magazines A, B and C provide
subscriptions in a particular city. In a survey conducted it
is revealed that 30% of the households subscribe to the
magazine A, 24% of the households subscribe to the
magazine B and 12% of the households subscribe to the
magazine C. 9% of the households subscribe to both the
magazines A and B, 7% of the households subscribe to
the magazines B and C, 2% of the households subscribe
to the magazines A and C and 1% of the households
subscribe to all the three magazines. What percentage of
the households have subscribed to at least one of the
magazines?
•

•
 Equally Likely Outcomes
•

Conditional Probability
•
• Example- Individuals buy digi cam, 60% buy
optional memory card, 40% buy extra battery
and 30% buy both card and battery. Given
that individuals purchased an extra battery,
what is the prob that an optional card was
also purchased?

ANSWER
•
 • Example- a news magazine publishes 3
columns A, B and C. reading habits of
randomly selected reader with respect to
these columns are:
Read A B C
Regularly

Probabilit .14 .23 .37 .08 .09 .13 .05

y

Obtain:
1. P(A|B)
2. P(A|BUC)
3. P(A|AUBUC)
4. P(AUB|C)

•
 Conditional Probability
•
 MULTIPLICATION THEOREM

Example:
• If two cards are drawn from a deck of 52 cards
such that the first card is not replaced before
the second card is drawn, then what is the
probability of drawing a jack twice?
•

Example
• A chain of video stores sell 3 different brands of DVD
players, of its DVD player sales, 50% are brand 1, 30% are
brand 2, 20% are brand 3. each manufacturer offers a 1
year warranty on parts and labor. It is known that 25% of
brand 1 DVd players require warranty repair work, 20% of
brand 2 and 10% of brand 3 also require the same.
1. what is the probability that a randomly selected purchaser
has bought a brand 1 DVD player that will need repair while
under warranty?
2. What is the probability that a randomly selected purchaser
has a DVD player that will need repair while under warranty?
3. If a customer returns to the store with a DVD player that
need warranty repair work, what is the probability that it is a
brand 1 DVD player? A brand 2 and a brand 3 DVD player?
A1= BRAND 1 is purchased, P(A1)= 0.5
A2= BRAND 2 is purchased, P(A2)= 0.3
A3= BRAND 3 is purchased, P(A3)= 0.2

Let B = { needs repair}

Then, P(B|A1) = 0.25
P(B|A2) = 0.2
P(B|A3) = 0.1
 BAYES’ THEOREM

Example:
• In a class of 100 students, 45 students have a high IQ
level, 25 students have an average IQ level whereas
the remaining students have a low IQ level. The
probability that a high IQ level student failing in an
examination is 0.007, for an average IQ level student
failing is 0.06 whereas for a low IQ level student the
probability of failing is 0.18. Obtain the following
probabilities:
• If the student has failed in the examination, then what
is the probability that his IQ level is low?
• If the student has passed in the examination, then
what is the probability that his IQ level is high?
•

•
 PRACTICE QUESTION
Members of a consulting firm rent cars from 3 rental
agencies-
60% from agency 1,
30% from agency 2,
10% from agency 3
If 9% of cars rented from agency 1 need a tune up,
20% of cars rented from agency 2 need a tune up and
6% of cars rented from agency 3 need a tune up,
1. What is the probability that a rental car delivered to
the firm will need a tune up?
2. If a rental car delivered to the consulting firm needs a
tune up, what is the probability that it comes from
rental agency 2?

ANSWER
1. B = Car needs a tune up
A1= car comes from agency 1
A2= car comes from agency 2
A3= car comes from agency 3
P(A1)= .6
P(A2)= .3
P(A3)= .1
P(B|A1)= .09
P(B|A2)= 0.2
P(B|A3)= 0.06
HENCE P(B) = (0.6)(0.09) + (0.3)(0.2) + (0.1)(0.06)= 0.12
•

Independence
• 2 events A and B are independent if P(A|B) =
P(A) and dependent otherwise.
(non occurrence or occurrence of either 1 does
not affect prob of occurrence of other)
 Example 2.32, Pg 83, Devore
Consider a gas station with 6 pumps numbered 1,2,….6
and Ei denote the simple event that a randomly selected
customer uses pump i (i=1,2,,,,6). Also,
P(E1) = P(E6)= 0.10
P(E2) = P(E5)= 0.15
P(E3)=P(E4)= 0.25
Let event A = {2,4,6} and
event B = {1,2,3} and
event C = {2,3,4,5}
1. Are events A and B independent?
2. Are events A and C independent?

•
 Alternate formula to check for
independence
•

Example
• It is known that 30% of a certain company's
washing machines require service while under
warranty, whereas only 10% of its dryers need
such service. If someone purchases both a
washer and a dryer made by this company,
1. what is the probability that both machines
will need warranty service?
2. what is the probability that neither machines
need warranty service?
 Solution 1.

Solution 2.
•