4 Brrrr…It’s Cold! Copyright © 2026 Pearson Education, Inc. Brrrr…It’s Cold! (50 – 60 minutes) Learning Objective(s): Students will match a scatter plot that represents bivariate numerical data with its residual plot. Students will determine the strength and direction of the correlation in a real-world context. Material needed: Student pages: Brrrr…It’s Cold! Calculator or online calculator Graph paper Lesson Procedure: Warm–Up 10 minutes Prompt: How does your household regulate indoor temperature? How do you keep warm in the winter and/or cool in the summer? Discuss: Have students share with the group their experiences with energy usage to regulate home temperature. Guided Instruction 15 minutes Present: scenario for Brrrr…It’s Cold! Example: Many people use natural gas to heat their homes. How do you think that natural gas companies can plan for demand during the winter? Sample answer: They can use historical data to predict how much gas they will sell. How does variation in their data affect their predictions? Sample answer: Variation increases the uncertainty in their models. That means that demand may be more or less than they predict, depending on the weather for a certain year. Review: key terms – linear model, residual linear model: a linear function that represents the data in a bivariate data set residual: the difference between the observed value of a dependent variable and the predicted value of that variable from a regression model Independent Practice 20 minutes Distribute: student activity Brrrr… It’s Cold Have students build a model and select the correct plot of the residuals. Then, have them work in pairs on question 3. Encourage and guide students to be supportive and courteous to each other during their discussion. Closure 10–15 minutes Review Answers: 1. See graph. 2. A 3. a. Sample answer: My partner’s work is different from mine, but both lines of best fit are reasonable. b. Sample answer: There appears to be a negative correlation, because lower values of x tend to have higher y values. c. Sample answer: The correlation is fairly strong. Most of the residuals seen in the data are close to 0. Discuss: How can linear regression and residuals help a company prepare for future gas demand?
RkJQdWJsaXNoZXIy NjM5ODQ=