MATERIAL04

4th Material Subject: Conditional Probability &
Bayes Theorem
Undergraduate of Telecommunication Engineering
MUH1F3 - PROBABILITY AND STATISTICS
Telkom University
Center of eLearning & Open Education Telkom University
Jl. Telekomunikasi No.1, Bandung - Indonesia
http://www.telkomuniversity.ac.id
Lecturer: Nor Kumalasari Caecar Pratiwi, S.T., M.T. (caecarnkcp@telkomuniversity.ac.id)

TABLE OF CONTENTS:
1. Conditional Probability
2. Multiplication and Total Probability Rules
3. Bayes Theorem
LEARNING OBJECTIVES:
After careful study of this chapter, student should be able to do the following:
1. Use Bayes theorem to calculate conditional probabilities
2. Interpret and calculate conditional probabilities of events
2/14 May 10, 2020 LECTURER CODE: NKC/
CONDITIONAL PROBABILITY
If event A and B are Dependent, the probability of an event B under the knowledge that the outcome will be in
event A is denoted as:
P(A ∩ B)
P(B|A) = , with P(A) >0 (1)
P(A)
and this is called the Conditional Probability of B given A. Otherwise, the probability of an event A under the
knowledge that the outcome will be in event B is denoted as:
P(A ∩ B)
P(A|B) = , with P(B) >0 (2)
P(B)
and this is called the Conditional Probability of A given B.

1
Example: A digital communication channel has an error rate of 1 bit per every 1000 transmitted (BER = 1000
).
Errors are rare, but when they occur, they tend to occur in bursts that affect many consecutive bits. If a single
bit is transmitted. However, if the previous bit was in error because of the bursts, we might believe that the
probability that the next bit will be in error is greater than is transmitted.
MULTIPLICATION AND TOTAL PROBABILITY
RULES
The conditional probability definition in equation (1) and (2) can be rewritten to provide a formula known as
the Multiplication Rule for probabilities.
P(A ∩ B) = P(B|A) · P(A) = P(A|B) · P(B) (3)
Figure 1: Partitioning an event into two mutually exclusive Figure 2: Partitioning an event into several mutually
0
subsets, where A and A are partition of U exclusive subsets, where E1 ,E2 , · · · Ek are partition of U
RULES
0
From Figure 1, shown A and A are partition of U and both are mutually exclusive events:
0 0
P(A ∪ A ) = P(A) + P(A ) (4)
The following Total Probability Rule for event B is obtained:
0 0
B = B ∩ U = B ∩ (A ∪ A ) = (B ∩ A) ∪ (B ∩ A )
Therefor:
0 0 0
P(B) = P(B ∩ A) + P(B ∩ A ) = P(B|A) · P(A) + P(B|A ) · P(A ) (5)

RULES
In general, see Figure 2, shown E1 ,E2 , · · · Ek are partition of U and they are mutually exclusive events:
P(E1 ∪ E2 ∪ · · · ∪ Ek ) = P(E1 ) + P(E2 ) + · · · + P(Ek ) (6)
The following Total Probability Rule for event B is obtained:
B = B ∩ U = B ∩ (E1 ∪ E2 ∪ · · · ∪ Ek ) = (B ∩ E1 ) ∪ (B ∩ E2 ) ∪ · · · ∪ (B ∩ Ek )
Therefor:
P(B) = P(B ∩ E1 ) + P(B ∩ E2 ) + · · · + P(B ∩ Ek )
P(B) = P(B|E1 ) · P(E1 ) + P(B|E2 ) · P(E2 ) + · · · + P(B|Ek ) · P(Ek ) (7)

RULES
In general, a collection of event E1 , E2 , · · · Ek such that E1 ∪ E2 ∪ · ∪ Ek = U said to be exhaustive.
P(B) = P(B ∩ E1 ) + P(B ∩ E2 ) + · · · + P(B ∩ Ek )
P(B) = P(B|E1 ) · P(E1 ) + P(B|E2 ) · P(E2 ) + · · · + P(P|Ek ) · P(Ek ) (8)
The Equation (5) and (8) called the Total Probability Rule

EXAMPLE
A photocopying company using 3 machines with a percentage of each use 55 %, 30 % and 15 %. Each machine
produces its own defects 8 %, 5 %, and 4 %. From the overall results of photocopying from all machines, one
sheet is chosen randomly.
a. Draw a tree diagram for the above situation!
b. Calculate the probability selected result is good!
c. Calculate the probability selected result is defect!
d. If the selected result is defect, calculate the probability of those results coming from the second machine!
e. If the selected result is good,calculate the probability that the result will come from the first machine!

