Linear Correlation Project

Goodwin Statistics 167

Linear Correlation Project 

Part 1

Create a scatter plot of the data. Make sure to label the axes of the graph and create a consistent scale. Make sure to give your scatterplot a title. You can do this by hand or by using Excel. If you choose to use Excel, here’s a video that will help you to create the scatterplot: 

Using only the graph, write a paragraph that addresses the following questions:

1. Does there appear to be a linear relationship between x and y? How can you tell?
2. Does the relationship appear to be positive or negative? How can you tell?
3. Does the relationship appear to be strong or weak? How can you tell?

Part 2

Calculate the correlation coefficient, r and the coefficient of determination, r². You learned how to use the TI-Graphing calculator to do this in Hawkes. But here’s another resource with the process in case you need a reminder: 

Write a paragraph that addresses the following questions:

1. What is the value of the correlation coefficient?
2. Does the correlation coefficient confirm the strength (weak or strong) and direction (positive or negative) you from your scatterplot in Part 1? Describe how you know.
3. Interpret the meaning of the coefficient of determination, r², within the context of your data.

Part 3

Determine the equation of the regression line, y=b₀+b₁x. You learned how to use the TI-Graphing calculator to do this in Hawkes. But here’s another resource with the process in case you need a reminder: 

1. What value is the slope (b₁) of the linear regression line? Describe what the slope means within the context of your data set. Your instructor will review how to describe this in class but if you need an additional resource, click this link: 
2. What is the value of the y-intercept (b₀)? Describe what this value means within the context of your data set. Your instructor will review how to describe this in class but if you need an additional resource, click this link: 
3. Describe how you could use the equation of the linear regression line to predict values not included in the data set. Then pick an x-value outside your given data set and use the equation to calculate the predicted y-value. You can choose any x-value you want as long as it is not included in the given data set.