ST 1

Probability Theory and
Bayes’ Theorem
 In our day-to-day life involving decision-making
problems, we deal with two broad types of problems.
These problems can be categorized into two types of
models:
1. Deterministic Models
2. Random or Probabilistic Models
1. Deterministic Models cover those situations, where
everything related to the situation is known with certainty to
the decision-maker, when decision is to be made.
2. Probabilistic Models, the totality of the outcomes is

known but it can not be certain, which particular outcome will
appear. So, there is always some uncertainty involved in
decision-making.
Probability:- is a measure of the likelihood of an event to occur. The
probability formula is defined as the possibility of an event to happen
and is equal to the ratio of the number of favorable outcomes to the total
number of outcomes.
Number of favorable outcomes
Probability =
Total number of outcomes
 Probabilities are expressed as fractions (1⁄6, 1⁄2, 8⁄9) or as decimals

(0.167, 0.500, 0.889) between zero and 1. Assigning a probability of
zero means that something can never happen; a probability of 1
indicates that something will always happen.
 In probability theory, an event is one or more of the possible outcomes
of doing something. If we toss a coin, getting a tail would be an event,
and getting a head would be another event.
 When a coin is tossed, there are only two possible outcomes.
Therefore, using the probability formula on tossing a coin, the
probability of getting a head is:
P(Head) = P(H) = ½
 Similarly, the probability of getting a tail is:

P(Tail) = P(T) = ½
 While tossing two different coins at the same time, then such
condition can be represented in tabular form as follows:
Second toss
H T
First toss H HH HT
T TH TT
S = (HH,HT,TH,TT)
Then, Probability of two heads = P(two heads) = ¼
P(one head) = 2/4 = ½
P(no heads) = 1/4
Probability Laws
 Venn diagram is a graph allowing one conceptually to represent the
occurrence of various events of interest.
 A denotes the occurrence of a particular event, and 𝐴ҧ denotes the
complementary event, its nonoccurrence.
Fig 1: Venn diagram showing the sample space and the events A and 𝐴ҧ
 Venn diagram representing the sample space (all possible
events) contain all elements in A (circle with diagonal lines)
and all the elements in 𝐴ҧ (remaining shaded area surrounding
the circle in Fig 1).
P(A) = 1 – P(𝑨ഥ)
Where P(A) = probability of the event A occurring
P(𝐴)ҧ = probability of the event A not occurring
Independent events:
 If A and B are two independent events, then probability that both will
happen, the joint probability – also known as the intersection 𝐴 ∩ 𝐵 of
the two events- is the product of their respective probabilities:
P(𝑨 ∩ 𝑩 ) = P (A and B) = P(AB) = P(A)P(B)

Not Mutually exclusive events
Fig 2: Venn diagram showing two events that are not mutually exclusive
If the events A and B are independent but not mutually exclusive events –
that is, P(AB)≠0. Then probability of at least one of these events
occurring is given by sum of the individual probabilities minus their joint
probability:
P(A and/or B) = P(A+B) = P(A) + P(B) – P(AB)
Not Mutually exclusive events
Fig 3: Venn diagram for three events A, B, and C that are not mutually
exclusive events
 If three events A,B and C are considered, and these events are not
mutually exclusive events, then the probability P(A and/or B and/or C) =
P(A + B + C ) is given as follows:
P(A + B + C) = P(A) + P(B) + P(C) – P(AB) – P(AC) – P(BC) –
P(ABC)
Mutually exclusive events
Fig 4: Venn diagram for two mutually exclusive events

 If A and B are mutually exclusive events, then either A or B may
occur, but not both; that is, P(AB) = 0. Then probability that either
one or the other of these events will takes place is the sum of their
probabilities:
P(A or B) = P(A) + P(B)
Conditional Probability:
 Often, events are not independent, and the occurrence of one alters
the probability of the second.
 The conditional probability of event B, given that A has occurred, is
written as P(B/A). In general,
𝑃(𝐴𝐵)
P(B/A) = ………………….(1)
𝑃(𝐴)
 Solving the above expression for P(AB), the probability of joint

occurrence AB is given by product of the conditional probability of
B, given that A has occurred, and the probability of A:
P(AB) = P(B/A) P(A)……………….(2)
Example 1:-
In a suburban neighborhood in the US, 25% of these homes have slab

foundation, and 75% do not. Previous studies have shown that 80% of
the homes with slab foundation in this region have indoor urban
problems due to intrusion of radon gas from the soil beneath. Of those
homes without slab floors, 10% have indoor radon problems due to
the remaining indoor sources of radon, such as construction material.
The following events are possible in this example:
A= event “house has a slab foundation”
𝐴ҧ = event “house does not have a slab foundation”
B = event “house has an indoor radon problem”
𝐵ത = event “house does not have an indoor radon problem”
Representing the percentage as probabilities, this problem is

