Module 8: Linear Regression
The Applied Research Center
Module 8 Overview
} Purpose of Linear Regression
} Scatter Diagrams
} Regression Equation
} Regression Results
} Example
Purpose
} To predict scores on one variable based on information
regarding the other variables.
} OR
} To explain why the participants scored differently on a
particular variable of interest.
Scatter Diagrams
} Regression can best be understood by examining a
scatter diagram, which includes the data points and a line
of best fit.
Regression Equation
} The slanted line passing through the data points of a
scatter diagram is the regression line or line of best
fit, which is used to make predictions.
} The regression equation is the technical way of
describing the regression line.
} Y = a + bX
} Y is the predicted score for the dependent variable
} a is the constant
} b is the regression coefficient
} X is the known score on the independent variable
Y = a + bX
} a is the constant, or intercept
} Indicates where the regression line would intersect the y axis
(or the vertical axis, also known as the ordinate).
} It is the value for Y when X = 0
} b is the regression coefficient, or the slope of the
regression line
} It signifies how many predicted units of change (either positive
or negative) in the DV there are for any one unit increase in
the IV.
Regression Results
} r
} the degree to which the predicted scores match up to the
actual scores.
} r2
} Coefficient of determination
} The proportion of variability in the dependent variable that is
explained by the independent variable
} Reported as a percent
Example
} A stats professor wanted to predict student grades on
Assignment 2 based on student grades on Assignment 1.
} Step 1: Write your null and alternate hypotheses:
} H0 = There is no relationship between Assignment 1 and
Assignment 2.
} Ha = There is a relationship between Assignment 1 and
Assignment 2.
Example (cont d)
} Step 2: Input the data into SPSS
} Create a variable for Assignment 1 and a second variable
for Assignment 2
} Input the student grades on Assignment 1 in the
Assignment 1 column and enter student grades on
Assignment 2 in the Assignment 2 column
Example (cont d)
} Step 3: Create a scatter diagram
} Graphs à Legacy Dialogues à Scatter/Dot
} Click on Simple Scatter, then Define
} Assignment 2à Y-axis box
} Assignment 1à X-axis box
} Click Ok
Example (cont d)
} To add a regression line to the scatter plot
} Double click on the chart (in the SPSS Output) to select it for
editing and maximize the chart editor
} Click on any of the data points in the scatter plot to highlight
the data points
} Click Elements from the main menu bar and click on Fit
Line at Total
} Click Close
Example (cont d)
Example (cont d)
} Step 4: Run the Bivariate Linear Regression
} Analyze à Regressionà Linear
} Assignment 2 à Dependent box
} Assignment 1 à Independent box
} Click Statistics
} Click Confidence Intervals and Descriptives (make sure
Estimates and Model fit are also selected)
} Click Continue
} Click OK
Example (cont d)
Example (cont d)
Example (cont d)
} Step 5: Write the prediction equation
} Y = -4.39 + 1.16X
} Step 6: Write up your results
} The hypothesis was tested using a bivariate linear
regression to determine whether student grades on
Assignment 2 could be predicted based on student grades
from Assignment 1. Regression analysis revealed that the
model significantly predicted Assignment 2 grades based
on Assignment 1 grades, F (1, 23) = 18.207, p < .001. R2 for
the model was .44, and adjusted R2 was .42
Module 8 Summary
} Purpose of Linear Regression
} Scatter Diagrams
} Regression Equation
} Regression Results
} Example
Review Activity
} Please complete the review activity at the end of the
module.
} All modules build on one another. Therefore, in order to
move onto the next module you must successfully
complete the review activity before moving on to next
module.
} You can complete the review activity and module as many
times as you like.
Upcoming Modules
} Module 1: Introduction to Statistics
} Module 2: Introduction to SPSS
} Module 3: Descriptive Statistics
} Module 4: Inferential Statistics
} Module 5: Correlation
} Module 6: t-Tests
} Module 7: ANOVAs
} Module 8: Linear Regression
} Module 9: Nonparametric Procedures