0% found this document useful (0 votes)
8 views8 pages

Data Analysis

Baye's Theorem is a probability formula that updates the likelihood of a hypothesis based on new evidence, relating prior and posterior probabilities. The document explains the theorem's formula and provides examples, including a scenario involving a disease test and another involving exam flunkers from different regions. Additionally, it includes homework problems to apply the concepts of Baye's Theorem.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views8 pages

Data Analysis

Baye's Theorem is a probability formula that updates the likelihood of a hypothesis based on new evidence, relating prior and posterior probabilities. The document explains the theorem's formula and provides examples, including a scenario involving a disease test and another involving exam flunkers from different regions. Additionally, it includes homework problems to apply the concepts of Baye's Theorem.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Baye’s

Theorem
Prepared by: Engr. Villamor J. Dela Cruz Jr.
Instructor II
College of Engineering, Architecture &
Technology
Baye’s Thereom

• A formula in probability theory that describes how to update the probability of a


hypothesis when new evidence is introduced.

• It shows the relationship between a “prior probability” – your initial belief about an
event – and a “posterior probability” – the revised probability after accounting for new
information.
Baye’s Theorem Formula

• For two events, A and B the formula is :


Prior
Likelihood The probability of “A” being
The probability of “B” being True. This is the Knowledge
True, given “A” is True

𝑷 𝑩 𝑨 ∙ 𝑷(𝑨)
𝑷 𝑨𝑩 =
𝑷(𝑩)

POSTERIOR Marginalization
The probability of “B” being True
The probability of “A” being
True, given “B” is True
Example Scenario

Imagine a rare disease that only affects 1% of the population. A new


test for this disease is developed with the following characteristics :

• True Positive Rate (Sensitivity): The test correctly identifies the disease in 99% of people
who have it

• False Positive Rate: The test incorrectly gives a positive result in 5% of people who do not
have the disease

Now, consider a person who tests positive. What is the actual probability that this person has the
disease?
𝑷 𝑩 𝑨 ∙ 𝑷(𝑨)
Example Scenario 𝑷 𝑨𝑩 =
𝑷(𝑩)

Define the events based on the problem statement


Imagine a rare disease that only affects Marginal Likelihood, P(B): This is the probability of a person
1% of the population. A new test for this A = The person has the disease testing positive, regardless of whether they have the disease.
B = The person tests positive for the disease.
𝑷(𝑨|𝑩)
disease is developed with the following
characteristics : They have the disease AND test positive (TRUE POSITIVE)
Determine the Probabilities
• True Positive Rate (Sensitivity): The They do NOT have the disease AND test positive
test correctly identifies the disease in Prior Probability, P(A) : based on the rate of the (FALSE POSITIVE)

99% of people who have it disease in the population


Probability of not having the disease, P(not A)
P(A) = 1%
• False Positive Rate: The test P(not A) = 1 – P(A) = 1 – 0.01 = 0.99
incorrectly gives a positive result in Likelihood, P(B|A): This is the probability of a positive
5% of people who do not have the test given the person has the disease (the true positive
Probability of False Positive
rate)
disease
P(B|A) = 99%
P(B|not A) = P(false positive rate) = 5%
Now, consider a person who tests
positive. What is the actual probability Probability of Positive Test P(B)
that this person has the disease? P(B) = 𝐏 𝐁 𝐀 ∙ 𝑷 𝑨 + 𝑷 𝑩 𝒏𝒐𝒕 𝑨 ∙ 𝑷(𝒏𝒐𝒕 𝑨) (𝟎. 𝟗𝟗) ∙ (𝟎. 𝟎𝟏)
𝑷 𝑨𝑩 =
P(B) = 𝟎. 𝟗𝟗 𝟎. 𝟎𝟏 + (𝟎. 𝟎𝟓)(𝟎. 𝟗𝟗) 𝟎. 𝟎𝟓𝟗𝟒
P(B) = 𝟎. 𝟎𝟓𝟗𝟒 𝑷 𝑨 𝑩 = 𝟎. 𝟏𝟔𝟔𝟕

Even with a positive test result from a highly accurate test, there is only about a
16.7% chance that the person actually has the disease.
𝑷 𝑭 𝑴 ∙ 𝑷(𝑴)
Example Scenario 𝑷 𝑴𝑭 =
𝑷(𝑭)

Define the events based on the problem statement


During the board examination in civil
Probability of the Examinee Flunking, P(F)
engineering, there were 350 L = examinee from Luzon

examinees from Luzon, 250 from V = examinee from Visayas


𝑷 𝑴𝑭 𝑷 𝑭 = 𝑷 𝑭 𝑳 ∙ 𝑷 𝑳 + 𝑷 𝑭 𝑽 ∙ 𝑷 𝑽 + 𝑷 𝑭 𝑴 ∙ 𝑷(𝑴)
Visayas, and 400 from Mindanao. M = examinee from Mindanao
F = examinee is a flunker 𝟑𝟓𝟎
The results of the exam revealed 𝑷 𝑭 𝑳 = 𝟑% 𝑷 𝑳 = = 𝟎. 𝟑𝟓
𝟏𝟎𝟎𝟎
that the flunkers from Luzon,
𝟐𝟓𝟎
Visayas, and Mindanao were 3%, 𝑷 𝑭 𝑽 = 𝟓% 𝑷 𝑽 = = 𝟎. 𝟐𝟓
The probability of a person flunking given they are from 𝟏𝟎𝟎𝟎
5% and 7% respectively. If the name mindanao
of the flunker is picked at random, 𝑷 𝑭 𝑴 = 𝟕% 𝑷 𝑭 𝑴 = 𝟕%
what is the probability that he/she is
from Mindanao? 𝑷 𝑭 = 𝟎. 𝟎𝟑 𝟎. 𝟑𝟓 + 𝟎. 𝟎𝟓 𝟎. 𝟐𝟓 + (𝟎. 𝟎𝟕)(𝟎. 𝟒𝟎)
The probability of a person flunking given they are from
Mindanao 𝑷 𝑭 = 𝟎. 𝟎𝟓𝟏

𝟒𝟎𝟎 𝟒𝟎𝟎
𝑷 𝑴 = = = 𝟎. 𝟒𝟎 (𝟎. 𝟎𝟕) ∙ (𝟎. 𝟒𝟎)
𝟑𝟓𝟎 + 𝟐𝟓𝟎 + 𝟒𝟎𝟎 𝟏𝟎𝟎𝟎 𝑷 𝑴𝑭 =
𝟎. 𝟎𝟓𝟏
The probability of that the Flunker is from Mindanao 𝟐𝟖
is 28/51 or 54.9%. = = 𝟎. 𝟓𝟒𝟗
𝟓𝟏
Homework
1. In a certain town, 60% of the people have fair complexion, 40% have a tall height, and
20% have both fair complexion and tall height. A person is selected at random from the
town.
a.) if the person has a fair complexion, what is the probability that he or she also has a
tall height?
b.) If the person has a tall height, what is the probability that he or she does not have a
fair complexion?
Homework
2. Two urns contain balls of different colors. Urn 1 contains 4 red, and 3 black balls, and
Urn 2 contains 5 red and 4 black balls. One ball is transferred from Urn 1 to Urn 2 and
then a ball is drawn from Urn 2. If the ball drawn is found to be red in color, what is the
probability that the transferred ball is black?

You might also like