Week 3 tutorial- with Tutor led questions (1)

Lesson Overview


Recap of Lecture 2: ProbabilitiesThe lecture provided an in-depth exploration of probabilities, giving students a foundation for understanding complex statistical concepts.


Part 1: Contingency tables, Marginal and joint probabilities (Tutor led)The tutor introduced contingency tables as a fundamental tool for visualizing the relationship between two categorical variables. Key concepts included marginal probability (the probability of one variable irrespective of the other) and joint probability (the probability of both variables happening simultaneously).


Quiz Part A: Students to completeFollowing the tutor-led session, students will engage in a quiz designed to reinforce their understanding of these initial concepts.


Part 2: Questions & Discussion (Tutor led)This section allowed students to clarify doubts and discuss applications of probability theory, facilitating a more interactive learning experience.


Quiz Part B: Students to completeA second quiz will assess students' comprehension and application of the material discussed.

Summary

Understanding Probability


  • Definition of Probability:Probability quantifies the chance or likelihood of an occurrence occurring, providing a numerical representation of uncertainty.

  • Notation:

    • P(A) = 0 → Indicates that event A will not occur (impossible event).

    • P(B) = 1 → Indicates that event B occurs with 100% certainty (certain event).

  • Additivity:

    • The sum of probabilities for all possible events must equal 1:

    • Example: P(Head) + P(Tail) = 1.

Types of Probabilities

  • Union of Events

    • Union: P(A or B) or P(A ∪ B) represents the occurrence of either event A or event B.


    • Formula: P(A or B) = P(A) + P(B) - P(A and B)This formula ensures that in cases where A and B can occur simultaneously, the overlap probability is not counted twice.

  • Intersection of Events

    • Joint Probability: P(A and B) or P(A ∩ B) denotes the occurrence of both events at the same time.

Practical Application - Marketing Dataset


Task OverviewThe objective of this practical session was to analyze how the "Have Tried" product variable correlates with demographic variables in a marketing dataset to identify potential trends and buyer behaviors.

  • Demographic Variables:

    • Income: Respondent's income range.

    • Gender: Male or Female.

    • Living Alone: Yes or No.

  • Datafile Information:

    • Unique Identifier: Person ID for tracking responses.

    • Categories: Each variable has specified categories for analysis.


Pivot Table ConstructionStudents are required to construct three pivot tables detailing:

  • Row Variable: "Have Tried"

  • Column Variables: Income, Gender, Living Alone

  • Display Settings: Counts should represent the percentage of the grand total for clear insights.

Quiz Part A: Questions

  1. What is the probability that a randomly selected participant has tried the product?

  2. What is the probability that a randomly selected participant lives alone and has tried the product?

  3. What is the probability that a randomly selected participant earns $50,000 or more?

  4. What is the probability that a randomly selected participant earns $50,000 or more and has tried the product?

Conditional Probability


  • Definition:Probability of event A, given that event B has already occurred.


  • Formula:P(A | B) = P(A ∩ B) / P(B) This formula is essential in scenarios where prior knowledge of event B alters the probability assessment of event A.


  • Revisit Contingency Tables:Students should analyze contingency tables for "Marketing," setting displays to show percentages of column totals for deeper insights into relationships and dependencies.

Independent and Mutually Exclusive Events

  • Mutually Exclusive Events

    • Definition: Events that cannot occur simultaneously.

    • Formula: P(A or B) = P(A) + P(B) - P(A and B)

    • For mutually exclusive events: P(A and B) = 0.

  • Independent Events

    • Definition: The occurrence of one event does not influence the occurrence of another event.

    • For events A and B to be independent:

    • P(A|B) = P(A)


    • P(A ∩ B) = P(A) × P(B)This criterion assists in defining the relationship between events and ensuring accurate probability calculations.

Part 2: Conditional Probability and Independence Questions

  • What is the probability a person living alone has tried the product?

  • What is the probability a female has tried the product?

  • What is the probability a person earning $50,000 or more has tried the product?

  • Are the tendencies to try the new frozen food product and income independent? Interpret the result.

Summary and Checklist

Checklist:

  • Construction of contingency table

  • Read marginal probabilities from table margins

  • Read joint probabilities from the table body

  • Calculate conditional probability via pivot tables

  • Compare marginal vs conditionals to assess independence

  • Determine potential directional relationships (e.g., income vs. "Have Tried" in the marketing case).