Mathematics · Class 12 · Probability and Linear Programming · Term 2

Total Probability and Bayes' Theorem

Students will understand and apply the theorem of total probability and Bayes' Theorem to solve inverse probability problems.

• CBSE Learning Outcomes
• NCERT: Probability - Class 12

About This Topic

The theorem of total probability helps students compute the probability of an event by summing over mutually exclusive and exhaustive partitions of the sample space. They practise writing P(B) = Σ P(B|A_i) P(A_i), where A_i are the partitions. Bayes' Theorem builds on this by reversing conditional probabilities: P(A_i|B) = [P(B|A_i) P(A_i)] / P(B). Students apply these to inverse problems, such as finding the probability of having a disease given a positive test result.

In the CBSE Class 12 Probability unit from Term 2, these concepts extend conditional probability and prepare students for real-world decision-making under uncertainty. Key skills include distinguishing prior probabilities (initial beliefs) from posterior probabilities (updated beliefs) and constructing problems like medical diagnostics. This fosters logical reasoning and data interpretation, aligning with NCERT standards.

Active learning suits this topic well. Simulations with coins or cards representing tests make abstract calculations concrete. Group discussions on scenarios reveal how new evidence shifts probabilities, helping students internalise the theorems through repeated application and peer explanation.

Key Questions

1. Explain how Bayes' Theorem allows us to update probabilities based on new evidence.
2. Differentiate between prior and posterior probabilities in the context of Bayes' Theorem.
3. Construct a medical diagnosis problem that can be solved using Bayes' Theorem.

Learning Objectives

• Calculate the probability of an event using the theorem of total probability, P(B) = Σ P(B|A_i) P(A_i).
• Apply Bayes' Theorem, P(A_i|B) = [P(B|A_i) P(A_i)] / P(B), to solve inverse probability problems.
• Differentiate between prior and posterior probabilities in given scenarios.
• Construct a real-world problem, such as a medical diagnosis, that can be solved using Bayes' Theorem.
• Analyze how new evidence updates initial probability estimates in conditional probability problems.

Before You Start

Conditional Probability

Why: Students must understand the concept of P(A|B) and how to calculate it before applying the theorems of total probability and Bayes'.

Sample Space and Events

Why: A firm grasp of sample spaces, events, and their relationships is fundamental to defining partitions and calculating probabilities.

Basic Probability Calculations

Why: Students need to be comfortable calculating simple probabilities, including those involving 'and' and 'or' conditions, to build upon.

Key Vocabulary

Total Probability Theorem	A theorem stating that if {A_i} is a partition of the sample space, then the probability of an event B can be found by summing the probabilities of B occurring with each event in the partition: P(B) = Σ P(B|A_i) P(A_i).
Bayes' Theorem	A theorem that describes the probability of an event based on prior knowledge of conditions that might be related to the event. It is used to update probabilities when new evidence is available.
Prior Probability	The initial probability of an event before any new evidence is considered. It represents our belief or knowledge before an experiment or observation.
Posterior Probability	The updated probability of an event after new evidence has been taken into account. It is calculated using Bayes' Theorem.
Inverse Probability	Problems where we are asked to find the probability of a cause given an observed effect, often solved using Bayes' Theorem.

Watch Out for These Misconceptions

Common Misconception

Bayes' Theorem only applies to medical tests.

What to Teach Instead

Bayes' works for any inverse probability, like spam detection or weather forecasting. Role-playing diverse scenarios in groups broadens understanding and shows the formula's versatility.

Common Misconception

Prior and posterior probabilities are the same.

What to Teach Instead

Priors are initial beliefs; posteriors incorporate evidence. Simulations where students update beliefs step-by-step clarify this shift, as they see numbers change with new data.

Common Misconception

Total probability ignores conditional aspects.

What to Teach Instead

It sums weighted conditionals explicitly. Building tree diagrams collaboratively ensures students account for each partition correctly.

Active Learning Ideas

Pairs: Medical Test Simulation

Pairs use coins to simulate disease presence (heads) and tests (second coin for accuracy). Tally 50 trials to compute actual P(disease|positive). Discuss how priors affect posteriors and verify with Bayes' formula.

30 min·Pairs

Small Groups: Partition Puzzle

Groups draw tree diagrams for total probability scenarios like faulty machine parts. Assign priors, conditionals, and compute P(defective item). Rotate roles to explain steps aloud.

40 min·Small Groups

Whole Class: Evidence Update Chain

Class starts with a prior on a class event (e.g., rain tomorrow). Teacher reveals evidence sequentially; students update posteriors on board using Bayes'. Vote on beliefs before/after.

35 min·Whole Class

Individual: Diagnosis Worksheet

Students create their own Bayes' problem on spam emails with given rates. Solve using total probability, then swap and check peers' work.

25 min·Individual

Real-World Connections

• Medical diagnostics: Doctors use Bayes' Theorem to estimate the probability of a patient having a specific disease given the results of diagnostic tests, considering the prevalence of the disease (prior) and the test's accuracy.
• Spam filtering: Email services use Bayes' Theorem to classify emails as spam or not spam. The prior probability is the general likelihood of an email being spam, updated by the presence of specific keywords in the email.
• Quality control in manufacturing: Engineers apply Bayes' Theorem to assess the probability that a manufactured item is defective, given results from quality checks. This helps in deciding whether to accept or reject a batch of products.

Assessment Ideas

Quick Check

Present students with a scenario involving two biased coins. Ask them to first calculate the probability of getting heads using the theorem of total probability. Then, pose a question like, 'Given that a head was obtained, what is the probability it came from the first coin?' to assess their application of Bayes' Theorem.

Discussion Prompt

Pose the question: 'Imagine you are a detective investigating a crime. You have an initial suspect based on circumstantial evidence (prior probability). A new witness provides a crucial piece of information (new evidence). How would you use Bayes' Theorem to update your belief about the suspect's guilt?' Facilitate a class discussion on how prior and posterior probabilities change.

Exit Ticket

Provide students with a simple medical test scenario (e.g., a test for a rare disease). Ask them to identify the prior probability, the likelihood of a positive test given the disease, and the likelihood of a positive test given no disease. Then, ask them to calculate the posterior probability of having the disease given a positive test result.

Frequently Asked Questions

How does Bayes' Theorem update probabilities with evidence?

Bayes' Theorem calculates posterior probability P(A|B) using prior P(A), likelihood P(B|A), and total P(B). For a disease test, if prior disease rate is 1% and test accuracy 99%, a positive result yields low posterior due to false positives. Students compute this to see evidence tempers strong tests.

What is the difference between prior and posterior probabilities?

Prior probability reflects belief before evidence, like base disease rate. Posterior incorporates new data via Bayes', often shifting dramatically. Examples in quality control show priors from history updated by inspections, building intuitive grasp through repeated calculations.

How can active learning help teach Total Probability and Bayes' Theorem?

Active methods like coin-flip simulations or group tree-building make formulas tangible. Students experience probability updates firsthand, discuss misconceptions in pairs, and apply to custom problems. This boosts retention over rote practice, as peer teaching reinforces steps and realises theorem power.

Construct a Bayes' Theorem problem for medical diagnosis.

Suppose 2% population has disease; test is 95% accurate for positives/negatives. For positive test, compute disease probability. Use total P(positive) = P(positive|disease)P(disease) + P(positive|no disease)P(no disease), then Bayes' gives about 28%. Students vary rates to explore sensitivity.