summarized formally as follows:
P(A) = 0.25 P(𝐴)ҧ = 0.75
P(B/A) = 0.80 ത
P(𝐵/A) = 0.20
P(B/𝐴)ҧ = 0.10 ത 𝐴)ҧ = 0.90
P(𝐵/
 Then, the probability of finding a house with slab foundation (A)
and a radon problem (B) is given by the product of the conditional
probability that a house has a radon problem, given that it has a slab
foundation, and the probability that it has a slab foundations:
P(B/A) P(A) = P(AB) = 0.80*0.25 = 0.20
 Similarly, the probability that a house chosen at random has a radon

problem and does not have a slab foundation is given by the
product of the conditional probability of a radon problem, given
that the house does not have a slab foundation, and the probability
that the house does not have a slab foundation:
P(B/𝐴)ҧ P(𝐴)ҧ = P(𝐴B)
ҧ = 0.10*0.75 = 0.075
 Because the occurrence of an indoor radon problem in a house that
has a slab foundation and the occurrence of a radon problem in a
house that does not are mutually exclusive events, it follows that
the probability of an indoor radon problem irrespective of the type
of foundation, is the union of the two events, or sum of the joint
probabilities of the two possible cases:
P(B) = P(B/A) P(A) + P(B/𝐴)ҧ P(𝐴)ҧ
= 0.20 + 0.075
= 0.275
Thus, 27.5% of the homes will have indoor radon problems.

Bayes’ Theorem
 A useful law called Bayes’ theorem can be developed from the
concept of conditional probability.
 In the conditional probability expression P(B/A), B is called
posterior events and A is called prior events.
 Thus, P(A) is known as prior probability and P(B) is known as
posterior probability.
 Therefore, probability of A given that B has occurred or P(A/B):
𝑃(𝐴𝐵)
P(A/B) = ……………(3)
𝑃(𝐵)
 It was shown from Eq. (2):
P(AB) = P(B/A) P(A)
Substituting this expression into the Eq. (3):
P(B/A) P(A)
P(A|B) = …………..(4)
𝑃(𝐵)
 Because P(B) is the sum of the probabilities of two mutually
exclusive events,
P(B) = P(AB) + P(𝐴B) ҧ
= P(B/A) P(A) + P(B/𝐴)ҧ P(𝐴)ҧ
 Substituting this expression for P(B) into Eq. (4):
 The following equation gives the “general form” which is known as
Bayes’ Theorem:
P(B/A) P(A)
P(A/B) = ………(5)
P(B/A) P(A) + P(B/Aത ) P(Aത )
 Dividing both the numerator and denominator by P(B/A) P(A), this

equation for Bayes’ Theorem also can be written as:
1
P(A/B) = …………………………....(6)
1+
P(B/ ഥ )P(A
A ഥ)
P(B/A) P(A)
Hence in the previous Example 1,
 Substituting the given values in the following equation:
1
P(A/B) = 0.10 0.75 = 0.7273
1+ 0.80 0.25
 Thus, rounding off this result, we can expect approximately 73% of

the homes reporting radon problem to have slab foundations.
 Initially the prior probability of slab foundation was P(A) = 0.25.
Once a radon problem was found in a particular house, it was
possible to update the original probability for that house, and the
probability that the house had a slab foundation became P(A|B) =
0.7273 = P(A’). Here P(A’) is the updated or posterior probability.
Thank You!!

ST 1

Uploaded by

Copyright:

Available Formats

ST 1

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

ST 1

Uploaded by

Copyright:

Available Formats

Probability Theory and

2. Probabilistic Models, the totality of the outcomes is

 Probabilities are expressed as fractions (1⁄6, 1⁄2, 8⁄9) or as decimals

 Similarly, the probability of getting a tail is:

P(𝑨 ∩ 𝑩 ) = P (A and B) = P(AB) = P(A)P(B)

Fig 4: Venn diagram for two mutually exclusive events

 Solving the above expression for P(AB), the probability of joint

In a suburban neighborhood in the US, 25% of these homes have slab

Representing the percentage as probabilities, this problem is

 Similarly, the probability that a house chosen at random has a radon

Thus, 27.5% of the homes will have indoor radon problems.

 Dividing both the numerator and denominator by P(B/A) P(A), this

 Thus, rounding off this result, we can expect approximately 73% of

You might also like

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