Scatterplots and correlation - Statistics AP Study Notes
Overview
Have you ever wondered if eating more ice cream makes you happier? Or if studying more really gets you better grades? In statistics, we often want to see if two different things are connected, or if they move together. That's where scatterplots and correlation come in! They help us visually explore and measure how two variables (things that can change) relate to each other. Imagine you're trying to figure out if the amount of time you spend practicing a video game affects your high score. You could keep track of both and then use these tools to see if there's a pattern. This isn't just for games or ice cream; businesses use it to see if advertising spending affects sales, doctors use it to see if a certain medicine affects recovery time, and scientists use it to understand how different factors in nature are linked. So, get ready to become a detective of data! We'll learn how to draw pictures that show relationships and how to put a number on how strong those relationships are. It's like finding clues in a mystery, but instead of finding a culprit, you're finding connections between different pieces of information.
What Is This? (The Simple Version)
Think of scatterplots like a secret map that shows you if two things are friends or not. Each point on the map represents one person or one event, and it tells you two pieces of information about them.
Imagine you're tracking how many hours your friends spend playing video games each week and their average test score. For each friend, you'd put a dot on your map:
- One side (the x-axis or horizontal line) shows the hours played.
- The other side (the y-axis or vertical line) shows their test score.
When you look at all the dots together, you can see if there's a pattern. Do the dots tend to go up together? Do they go down? Or are they just all over the place with no clear path?
Correlation is like a special number that tells you how strong and in what direction that friendship (or relationship) is. It's a number between -1 and 1. If it's close to 1, they're best friends and move in the same direction (like more practice = higher score). If it's close to -1, they're like rivals and move in opposite directions (like more practice = lower score, which probably wouldn't happen for video games, but you get the idea!). If it's close to 0, they're basically strangers, and there's no clear connection between them.
Real-World Example
Let's say you're curious about how the temperature outside affects the number of ice cream cones sold at a local shop. You decide to collect data for 10 different days.
Step 1: Collect your data.
- Day 1: 70°F, 100 cones sold
- Day 2: 75°F, 120 cones sold
- Day 3: 60°F, 70 cones sold
- Day 4: 80°F, 150 cones sold
- Day 5: 65°F, 85 cones sold
- Day 6: 72°F, 110 cones sold
- Day 7: 55°F, 50 cones sold
- Day 8: 82°F, 160 cones sold
- Day 9: 68°F, 95 cones sold
- Day 10: 78°F, 135 cones sold
Step 2: Make a scatterplot. You'd draw a graph. The x-axis (horizontal) would be 'Temperature (°F)' and the y-axis (vertical) would be 'Cones Sold'. For each day, you'd put a dot. For example, for Day 1, you'd find 70°F on the bottom and 100 on the side, and put a dot where they meet.
Step 3: Look at the pattern. As you plot all the points, you'd probably notice that as the temperature goes up, the number of cones sold also tends to go up. The dots would generally trend upwards from left to right. This shows a positive association (they move in the same direction).
Step 4: Calculate correlation (or have a computer do it!). If you calculated the correlation for this data, you'd likely get a number close to +1 (maybe around +0.9). This high positive number tells you there's a strong, positive relationship between temperature and ice cream sales. When it's hotter, people buy more ice cream!
How It Works (Step by Step)
Here's how you break down what you see in a scatterplot, like being a detective looking for clues: 1. **Look at the overall direction (Form):** Do the points generally go up from left to right (positive association)? Do they go down (negative association)? Or do they just look like a cloud with no...
Unlock 3 More Sections
Sign up free to access the complete notes, key concepts, and exam tips for this topic.
No credit card required · Free forever
Key Concepts
- Scatterplot: A graph that shows the relationship between two quantitative (number-based) variables by plotting individual data points.
- Association: The general relationship or pattern between two variables, describing how they tend to change together.
- Direction (of association): Describes whether the relationship is positive (both variables increase), negative (one increases as the other decreases), or no association.
- Form (of association): Describes the shape of the relationship, typically linear (straight line) or non-linear (curved).
- +6 more (sign up to view)
Exam Tips
- →Always describe a scatterplot using 'DOFS': Direction, Outliers, Form, and Strength. Don't just say 'it's positive'; explain *what* is positively related to *what*.
- →Remember that correlation (the 'r' value) only measures *linear* relationships. If a scatterplot shows a curve, 'r' might be close to zero even if there's a strong pattern.
- +3 more tips (sign up)
More Statistics Notes