Bayes Theorem Application

Example 1: Medical Diagnosis
Suppose a rare disease, "X," affects 1% of the population. There is a medical

test for this disease that is 95% accurate for both positive and negative
results. If a person tests positive for the disease, what is the probability that
they actually have it?
Solution:
Let's define the events:
 A: Having the disease (1% chance, P(A) = 0.01)

 B: Testing positive for the disease (conditional probability, P(B|A) =
0.95)
We want to find P(A|B), the probability of having the disease given a

positive test result. Using Bayes' theorem:
P(A|B) = [P(B|A) * P(A)] / P(B)
P(B) can be calculated using the law of total probability:
P(B) = P(B|A) * P(A) + P(B|¬A) * P(¬A)
P(B|¬A) is the probability of testing positive given that you don't have the
disease, which is the false positive rate. In this case, it's 5% (0.05).
P(¬A) is the probability of not having the disease, which is 99% (1 - 0.01).
Now, plug these values into the formula:
P(B) = (0.95 * 0.01) + (0.05 * 0.99) = 0.0149
Now, use Bayes' theorem to find P(A|B):
P(A|B) = (0.95 * 0.01) / 0.0149 ≈ 0.637
So, if a person tests positive for the disease, the probability that they
actually have it is approximately 63.7%.
Example 2: Email Spam Detection
Suppose you receive an email with certain keywords commonly found in

spam emails. If 90% of spam emails contain those keywords, but only 10%
of legitimate emails do, and you know that 30% of the emails in your inbox
are spam, what's the probability that an email containing these keywords is
spam?
Solution:
 A: The email contains the keywords (P(A) = ?)

 B: The email is spam (P(B) = 0.30)
 ¬B: The email is not spam (P(¬B) = 0.70)
 P(A|B) = 0.90 (probability that a spam email contains the keywords)
 P(A|¬B) = 0.10 (probability that a legitimate email contains the
keywords)
We want to find P(B|A), the probability that the email is spam given that it
contains the keywords. Using Bayes' theorem:
P(B|A) = [P(A|B) * P(B)] / P(A)
Now, we need to calculate P(A):
P(A) = P(A|B) * P(B) + P(A|¬B) * P(¬B) P(A) = (0.90 * 0.30) + (0.10 * 0.70) =
0.27 + 0.07 = 0.34
Now, use Bayes' theorem to find P(B|A):
P(B|A) = (0.90 * 0.30) / 0.34 ≈ 0.794
So, if an email contains the keywords, the probability that it's spam is
approximately 79.4%.
Example 3: Weather Prediction
Suppose a meteorologist predicts that there is a 70% chance of rain on a

given day. However, historical data shows that the meteorologist is correct
only 60% of the time when predicting rain and 90% of the time when
predicting no rain. What's the probability that it will rain given the
meteorologist's prediction?
Solution:
 A: It rains (P(A) = ?)
 B: Meteorologist predicts rain (P(B) = 0.70)
 ¬B: Meteorologist predicts no rain (P(¬B) = 0.30)
 P(A|B) = 0.60 (probability of correct rain prediction)
 P(A|¬B) = 0.90 (probability of correct no-rain prediction)
We want to find P(A|B), the probability that it will rain given the
meteorologist's prediction. Using Bayes' theorem:
P(A|B) = [P(B|A) * P(A)] / P(B)
Now, we need to calculate P(B):
P(B) = P(B|A) * P(A) + P(B|¬A) * P(¬A) P(B) = (0.60 * P(A)) + (0.30 * (1 - P(A)))
We know that P(A) + P(¬A) = 1, so P(¬A) = 1 - P(A). Substituting this into

the equation:
P(B) = (0.60 * P(A)) + (0.30 * (1 - P(A)))
Now, we can use the fact that P(B) = 0.70:
0.70 = (0.60 * P(A)) + (0.30 * (1 - P(A)))
Solve for P(A):
0.70 = 0.60P(A) + 0.30 - 0.30P(A) 0.40P(A) = 0.40 P(A) = 0.40 / 0.40 P(A) = 1
Now that we know P(A) is 1, we can use Bayes' theorem to find P(A|B):
P(A|B) = (0.60 * 1) / 0.70 ≈ 0.857

