PSYCHOLOGY 301
Methods & Design in Psychology

Lecture 6 (2005)

Multiple Linear Regression 2

Readings

• Multivariate Techniques (Weiss)
(optional, but the section on MLR is recommended)

Overview of MLR2 Lecture

• Types of MLR (from MLR Lecture 1)

• General MLR strategy

General MLR Strategy

• Check assumptions

• Conduct MLR – choose type

• Interpret the output

• Develop a regression equation

1. Check Assumptions

• Check histograms of all variables

• Check scatterplots

• Check correlation table

• Check influential outlying cases

2. Conduct a Multiple Linear Regression

Conduct a multiple linear regression:

• Standard

• Hierarchical

• Stepwise

• Forward

• Backward

3. Interpret the results

Interpret the technical and psychological meaning of the results, based on:

• R, R2, Adjusted R2, the statistical significance of R

• Changes in R and the significance of the changes if steps (i.e., more than 1 model are used)

• Standardised and unstandardised regression coefficients for each model

• Zero-order and partial correlations for each IV in each model

4. Regression equation

If useful, develop a regression equation for the final model.