Module 2: Visual Detection of Normality

Pattern Recognition Challenge

☁️ Working Guidelines

0% Complete

🎯 Learning Objectives

By the end of this module, you will:

  1. Recognize patterns in histograms, boxplots, and Q-Q plots that indicate normality
  2. Identify different types of non-normality (skewness, outliers, bimodal)
  3. Develop a systematic approach to visual diagnosis
  4. Create your own field guide for spotting non-normal distributions

🕵️ The Challenge

You're a data detective!

Six mystery datasets have arrived on your desk. Some are normal, some aren't.

Your mission: Examine each dataset carefully and identify which distributions are normal and which are not. Build your skills by discovering the patterns yourself!

Step 1: Generate the Mystery Datasets

Click the button below to create six mystery datasets. Don't worry about how they're generated—just focus on what you observe!

Step 2: Examine Each Dataset

Click on each dataset below to see its diagnostic plots. Study them carefully!

Step 3: Record Your Detective Work

For EACH dataset, fill in your observations:

Use the table below to organize your findings. Be specific about what you see!

Dataset Histogram Shape Q-Q Plot Pattern Mean vs Median Verdict
Dataset 1

Dataset 2

Dataset 3

Dataset 4

Dataset 5

Dataset 6

Step 4: Pattern Discovery

Look across all 6 datasets. What PATTERNS do you notice?

Question 1: When data ARE normal, the histogram looks:

Question 2: When data ARE normal, the Q-Q plot shows points that:

Question 3: When data are NOT normal, I notice these warning signs:

Histogram warning signs:

Q-Q plot warning signs:

Mean vs Median warning signs:

Step 5: Create Your Field Guide

Based on your discoveries, create a "field guide" for spotting non-normal data:

📊 HISTOGRAM RED FLAGS

List at least 3 things that indicate non-normality in a histogram:

📈 Q-Q PLOT RED FLAGS

List at least 3 patterns in Q-Q plots that suggest problems:

🔢 DESCRIPTIVE STATISTICS RED FLAGS

List at least 2 statistical indicators of non-normality:

Step 6: Check Your Answers

Ready to see how the datasets were actually generated?

Step 7: Reflection

Question 4: Were you correct? Which datasets surprised you and why?

Question 5: What patterns did you miss initially that you now understand?

Question 6: Which type of non-normality was easiest to spot? Which was hardest?

🎯 Key Discoveries

What You Should Have Discovered:

✓ Normal Data Characteristics:

✓ Types of Non-Normality:

✓ Most Reliable Indicators:

  1. Q-Q Plot is the most sensitive diagnostic tool
  2. Histogram gives quick overview but can be misleading with small samples
  3. Boxplot is best for spotting outliers
  4. Mean vs Median gives numerical confirmation of skewness

📚 Looking Ahead

In Module 3, you'll learn:

📋 Before You Submit

✅ Submission Checklist

📤 How to Submit

  1. Click "Save Progress" to ensure everything is stored
  2. Use Print: Ctrl+P (Windows) or Cmd+P (Mac)
  3. Choose "Save as PDF"
  4. Save as: module2_lastname1_lastname2.pdf
  5. Upload to your course management system

🎉 Great detective work! 🎉

You've learned to visually diagnose normality. In Module 3, you'll add statistical tests to your toolkit!