So, if the meteorologist predicts rain, the probability that it will rain is
approximately 85.7%.
Example 1: Medical Diagnosis
Suppose a rare disease, "Disease X," affects 1% of the population. A

diagnostic test for Disease X is not perfect, with a false positive rate of 5%
and a false negative rate of 2%. If a randomly selected person tests positive
for Disease X, what is the probability that they actually have the disease?
Solution: Let A be the event that a person has Disease X, and B be the event
that the test result is positive. We want to find P(A | B), the probability that
a person has the disease given a positive test result.
Using Bayes' Theorem: P(A∣B)=P(B)P(B∣A)∗P(A)
P(B | A) = Probability of a positive test result given that a person has the
disease = 1 - False Negative Rate = 1 - 0.02 = 0.98 P(A) = Prior probability
of having the disease = 0.01 P(B) = Total probability of a positive test result
= P(B | A) * P(A) + P(B | ¬A) * P(¬A) = (0.98 * 0.01) + (0.05 * 0.99) ≈ 0.0587
Now, calculate P(A | B): P(A∣B)=0.05870.98∗0.01≈0.1668
So, given a positive test result, the probability that a person actually has
Disease X is approximately 16.68%.
Example 2: Email Spam Detection
Suppose you receive an email, and your spam filter has previously
determined that 90% of spam emails contain the word "free," while only
10% of legitimate emails contain this word. If the email you received
contains the word "free," what is the probability that it's spam?
Solution: Let A be the event that an email is spam, and B be the event that
the email contains the word "free." We want to find P(A | B), the probability
that the email is spam given that it contains the word "free."
Using Bayes' Theorem: P(A∣B)=P(B)P(B∣A)∗P(A)

P(B | A) = Probability of an email containing "free" given that it's spam =
0.90 P(A) = Prior probability of an email being spam = 0.50 (assuming a
50% spam rate) P(B) = Total probability of an email containing "free" = P(B |
A) * P(A) + P(B | ¬A) * P(¬A) = (0.90 * 0.50) + (0.10 * 0.50) = 0.50
Now, calculate P(A | B): P(A∣B)=0.500.90∗0.50=0.90
So, if an email contains the word "free," the probability that it's spam is
90%.
Example 3: Coin Toss
Suppose you have two coins in a bag. Coin A is a fair coin (50% chance of
heads), while Coin B is biased (80% chance of heads). You randomly choose
one of the coins and toss it, and it comes up heads. What is the probability
that you chose Coin B?
Solution: Let A be the event of choosing Coin A, and B be the event of

choosing Coin B. Let H be the event of getting heads. We want to find P(B |
H), the probability that you chose Coin B given that you got heads.
Using Bayes' Theorem: P(B∣H)=P(H)P(H∣B)∗P(B)
P(H | B) = Probability of getting heads with Coin B = 0.80 P(B) = Probability

of choosing Coin B = 0.50 (assuming an equal chance of choosing either
coin) P(H) = Total probability of getting heads = P(H | A) * P(A) + P(H | B) *
P(B) = (0.50 * 0.50) + (0.80 * 0.50) = 0.65
Now, calculate P(B∣H)=0.650.80∗0.50≈0.6154
So, if you got heads, the probability that you chose Coin B is approximately
61.54%.
1. Medical Diagnosis: Suppose a medical test is used to detect a rare

