← QuantegyAI

Module 6 — Statistical Investigation Project

MATH 3309 · 150 points 100 pts tasks 20 pts group 20 pts discussion Due Oct 2

A Rigorous Statistical Investigation (RSI) integrating every Module 6 concept: scatterplots, correlation, regression, sets, probability, tree diagrams, sample spaces, data classification, pictographs, and two-way frequency tables — with a group collaboration component and discussion forum.

RSI Framework. This project follows the Rigorous Statistical Investigation cycle: (R) Research question → (S) Statistical analysis → (I) Interpretation & defense. Every claim must be backed by evidence, and every model must be checked — not assumed.

Student Learning Outcomes

The Dataset: Study Habits & Exam Performance

A dataset from 12 students in an introductory statistics course. Each recorded weekly study hours, practice problems completed, whether they attended a review session, and their final exam score (out of 100).

Student Dataset
StudentStudy Hours/WkPractice ProblemsAttended ReviewExam Score
1315No58
2522No64
3418Yes67
4730No72
5625Yes75
6835Yes81
71040No85
8938Yes88
91250Yes94
10210No52
111145Yes91
12628No70
Why this dataset? Every variable is neutral and observable. No demographic data is collected or implied. Small enough for hand calculation, large enough for meaningful patterns.

Interactive Scatterplot Explorer

Select variables to plot. The scatterplot updates live. Use this to explore relationships before completing Task 2.

Scatterplot Builder
Select variables to see statistics.

Interactive Correlation Calculator

See the step-by-step correlation calculation. Select two variables.

Correlation Coefficient Calculator
Select variables and the calculation will appear here.

Interactive Regression Line

Adjust the sliders to fit a line, then compare with the actual best-fit line.

Regression Line Fitter

Adjust the sliders to fit a line, then click "Show Best-Fit Line" to compare.

Interactive Probability Tree

Build a probability tree for a randomly selected student, branching on review attendance and scoring 75+.

Probability Tree Diagram
Click the steps below to build the probability tree.

Interactive Two-Way Frequency Table

Fill in the frequency table from the dataset. The calculator checks your work and computes probabilities.

Two-Way Frequency Table Builder
Scored 75+Scored <75Total
Attended Review
Did Not Attend
Total12
Fill in the four cells from the dataset above. The table will check your work automatically.

Interactive Self-Checks

Scatterplots

A scatterplot shows points rising from lower-left to upper-right with minor scatter. What direction, form, and strength?

Direction: positive. Form: roughly linear. Strength: strong (points tightly clustered with little vertical spread).
Correlation

If r = 0.98 between study hours and exam scores, does this prove that increasing study hours causes exam scores to rise?

No. Correlation measures strength and direction of a linear association, not causation. Confounding variables (motivation, prior knowledge, sleep, course difficulty) may explain the relationship. A causal claim requires an experimental design with random assignment.
Regression

You compute a regression line \(\hat{y} = 46.4 + 4.1x\). What does the slope of 4.1 mean in context?

For each additional hour of study per week, the model predicts an increase of approximately 4.1 points on the exam, on average. This is a prediction from the fitted line, not a guarantee for any individual student.
Sets

In a sample of 12, 6 scored 75+ (set A) and 6 attended review (set B). If 5 students are in both, what is P(A ∪ B)?

P(A ∪ B) = P(A) + P(B) - P(A ∩ B) = 6/12 + 6/12 - 5/12 = 7/12 ≈ 0.583. About 58.3% scored 75+ or attended review (or both).
Tree diagrams

A tree shows P(Review) = 0.5 and P(75+ | Review) = 0.83. What is P(Review ∩ 75+)?

P(Review ∩ 75+) = P(Review) × P(75+ | Review) = 0.5 × 0.83 = 0.417. About 41.7% (5 out of 12) both attended review and scored 75+.
Two-way tables

P(75+ | Attended) = 0.83 and P(75+ | Did Not Attend) = 0.17. Are "Attended" and "Scored 75+" independent?

No. If independent, the conditional probability would equal the marginal regardless of attendance. Since 0.83 ≠ 0.17, the events are dependent. This association does not prove attendance causes higher scores.

Project Tasks

TASK 1

Variable Classification & Individuals 9 pts

RSI phase: Research question setup.

  1. Identify the individuals (observational units) in this dataset.
  2. For each variable (Study Hours, Practice Problems, Attended Review, Exam Score), classify it as categorical or quantitative and explain why.
  3. For quantitative variables, identify the units of measurement.
  4. State whether this is an observational study or an experiment. Justify and explain what this means for causal claims.
TASK 2

Scatterplot & Description 12 pts

RSI phase: Exploratory analysis. Use the interactive scatterplot explorer above to explore, then create your own by hand or with software.

  1. Create a scatterplot of Study Hours (x) vs Exam Score (y). Label both axes with units.
  2. Describe using direction, form, and strength.
  3. Identify any outliers. If none, state so.
  4. Create a second scatterplot of Practice Problems vs Exam Score. Compare the two — which is stronger, and why?
TASK 3

Correlation Coefficient 12 pts

RSI phase: Statistical measurement. Use the correlation calculator above to check your work.

