Introduction to Linear Regression

Active learning works for linear regression because students need to see the line shift in real time as data changes, not just memorize formulas. Moving points and watching residuals shrink helps them grasp why the least squares line fits best, making abstract ideas concrete.

• Year 10
• Mathematics
• 4 activities
• 20 min–45 min

Learning Objectives

1. Calculate the equation of the least squares regression line for a given bivariate dataset using technology.
2. Analyze the meaning of the slope and y-intercept of a regression line in the context of a specific real-world scenario.
3. Predict the effect of an outlier on the slope and y-intercept of a regression line by manipulating data points.
4. Explain the principle of minimizing the sum of squared residuals in the context of linear regression.

Flipped Classroom

⏱ 30 min·Pairs

Pairs Practice: Study Time Regression

Pairs collect data on classmates' weekly study hours and test scores, enter into a graphing tool, and fit the regression line. They identify slope and y-intercept meanings, then predict scores for 10 extra hours. Share one prediction with the class.

Prepare & details

Explain the concept of 'least squares' in fitting a regression line.

Facilitation Tip: During Pairs Practice, circulate and ask each pair to explain their slope interpretation in their own words before they check it with technology.

Setup: Standard classroom, flexible for group activities during class

Materials: Pre-class content (video/reading with guiding questions), Readiness check or entrance ticket, In-class application activity, Reflection journal

• Understand
• Apply
• Analyze
• Self-Management
• Self-Awareness

Flipped Classroom

⏱ 45 min·Small Groups

Small Groups: Outlier Impact Stations

Provide three datasets at stations: normal, one outlier, multiple outliers. Groups fit lines using technology, compare equations and graphs before and after removing outliers, and note slope changes. Rotate stations and report findings.

Prepare & details

Analyze the meaning of the slope and y-intercept in the context of a regression equation.

Facilitation Tip: In Outlier Impact Stations, assign each group a different outlier to test so the whole class sees varied effects on the regression line.

Setup: Standard classroom, flexible for group activities during class

Materials: Pre-class content (video/reading with guiding questions), Readiness check or entrance ticket, In-class application activity, Reflection journal

• Understand
• Apply
• Analyze
• Self-Management
• Self-Awareness

Flipped Classroom

⏱ 25 min·Whole Class

Whole Class: Real-World Data Fit

Collect class data on sleep hours versus alertness ratings. Display on shared screen, fit regression line together, interpret parameters, and vote on outlier removal. Discuss predictions for extreme values.

Prepare & details

Predict how an outlier might influence the equation of the regression line.

Facilitation Tip: For Real-World Data Fit, prepare two contrasting datasets so students compare how well each line fits its scatterplot and discuss why.

Setup: Standard classroom, flexible for group activities during class

Materials: Pre-class content (video/reading with guiding questions), Readiness check or entrance ticket, In-class application activity, Reflection journal

• Understand
• Apply
• Analyze
• Self-Management
• Self-Awareness

Flipped Classroom

⏱ 20 min·Individual

Individual: Prediction Challenge

Give students a bivariate dataset on advertising spend and sales. Use technology to find the line, interpret slope and intercept in context, and predict sales for a new spend value. Submit with justification.

Prepare & details

Explain the concept of 'least squares' in fitting a regression line.

Setup: Standard classroom, flexible for group activities during class

Materials: Pre-class content (video/reading with guiding questions), Readiness check or entrance ticket, In-class application activity, Reflection journal

• Understand
• Apply
• Analyze
• Self-Management
• Self-Awareness

Teaching This Topic

Teachers should start by having students manipulate data points on paper or whiteboards before using software, so they feel the pull of residuals and why squaring matters. Avoid rushing to the equation; let students feel the ‘drag’ of outliers firsthand. Research shows this tactile step builds stronger intuition than plugging numbers into a formula.

What to Expect

By the end of these activities, students will confidently explain how the regression line minimizes residuals, interpret slope and intercept in context, and recognize how outliers influence the model. Success looks like students using technology to build equations and justify their choices with data.

Watch Out for These Misconceptions

Common Misconception

During Pairs Practice: Study Time Regression, watch for students who assume the line must touch every point.

What to Teach Instead

Have students drag points away from the line and observe how residuals grow, then ask them to explain why the line can’t pass through all points unless data align perfectly.

Common Misconception

During Real-World Data Fit: whole class debates, watch for students who claim the slope shows that one variable causes the other.

What to Teach Instead

Pause the debate and ask groups to propose at least one alternative explanation for the relationship, using the dataset to justify their reasoning.

Common Misconception

During Outlier Impact Stations, watch for students who think moving one outlier won’t change the line much.

What to Teach Instead

Ask students to add or remove their assigned outlier and note the immediate shift in the line’s slope or intercept, then share observations with the class.

Assessment Ideas

Quick Check

After Pairs Practice: Study Time Regression, give each pair a scatterplot and its regression equation. Ask them to identify one residual, explain its meaning in context, and interpret the slope and y-intercept before moving on.

Exit Ticket

After Small Groups: Outlier Impact Stations, give students a small dataset and ask them to use a calculator or tool to find the regression equation. On their ticket, they should write the equation and explain in one sentence how adding a point far from the trend might change the slope.

Discussion Prompt

During Whole Class: Real-World Data Fit, pose the question: 'Why do we square the residuals when finding the least squares regression line?' Facilitate a class discussion where students explain how squaring emphasizes larger residuals and protects against outliers pulling the line too much.

Extensions & Scaffolding

• Challenge: Provide a dataset with a clear outlier and ask students to adjust it so the regression line matches a target slope they choose.
• Scaffolding: Give students a partially completed table to organize residuals before calculating the sum of squares.
• Deeper: Have students research a real-world dataset, fit a regression line, and present how they would collect more data to improve the model.

Key Vocabulary

Least Squares Regression Line	The line that best fits a set of data points by minimizing the sum of the squares of the vertical distances (residuals) from each point to the line.
Residual	The vertical distance between an observed data point and the value predicted by the regression line; it represents the error in the prediction.
Slope (m)	In a regression equation (y = mx + b), the slope indicates the average change in the response variable (y) for each one-unit increase in the explanatory variable (x).
Y-intercept (b)	In a regression equation (y = mx + b), the y-intercept represents the predicted value of the response variable (y) when the explanatory variable (x) is zero.
Outlier	A data point that is significantly different from other observations in the dataset, which can disproportionately influence the regression line.