Learning about Linear Regression with Bungee Jumping Barbie

Learning about Linear Regression with Bungee Jumping Barbie


To learn how to set up a linear regression model between two variables from a set of data, and how to use that model to make predictions about the responsive variable.

This packet will use an experiment with bungee jumping barbies to demonstrate how to write a linear regression model (least squares regression line) from a set of data and use linear regression to make predictions about the responsive variable.

See More
Introduction to Psychology

Analyze this:
Our Intro to Psych Course is only $329.

Sophia college courses cost up to 80% less than traditional courses*. Start a free trial now.


Background Knowledge


Correlation Coefficient

Linear Association

Explanatory (independent) Variable

Responsive (dependent) Variable


Calculating Sample Statistics

An Introduction to Linear Regression

Source: Rachel Orr-Depner

Collecting The Data - Let's See Barbie Jump!

This video demonstrates how to collect our data.

Calculating a Linear Regression Model

This video demonstrates how to calculate a linear regression model when you have the correlation coefficient and summary statistics of two quantitative variables. I also review how to make predictions from the linear regression videos and how to find a residual.

Source: Rachel Orr-Depner

A Few Additional Notes

When I was in the classroom and I was running this activity with my students, we would typically end it by using the linear regression model to predict how many rubber bands Barbie would need on her bungee if she wanted to jump from 2 stories high.  I would measure the distance in inches (usually from a stair well), and then we would test our predicted number of rubber bands.  The goal was to get Barbie's head as close to the ground with out having her actually hit her head!  So if you have the space, it is a lot of fun to try it out! 

Try this experiment with not just Barbie, but also with Ken!  What difference do you think you'd see in their linear regression models?