  1. Calculate the correlation coefficient \(r\) between Study Hours and Exam Score. Show your work.
  2. Interpret \(r\) in context: direction and strength.
  3. Calculate \(r\) between Practice Problems and Exam Score. Compare.
  4. A classmate claims: "Since r is high, studying more causes higher exam scores." Explain why this is not justified. Name at least two confounding variables.
TASK 4

Simple Linear Regression 15 pts

RSI phase: Model building. Use the regression fitter above to explore.

  1. Fit a regression line for predicting Exam Score from Study Hours. Calculate slope and intercept.
  2. Write the equation: \(\hat{y} = b_0 + b_1 x\).
  3. Interpret the slope in context.
  4. Interpret the intercept. Is it meaningful? Why or why not?
  5. Predict the exam score for 9 hours/week. Is this extrapolation?
  6. Compute residuals for all 12 students. Create a residual plot. Does the linear model appear appropriate?
TASK 5

Sets, Sample Spaces & Probability 12 pts

RSI phase: Probabilistic reasoning.

Define: A = {scored 75+}, B = {attended review}, C = {fewer than 25 practice problems}.

  1. List the elements of: A, B, C, A ∪ B, A ∩ B, Ac, and B ∩ Cc.
  2. Compute: P(A), P(B), P(C), P(A ∩ B), P(A ∪ B), and P(A | B).
  3. Verify the addition rule. Show the numbers.
  4. Are A and B independent? Check whether P(A | B) = P(A).
TASK 6

Tree Diagram & Conditional Probability 9 pts

RSI phase: Probabilistic reasoning. Use the interactive tree above.

  1. Construct a tree diagram: first branch "Attended Review" (Yes/No), second branch "Scored 75+" (Yes/No). Label each branch with its probability.
  2. Compute: P(75+ | Attended), P(75+ | Did Not Attend), P(75+) using law of total probability.
  3. Write a one-paragraph interpretation. What caveats apply?
TASK 7

Two-Way Frequency Table 12 pts

RSI phase: Statistical communication. Use the interactive table above to check your work.

  1. Construct a two-way frequency table with "Attended Review" as rows and "Scored 75+" as columns. Include all marginal totals.
  2. Compute marginal, joint, and conditional probabilities.
  3. Convert to a relative frequency table.
  4. Explain what the conditional probabilities tell you. Compare to your tree diagram results.
TASK 8

Pictograph Design & Critique 9 pts

RSI phase: Communication & visualization ethics.

  1. Create a pictograph showing average exam score for review attendees vs non-attendees. Use icons where each represents 10 points.
  2. Critique your pictograph: does the visual area accurately represent proportions? Could differently-sized icons mislead?
  3. Find one example of a misleading pictograph or bar chart. Describe what makes it misleading and how you would fix it.
TASK 9

Screen Recording: Walkthrough of a Key Finding 10 pts

RSI phase: Statistical communication. Assesses SLO 9.

  1. As a group, choose one finding from your project that you find most interesting or surprising. This could be the correlation strength, the regression prediction, the conditional probability from the tree diagram, or the independence check.
  2. Record a 3–5 minute screen recording where one or more group members explain the finding. Share your screen showing the interactive QuantegyAI page, your scatterplot, regression output, tree diagram, or two-way table while you talk through:
    • What the data shows
    • What the statistic means in context
    • One caveat or limitation of the analysis
  3. Upload the recording to YouTube (unlisted), Google Drive, or Canvas Studio and paste the link in your submission.

Tip: You can use free tools like Loom, OBS Studio, or your computer's built-in screen recorder (QuickTime on Mac, Snipping Tool / Xbox Game Bar on Windows). Speak naturally — this is about explaining statistics in your own words, not a polished production.

Group Project Component 30 pts

Collaborative Investigation. Form groups of 3–4 students. Each member takes a specialized role, contributes their part, and the group submits a unified report. All members receive the same group grade, but individual contributions should be clearly labeled.

Group Roles

Assign one role per member. If 4 members, split Data Analyst into two (one for regression, one for probability).

DR
Data Researcher

Completes Tasks 1 & 2: Variable classification, study type, scatterplot creation and description. Identifies individuals, classifies variables, produces both labeled scatterplots with written descriptions of direction, form, and strength.

DA
Data Analyst

Completes Tasks 3 & 4: Correlation calculation and regression modeling. Computes both correlations, fits the regression line, interprets slope/intercept, makes predictions, performs residual analysis. Responsible for the causal-boundary discussion.

PB
Probability Builder

Completes Tasks 5 & 6: Set operations, probability calculations, tree diagram. Lists all set elements, computes all probabilities, verifies the addition rule, checks independence, builds the tree diagram.

