Probability

Bayes' Theorem

Probability

Bayes' Theorem: 동영상 및 연습문제

주제 요약

Bayes' Theorem is used to find a conditional probability when the usual conditional probability rule is harder to apply directly. It helps reverse a condition, such as finding the probability of event $B$ given event $A$ from information about $A$ given $B$. A key idea is to identify the given event as $A$, the event of interest as $B$, and often the complement event $B'$ as well.

The central formula is $P(B\mid A)=\frac{P(A\mid B)P(B)}{P(A\mid B)P(B)+P(A\mid B')P(B')}$ . This combines the prior probability $P(B)$, the likelihood $P(A\mid B)$, and the competing case involving $B'$. In practice, success depends on correctly interpreting phrases like “given,” finding $P(B')=1-P(B)$, and distinguishing true positive or false positive style probabilities from the probability ultimately being asked for.

개념

Bayes' Theorem

영상 길이:

Bayes' Theorem Video Summary

Conditional probability is a crucial concept in probability theory that allows us to determine the likelihood of an event occurring given that another event has already taken place. Specifically, when we want to find the probability of event B occurring given that event A has occurred, we denote this as P(B|A). However, calculating this directly can sometimes be challenging, especially if we lack the necessary probabilities for events A and B. In such cases, Bayes' theorem provides a powerful alternative.

Bayes' theorem can be expressed as:

\[ P(B|A) = \frac{P(A|B) \cdot P(B)}{P(A)} \]

In this formula, P(A|B) represents the probability of event A occurring given that event B has occurred, P(B) is the probability of event B, and P(A) is the total probability of event A. By breaking down the components of this theorem, we can simplify our calculations and find the desired conditional probabilities more easily.

To illustrate this, consider a scenario involving two bags of marbles. The left bag contains 2 red marbles and 4 blue marbles, while the right bag has 1 red marble and 5 blue marbles. If we observe that 3 out of every 4 marbles drawn come from the left bag, we can denote the events as follows: let event A be drawing a red marble, and event B be drawing from the left bag. Our goal is to find P(B|A), the probability that the marble came from the left bag given that it is red.

First, we identify the probabilities needed for Bayes' theorem:

P(B) = Probability of drawing from the left bag = $ \frac{3}{4} $
P(B complement) = Probability of drawing from the right bag = $ \frac{1}{4} $
P(A|B) = Probability of drawing a red marble from the left bag = $ \frac{2}{6} $
P(A|B complement) = Probability of drawing a red marble from the right bag = $ \frac{1}{6} $

Now, we can apply Bayes' theorem:

\[ P(B|A) = \frac{P(A|B) \cdot P(B)}{P(A|B) \cdot P(B) + P(A|B \text{ complement}) \cdot P(B \text{ complement})} \]

Substituting the values we calculated:

\[ P(B|A) = \frac{\left(\frac{2}{6}\right) \cdot \left(\frac{3}{4}\right)}{\left(\frac{2}{6} \cdot \frac{3}{4}\right) + \left(1 \cdot \frac{1}{4}\right)} \]

Calculating the numerator gives us $ \frac{6}{24} $, and the denominator simplifies to $ \frac{6}{24} + \frac{6}{24} = \frac{12}{24} $. Thus, we find:

\[ P(B|A) = \frac{6/24}{12/24} = \frac{6}{12} = \frac{6}{7} \]

Therefore, the probability that the marble came from the left bag given that it is red is $ \frac{6}{7} $. This example demonstrates how Bayes' theorem can simplify the process of finding conditional probabilities, especially when direct calculations are not straightforward. Practicing with various examples will further enhance your understanding and application of these concepts.

워크시트로 더 똑똑하게 공부하세요.

각 영상을 인쇄 가능한 워크시트로 따라 하세요

문제

A rare condition affects 1 out of every 100 people. The test for this condition has the following probabilities: If a person has the condition, the test is correct 95% of the time. If a person does not have the condition, the test gives a wrong result 10% of the time. If A is the event 'tested positive' and B is the event 'has condition,' find P(B'), P(AIB), and P(A|B').

P(B') = 0.99; P(A|B) = 0.95; P(A|B') = 0.10

P(B') = 0.99; P(A|B) = 0.95; P(A|B') = 0.01

P(B') = 0.95; P(A|B) = 0.99; P(A|B') = 0.01

P(B') = 0.95; P(A|B) = 0.99; P(A|B') = 0.10

예시

Bayes' Theorem Example 1

영상 길이:

Bayes' Theorem Example 1 Video Summary

Bayes' Theorem is a powerful tool for calculating conditional probabilities, particularly in medical testing scenarios. In this example, we explore how to determine the probability of having the flu given a positive test result.