EXAMPLE
ANSWER: We first determine the possibility of any event will happen:

• A is event that states the selected paper from first machine
• B is event that states the selected paper from second machine
• C is event that states the selected paper from third machine
• G is event that states the selected paper in good condition
• G is event that states the selected paper in defect condition

EXAMPLE
a. The tree diagram for the above situation

EXAMPLE
b. The probability selected result is good → Total Probability Rules
P(G) = P(G ∩ A) + P(G ∩ B) + P(G ∩ C)

P(G) = P(G|A) · P(A) + P(G|B) · P(B) + P(G|C) · P(C)
187
P(G) = 0.92 · 0.55 + 0.95 · 0.3 + 0.96 · 0.15 = = 0.935
200

EXAMPLE
c. The probability selected result is defect → Total Probability Rules
P(G) = P(G ∩ A) + P(G ∩ B) + P(G ∩ C)

P(G) = P(G|A) · P(A) + P(G|B) · P(B) + P(G|C) · P(C)
13
P(G) = 0.08 · 0.55 + 0.05 · 0.3 + 0.05 · 0.15 = = 0.065
200
Or, simply we can calculate:
187 13
P(G) = 1 − P(G) = 1 − = = 0.065
200 200
EXAMPLE
d. If the selected results are defect, the probability of those results coming from the second machine is →
Conditional Probability
P(C ∩ G) P(B) · P(G|B) 0.3 · 0.05 3

P(B|G) = = = = = 0.23
P(G) P(G) 0.065 13
e. If the selected result is good, the probability that the result will come from the first machine is
P(A ∩ G) P(A) · P(G|A) 0.55 · 0.92 46

P(A|G) = = = = = 0.54
P(G) P(G) 0.935 85

Thank You

MATERIAL04

Uploaded by

Copyright:

Available Formats

MATERIAL04

Uploaded by

Document Information

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

MATERIAL04

Uploaded by

Copyright:

Available Formats

4th Material Subject: Conditional Probability &

Lecturer: Nor Kumalasari Caecar Pratiwi, S.T., M.T. (caecarnkcp@telkomuniversity.ac.id)

and this is called the Conditional Probability of A given B.

P(A ∩ B) = P(B|A) · P(A) = P(A|B) · P(B) (3)

The following Total Probability Rule for event B is obtained:

5/14 May 10, 2020 LECTURER CODE: NKC/

P(E1 ∪ E2 ∪ · · · ∪ Ek ) = P(E1 ) + P(E2 ) + · · · + P(Ek ) (6)

The following Total Probability Rule for event B is obtained:

6/14 May 10, 2020 LECTURER CODE: NKC/

In general, a collection of event E1 , E2 , · · · Ek such that E1 ∪ E2 ∪ · ∪ Ek = U said to be exhaustive.

P(B) = P(B ∩ E1 ) + P(B ∩ E2 ) + · · · + P(B ∩ Ek )

P(B) = P(B|E1 ) · P(E1 ) + P(B|E2 ) · P(E2 ) + · · · + P(P|Ek ) · P(Ek ) (8)

7/14 May 10, 2020 LECTURER CODE: NKC/

a. Draw a tree diagram for the above situation!

b. Calculate the probability selected result is good!

c. Calculate the probability selected result is defect!

8/14 May 10, 2020 LECTURER CODE: NKC/

ANSWER: We first determine the possibility of any event will happen:

9/14 May 10, 2020 LECTURER CODE: NKC/

10/14 May 10, 2020 LECTURER CODE: NKC/

b. The probability selected result is good → Total Probability Rules

P(G) = P(G ∩ A) + P(G ∩ B) + P(G ∩ C)

11/14 May 10, 2020 LECTURER CODE: NKC/

P(G) = P(G ∩ A) + P(G ∩ B) + P(G ∩ C)

P(C ∩ G) P(B) · P(G|B) 0.3 · 0.05 3

P(A ∩ G) P(A) · P(G|A) 0.55 · 0.92 46

13/14 May 10, 2020 LECTURER CODE: NKC/

14/14 May 10, 2020 LECTURER CODE: NKC/

You might also like

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