CR
Communication Reporter

Completes Tasks 7 & 8: Two-way frequency table, pictograph, and final report assembly. Constructs the frequency table, creates the pictograph, finds a misleading graph example, and compiles all members' work into a unified report.

Group Submission Form

Group Information

Fill in your group details. Each member listed with their assigned role.

Group Collaboration Guidelines

Interactive Group Activities

Work through these collaborative challenges together. Each activity saves your group's progress in your browser.

Challenge 1: Group Prediction Game

Before computing anything, each member guesses the correlation between Study Hours and Exam Scores. Closest guess wins! Then reveal the actual value and discuss.

Challenge 2: Group Discussion Board

Post questions, observations, and replies. Your group's discussion is saved in this browser so you can come back to it.

Challenge 3: Group Consensus — Are These Events Independent?

Each member votes: Do you think "Attended Review" and "Scored 75+" are independent events? Vote before checking the answer, then discuss as a group.

Discussion Component 20 pts · Required

Discussion: "Correlation Does Not Imply Causation — But What Does It Imply?"

You found a strong positive correlation between study hours and exam scores. Attending a review session is associated with higher scores. Your regression model can predict exam scores from study hours.

But can you conclude that studying more causes higher scores?

In a 200–300 word discussion post, address all three prompts:

  1. The causal boundary: What is the difference between "studying more is associated with higher scores" and "studying more causes higher scores"? Use at least two confounding variables to explain the distinction.
  2. The design question: What study design would you need to make a causal claim? Describe what such a study would look like. What ethical or practical concerns might arise?
  3. The communication question: If advising a student who wants to improve their exam score, how would you communicate findings honestly using correlation and prediction language without overstating causation? Write one sentence you would say to the student.

Requirements: 200–300 words · proper statistical terminology · reference at least one specific number from your analysis · post by due date · respond to at least one classmate (50+ words).

Write Your Discussion Post

Type your 200–300 word response below. When done, click Download to save your work as a text file for submission.

0 words

Your Tree Diagram Interpretation

After exploring the interactive tree above, write your one-paragraph interpretation of the conditional probabilities and what they mean.

0 words

Your Reflection (Task 8 Self-Critique)

Write your pictograph self-critique and misleading-graph analysis here.

0 words

Discussion Response Prompts

When responding to a classmate's post, consider:

Submission Checklist

Grading Rubric (100 points total)

CriterionExcellentProficientDevelopingBeginning
Variable Classification (9)All correctly classified with units; study type identified with justificationMost correct, minor errorsClassification errors but some understandingMissing or incorrect
Scatterplots (12)Both drawn with labels; direction/form/strength accurate; outliers notedDrawn, descriptions mostly accurateOne scatterplot or vague descriptionsMissing or unreadable
Correlation (12)Both r values correct; interpretation precise; 2+ confounders namedCalculations correct, interpretation vagueCalculation errors but method shownMissing or no causal discussion
Regression (15)Correct slope/intercept, interpretations, prediction, residual plotCorrect equation, partial interpretationsEquation errors, minimal residualsMissing or no residual analysis
Sets & Probability (12)All sets listed, all probabilities correct, addition rule verified, independence checkedMost correct, minor set errorsSeveral errors but approach shownMissing or incorrect
Tree Diagram (9)Correctly constructed, all probabilities computed, thoughtful interpretationTree correct, minor errorsTree incomplete or errors throughoutMissing
Two-Way Table (12)Complete table with marginals, all probabilities correct, relative frequency, comparison to treeTable complete, most probabilities correctTable incomplete, several errorsMissing
Pictograph (9)Accurate pictograph, thoughtful self-critique, valid misleading examplePictograph correct, critique superficialPictograph errors, minimal critiqueMissing
Group Collaboration (30)All roles filled, work clearly labeled, cross-checking evident, cohesive reportRoles filled, some labeling, minor gapsUneven contribution, incomplete labelingMissing or non-functional group
Discussion200-300 words, references data, correct terminology, causal distinction, classmate responseMostly correct, minor issuesShort, vague, missing causal discussionMissing or no response to classmate
Screen Recording (10)3-5 min, clear explanation of one finding, uses visuals, states a limitation, natural deliveryExplains finding with minor gaps, uses some visualsBrief or unclear, minimal use of visualsMissing or no statistical content

How to Submit

Statistical Tasks 1–8 (90 pts): Submit a single PDF with all 8 tasks. Include the group information form on page 1. Label each task with the responsible member's name and role. One submission per group.

Group Collaboration (30 pts): Assessed based on role completion, labeling, cross-checking, and peer evaluations.

Screen Recording (10 pts): Upload your 3–5 minute screen recording to YouTube (unlisted), Google Drive, or Canvas Studio. Paste the link in your group submission.

Discussion (20 pts): Post your 200–300 word response in the Canvas discussion forum. Respond to at least one classmate (50+ words).

Due: October 2 · Total: 150 points

Academic honesty. You may use calculators, spreadsheets, and AI tools to check calculations. All written interpretations and discussion responses must be in your own words. If you use AI to check work, include a brief note describing how.