create and use linear regression to determine if there is a relationship between two sets of values
Math 114 Regression Project
Goal:
Process:
Use regression to determine if there is a relationship between two sets of values.
1.Choose a question asking if there is a relationship between two values.
The question can from any field of study, and should be one where a relationship is not already predetermined, but feasible.
My example is: Does the payroll of a professional baseball team help determine the number of games that team wins?
2.Gather data on the values and enter into a spreadsheet.
Data can be gathered from any source, but should be documented. There are official guidelines for gathering data directly from people.
For my example, I used the payrolls for all 30 Major League baseball teams and their current winning percentages.
3.Create a graph of the data, including a trendline.
Any software that graphs can be used, but I will be using Microsoft Excel. The graph should be titled with labeled axes. The trendline, equation, and R2-value should be displayed on the graph.
4.Determine if there is a relationship between the values.
An R2 close to one shows a high correlation between the values, close to zero shows there is no correlation. Remember that correlation is not causation; there may be hidden variables at work.