At the peak of flu season, it is known that 10% of the population in a town contracts the flu. This probability can be expressed as:

$ P(B) = 0.1 $

where $ B $ represents the event of being sick with the flu. Consequently, the probability of not being sick, denoted as $ B' $, is:

$ P(B') = 1 - P(B) = 0.9 $

Next, we consider the accuracy of the flu test. The test correctly identifies a sick person 95% of the time, which gives us:

$ P(A|B) = 0.95 $

where $ A $ is the event of testing positive. Conversely, the test incorrectly identifies a healthy person as sick 1% of the time, leading to:

$ P(A|B') = 0.01 $

To find the probability of actually having the flu given a positive test result, we apply Bayes' Theorem, which is formulated as:

$ P(B|A) = \frac{P(A|B) \cdot P(B)}{P(A)} $

To compute $ P(A) $, the total probability of testing positive, we use the law of total probability:

$ P(A) = P(A|B) \cdot P(B) + P(A|B') \cdot P(B') $

Substituting the known values, we have:

$ P(A) = (0.95 \cdot 0.1) + (0.01 \cdot 0.9) $

Calculating this gives:

$ P(A) = 0.095 + 0.009 = 0.104 $

Now, we can substitute back into Bayes' Theorem:

$ P(B|A) = \frac{0.95 \cdot 0.1}{0.104} \approx 0.9135 $

This result indicates that the probability of being sick with the flu given a positive test result is approximately 91.35%. Thus, if someone tests positive, there is a high likelihood that they actually have the flu, reinforcing the importance of understanding conditional probabilities in medical testing.

문제

According to data from a metro station, 28% of trains are delayed. When compared to weather data, it was found that 73% of train delays and 35% of on-time rides were on days with precipitation. Given there is precipitation, what is the probability the train will be delayed?

0.45

0.56

0.20

0.80

더 연습하고 싶어?

학생들이 이 주제에 대해 묻는 질문은 다음과 같습니다:

Bayes' Theorem is a formula used to find the probability of an event $B$ given that another event $A$ has occurred, especially when directly finding $P(B|A)$ is difficult. It reverses the condition by using known probabilities like $P(A|B)$ , the likelihood of $A$ given $B$ , and the prior probability $P(B)$ . The theorem is expressed as $P (B | A) = \frac{P (A | B) P (B)}{P (A | B) P (B) + P (A | B') P (B')}$ . This helps calculate the probability of $B$ when $A$ is known, by considering both $B$ and its complement $B′$ . It is especially useful in cases like medical testing or decision-making where direct probabilities are hard to find.

When using Bayes' Theorem, it is crucial to correctly identify the events $A$ and $B$ . Event $A$ is the given or known event, the condition that has already occurred. Event $B$ is the event of interest, the one whose probability we want to find given $A$ . For example, if you know a marble drawn is red ( $A$ ), and you want to find the probability it came from the left bag ( $B$ ), then $A$ is 'red marble drawn' and $B$ is 'marble from left bag'. The complement $B′$ is the event that $B$ did not happen (e.g., marble from the right bag). Correctly identifying these events ensures the correct application of the formula and accurate results.

The complement event, denoted as $B′$ , represents the scenario where event $B$ does not occur. In Bayes' Theorem, the complement is important because the total probability of event $A$ happening can come from either $B$ or $B′$ . The denominator of Bayes' formula sums the probabilities of $A$ occurring with $B$ and with $B′$ , ensuring all possibilities are considered. This is expressed as $P (A | B) P (B) + P (A | B′) P (B′)$ . Including the complement ensures the total probability accounts for all ways $A$ can happen, which is essential for accurate conditional probability calculation.

Consider a game with two bags of marbles. The left bag has 2 red and 4 blue marbles; the right bag has 1 red and 5 blue marbles. Three out of every four marbles drawn come from the left bag. If a red marble is drawn, we want to find the probability it came from the left bag. Here, event $A$ is 'red marble drawn', and event $B$ is 'marble from left bag'. Using Bayes' Theorem: $P (B | A) = \frac{P (A | B) P (B)}{P (A | B) P (B) + P (A | B′) P (B′)}$ . Plugging in values: $P(A|B) = 2/6$ , $P(B) = 3/4$ , $P(A|B′) = 1/6$ , and $P(B′) = 1/4$ . Calculating gives $P(B|A) = 6/7$ , meaning there's a high chance the red marble came from the left bag.

Bayes' Theorem can be easier to use than the standard conditional probability rule when direct probabilities like $P(A \, $\text{and}$ \, B)$ or $P(A)$ are hard to find. Instead, Bayes' Theorem uses known probabilities such as $P(A|B)$ and prior probabilities $P(B)$ , which are often more accessible. It also accounts for the complement event $B′$ , allowing us to consider all possible ways event $A$ can occur. This makes it especially useful in real-world problems like medical testing or decision-making, where we know the likelihood of symptoms given a disease but want to find the probability of the disease given symptoms. Thus, Bayes' Theorem simplifies calculations by reversing the conditioning and using available data effectively.