Introduction To Probability

Introduction to Probability
Introduction to Business Analytics - Batch 23@XIME

Experiment is any procedure that can be
repeated many times and has a well-defined
set of outcomes
The set of all possible outcomes for an

experiment is the sample space
Event is a subset of points in a sample space

Quiz
You toss two fair dice. What is the sample

space?
The total number of dots showing on two

dice is eight. What is this?
When two coins are tossed, a total of one

head is observed. What is this?
Axioms
For any event E, 0<=P(E)<=1
If the event consists of all the points in the

sample space, then P(E) = ?
Law of Complements
P(Not A) = 1 - P(A)
What is the chance that you do not throw a

total of 2?
Mutually Exclusive Events
If two events cannot occur simultaneously, the events are mutually

exclusive
Event A= Interest rate on fixed deposits goes up by at least 10% in 2018
and Event B = Interest rate on fixed deposits goes up by at least 15% in
2018, are the events A and B mutually exclusive?
If event A = total with two dice is 4 and event B = total with two dice is
8, are the two events A and B mutually exclusive?
Additive rule for computing
probabilities
P(A or B) = P(A)+P(B) - P(A and B){You

subtract this to avoid double counting}
If A and B are mutually exclusive what is P(A

or B)?
If there is a 50% chance of rain on Saturday

and a 50% chance of rain on Sunday, can we
be certain of rain during the weekend?
Independent Events
Two events A and B are independent if

knowing that one event has occurred does
not change your estimate of the probability of
the other event occurring
Two events are independent if and only if

P(A and B) = P(A) * P(B)
Are these independent events?
A= Average salary offered to students jumps

to 8L/year in December 2018
B = Students can enter the hostel at 3 am on

Sunday and Saturday(Low, very low, very
very low probability )
Conditional Probability
We define the conditional probability of event

B occurring, given that event A has occurred
as P(B|A) = P(A and B)/P(A)
Rewrite as P(A and B)=P(A)*P(B|A) or

P(B)*P(A|B)
If P(B|A) = P(B), what can you tell about

events A and B?
Suppose you toss two dice. A = Event you get
at least one 6 and B = Event total of the two
dice is 10. What is P(B|A)?
Law of total probability
Refers to computing the probability of an

event by adding together the probabilities of
several mutually exclusive events
Sometimes we can compute the probability of

an event by conditioning it on other events.
Suppose 5% of used cars have flood damage and
80% of those cars later develop engine problems
Also, suppose that 10% of cars that are not

damaged by flood later develop engine
problems.
What is the chance that a randomly chosen car

will have engine problems?
P(EP)=P(EP and FL) + P(EP and no FL) = P(EP|

FL)* P(FL) +P(EP|no FL)* P(no FL)
Contingency Table Engine Problem No engine problem
Flood Damage 0.04 0.01
No Flood Damage 0.095 0.855

Bayes’ Theorem
Understand conditional probability and the

law of total probability
In many situations, we are trying to estimate

the probabilities of various states of the
world
Then we receive information that we use to

change our probability estimates
Consider a 40 year old woman with no risk
factors for cancer
Event C = Woman has cancer
Event NC = Woman does not have cancer
Given no other information, probabilities of

these events(known as prior or a priori) are
given by P(C)= .004 and P(NC) = .996
Now we receive more information(results of
a test for cancer) that change our estimates of
prior probabilities
Suppose a test yields a positive(+) result
To update our probability estimates, we need

to know the likelihood of a positive test result
for each state of the world
These are known-: P(+|C) = 0.80 and P(+|

NC) = 0.10
Now we want to update our prior
probability(.004) of cancer after receiving the
positive test result
The new probability P(C|+) is called

posterior or a posteriori probability
Applying the definitions of conditional

probability and the law of total probability
we find…
P(C|+) = P(C and +)/P(+)
P(C and +) = P(+|C)*P(C) = ?
P(+) = P(+|C)*P(C)+P(+|NC)*P(NC) = ?
What is a false positive?

10,000 women + Test -Test
Cancer
No Cancer
Are events A and Not A mutually exclusive?
Can mutually exclusive events be

independent?
You are studying finance and marketing.
Assume that you have a 90% chance of
getting an A in Finance and an 80% chance of
getting an A in marketing. If your
performance in each of the two courses is
independent of the other, what is the
probability of your getting at least one ‘A’ ?
Suppose 10% of all adults watch Big Boss.
Assume that 80% of these viewers are women
and half of all adults are men. Compute the
probability that a given woman or man is a
viewer of Big Boss.
Assume that one in every 1000 people is a
liar(incapable of telling the truth). Also,
suppose a lie-detector test is 98% accurate.
That is, if a person is lying there is a 98%
chance that the test will indicate the person is
lying. Also, if the person is not lying, there is
a 98% chance the test will indicate the person
is not lying. If the lie-detector test indicates
the person is lying, what is the chance the
person is lying?
Of an insurance company’s policyholders,
80% are high risk and 20% are low risk.
assume nobody has more than one accident
in a year. Also, assume 10% of high-risk
people have an accident during a year and
3% of low-risk people have an accident
during a year. if you randomly choose a
policyholder who had an accident last year,
what is the chance that he or she is a high-
risk policyholder?

Introduction To Probability

Uploaded by

Copyright:

Available Formats

Introduction To Probability

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Introduction To Probability

Uploaded by

Copyright:

Available Formats

Introduction to Probability

Introduction to Business Analytics - Batch 23@XIME

The set of all possible outcomes for an

Event is a subset of points in a sample space

You toss two fair dice. What is the sample

The total number of dots showing on two

When two coins are tossed, a total of one

For any event E, 0<=P(E)<=1

If the event consists of all the points in the

What is the chance that you do not throw a

If two events cannot occur simultaneously, the events are mutually

P(A or B) = P(A)+P(B) - P(A and B){You

If A and B are mutually exclusive what is P(A

If there is a 50% chance of rain on Saturday

Two events A and B are independent if

Two events are independent if and only if

A= Average salary offered to students jumps

B = Students can enter the hostel at 3 am on

We define the conditional probability of event

Rewrite as P(A and B)=P(A)*P(B|A) or

If P(B|A) = P(B), what can you tell about

Refers to computing the probability of an

Sometimes we can compute the probability of

Also, suppose that 10% of cars that are not

What is the chance that a randomly chosen car

P(EP)=P(EP and FL) + P(EP and no FL) = P(EP|

Flood Damage 0.04 0.01

No Flood Damage 0.095 0.855

Understand conditional probability and the

In many situations, we are trying to estimate

Then we receive information that we use to

Event C = Woman has cancer

Event NC = Woman does not have cancer

Given no other information, probabilities of

Suppose a test yields a positive(+) result

To update our probability estimates, we need

These are known-: P(+|C) = 0.80 and P(+|

The new probability P(C|+) is called

Applying the definitions of conditional

P(C and +) = P(+|C)*P(C) = ?

What is a false positive?

Can mutually exclusive events be

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.