disease, and the test is known to have a 95% accuracy rate (true
positive rate). However, the test also produces false positives 10% of
the time. If the prevalence of the disease in the population is 2%, you
can use Bayes' theorem to calculate the probability that a person
actually has the disease given that they tested positive.
P(Disease) = 0.02 (prevalence) P(Positive | Disease) = 0.95 (true
positive rate) P(Positive | No Disease) = 0.10 (false positive rate)
Using Bayes' theorem: P(Disease | Positive) = [P(Positive | Disease) *
P(Disease)] / [P(Positive | Disease) * P(Disease) + P(Positive | No
Disease) * P(No Disease)]
Plug in the values: P(Disease | Positive) = [0.95 * 0.02] / [0.95 * 0.02 +
0.10 * 0.98] ≈ 0.1637 or 16.37%
So, the probability that a person actually has the disease given a
positive test result is approximately 16.37%.
2. Card Games: Consider a deck of cards. You draw a card at random,
but before showing it to you, someone tells you whether it's a red
card (heart or diamond) or a black card (spade or club). You want to
find the probability that the card is a heart given that it's red.
P(Heart) = 13/52 (number of hearts in a deck of 52 cards) P(Red) =
26/52 (number of red cards in a deck of 52 cards)
Using Bayes' theorem: P(Heart | Red) = [P(Red | Heart) * P(Heart)] /
P(Red)
Since P(Red | Heart) is 1 (if it's a heart, it's red), the formula simplifies
to: P(Heart | Red) = (1 * 13/52) / (26/52) = 0.5 or 50%
So, the probability that the card is a heart given that it's red is 50%.
3. Weather Prediction: Suppose a meteorologist predicts that there is
an 80% chance of rain when the sky is cloudy and a 20% chance of
rain when the sky is clear. On a given day, the sky is cloudy 60% of
the time and clear 40% of the time. You want to find the probability
of rain on that day.
P(Rain | Cloudy) = 0.80 (probability of rain when cloudy) P(Rain |
Clear) = 0.20 (probability of rain when clear) P(Cloudy) = 0.60
(probability of a cloudy day)
Using Bayes' theorem: P(Rain) = [P(Rain | Cloudy) * P(Cloudy)] +
[P(Rain | Clear) * P(Clear)]
Plug in the values: P(Rain) = (0.80 * 0.60) + (0.20 * 0.40) = 0.48 + 0.08
= 0.56 or 56%
So, the probability of rain on that day is 56%.

Bayes Theorem Application

Uploaded by

Copyright:

Available Formats

Bayes Theorem Application

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

Bayes Theorem Application

Uploaded by

Copyright:

Available Formats

Example 1: Medical Diagnosis

Suppose a rare disease, "X," affects 1% of the population. There is a medical

Let's define the events:

 A: Having the disease (1% chance, P(A) = 0.01)

We want to find P(A|B), the probability of having the disease given a

P(A|B) = [P(B|A) * P(A)] / P(B)

P(B) can be calculated using the law of total probability:

P(B) = P(B|A) * P(A) + P(B|¬A) * P(¬A)

Now, plug these values into the formula:

P(B) = (0.95 * 0.01) + (0.05 * 0.99) = 0.0149

Now, use Bayes' theorem to find P(A|B):

P(A|B) = (0.95 * 0.01) / 0.0149 ≈ 0.637

Suppose you receive an email with certain keywords commonly found in

Let's define the events:

 A: The email contains the keywords (P(A) = ?)

P(B|A) = [P(A|B) * P(B)] / P(A)

Now, we need to calculate P(A):

Now, use Bayes' theorem to find P(B|A):

P(B|A) = (0.90 * 0.30) / 0.34 ≈ 0.794

Example 3: Weather Prediction

Suppose a meteorologist predicts that there is a 70% chance of rain on a

Let's define the events:

P(A|B) = [P(B|A) * P(A)] / P(B)

Now, we need to calculate P(B):

We know that P(A) + P(¬A) = 1, so P(¬A) = 1 - P(A). Substituting this into

P(B) = (0.60 * P(A)) + (0.30 * (1 - P(A)))

Now, we can use the fact that P(B) = 0.70:

0.70 = (0.60 * P(A)) + (0.30 * (1 - P(A)))

Solve for P(A):

P(A|B) = (0.60 * 1) / 0.70 ≈ 0.857

Example 1: Medical Diagnosis

Suppose a rare disease, "Disease X," affects 1% of the population. A

Using Bayes' Theorem: P(A∣B)=P(B)P(B∣A)∗P(A)

Now, calculate P(A | B): P(A∣B)=0.05870.98∗0.01≈0.1668

Example 2: Email Spam Detection

Using Bayes' Theorem: P(A∣B)=P(B)P(B∣A)∗P(A)

Now, calculate P(A | B): P(A∣B)=0.500.90∗0.50=0.90

Example 3: Coin Toss

Solution: Let A be the event of choosing Coin A, and B be the event of

Using Bayes' Theorem: P(B∣H)=P(H)P(H∣B)∗P(B)

P(H | B) = Probability of getting heads with Coin B = 0.80 P(B) = Probability

Now, calculate P(B∣H)=0.650.80∗0.50≈0.6154

1. Medical Diagnosis: Suppose a medical test is used to detect a rare

You might also like

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