💡

Essential Question

How can we discover relationships between variables?

🎯 What You'll Learn

  • ✅ Input experimental data and visualize relationships
  • ✅ Understand different types of mathematical relationships
  • ✅ Calculate correlation metrics (R² values)
  • ✅ Find the best-fit model for your data
  • ✅ Interpret results scientifically

This app guides you through discovering hidden patterns in data. Whether studying physics, biology, or economics, you'll learn how to find mathematical relationships that explain real-world phenomena. Ready to explore? Let's get started! 🚀

📈 What are Variables?

Independent Variable (X): The variable you control or change. For example, temperature, time, or concentration.

Dependent Variable (Y): The variable you measure or observe. It depends on the independent variable. For example, reaction rate or plant height.

🔗 Correlation vs Causation

Correlation: Two variables move together in a predictable pattern.
Causation: One variable directly causes changes in another.

💡 Important: Just because variables correlate doesn't mean one causes the other! Always think critically about the science.

🌊 Types of Relationships

📊 Linear: y = mx + b (straight line)
↘️ Inverse: y = a/x + b (decreasing curve)
🔻 Inverse Square: y = a/x² + b (faster decreasing curve)
🧩 Quadratic: y = ax² + bx + c (parabola)
📈 Exponential: y = a·e^(bx) (rapid growth or decay)
🌲 Logarithmic: y = a·ln(x) + b (quick rise then leveling)
2️⃣ Power (2): y = ax² + b (second-order power relation)
3️⃣ Power (3): y = ax³ + b (third-order power relation)
4️⃣ Power (4): y = ax⁴ + b (fourth-order power relation)

📊 R² (Coefficient of Determination)

tells you how well a model fits your data (0 to 1):
• R² = 1: Perfect fit
• R² = 0.8-0.99: Excellent fit ⭐
• R² = 0.5-0.79: Good fit ✅
• R² < 0.5: Poor fit ⚠️

Formula:
R² = 1 - (SSres / SStot)

📉 Pearson r (Correlation Coefficient)

Pearson r measures the direction and strength of a linear relationship between X and Y.
• r = +1: Perfect positive linear relationship
• r = 0: No linear relationship
• r = -1: Perfect negative linear relationship

Formula:
r = Σ((x - x̄)(y - ȳ)) / √[Σ(x - x̄)² × Σ(y - ȳ)²]

📊 Data Input

📝 Set Up Column Headers

Rename your two variables here, then click Apply Headers to use those titles in the data table and graph.

📦 Demo Data

Use a sample dataset if you want to explore the analyzer first. Demo datasets now include realistic noise so they behave more like measured data.

# X (Independent) Y (Dependent) Action

💡 Tip: Start with sample data to see how the analyzer works, then try your own measurements in the table below.

📈 Visualization

🤖 Analyze

Model comparison and interpretation update automatically once at least 4 valid data points are available.

Switch between the available trendline options to review each equation, fit quality, and model-specific interpretation.

🎓 Reflection Questions

🧐

Think

Which model best represents your data and why? What does the shape tell you about the relationship?

💬

Discuss

How does the R² value help in choosing the best trendline? What would a low R² suggest?

✍️

Answer

Can you predict what would happen if you extended this relationship beyond your data range?