1
HPS434 Psychology Research Methods (Advanced)
Core Learning Objectives
Week 1: Multiple Regression (reading: Field chapter 9)
1. What is multiple regression (including the regression equation) and when is it useful.
2. How do methods of multiple regression (standard, hierarchical, stepwise) differ.
3. What are the key pieces of output, and how do they relate to my research questions.
4. What are the key assumptions to make multiple regression run properly and how do I
check these assumptions.
Week 2: Logistic Regression (reading: Field chapter 20)
1. Understanding when logistic regression should be used.
2. Examining the differences between logistic regression and other methods (i.e., MR).
3. Understanding logistic function vs other functions.
4. Understanding the role of categorical coding.
5. Interpreting logistic regression statistics (model overall and individual predictors).
6. Making sense of logistic regression output (log odds and odds ratios).
Week 3: Mediation and Moderation (reading: Field chapter 11)
1. Exploring what moderation is.
2. Understanding when to undertake a moderation analysis.
3. Understanding how to undertake a moderation analysis.
4. Learning how to interpret the output of moderation analyses.
5. Exploring what mediation is.
6. Understanding when to undertake a mediation analysis.
7. Understanding how to undertake a mediation analysis.
8. Learning how to interpret the output of mediation analyses.
Week 4: Path Analysis (no prescribed reading)
1. What is structural equation modelling.
2. How does path analysis fit within SEM.
3. What are the basic building blocks of SEM
4. How is SEM (in particular, path analysis) different from multiple regression
5. What are the advantages of path analysis.
6. Explain how to evaluate your model (using the chi-square statistic).
Week 5: Confirmatory Factor Analysis (no prescribed reading)
1. Confirmatory factor analysis and when/why it is used.
2. What a Confirmatory factor analysis implies.
3. The issue of scaling.
4. Exploring fit indices beyond (chi square).
5. Examining key output.
Week 6: Structural Equation Modelling (no prescribed reading)
1. Piecing it all together: SEM is Path Analysis plus Confirmatory Factor Analysis
(Measurement model; structural model; SEM vs path analysis).
2. Assumptions (Sample size; other GLM assumptions; identification).
3. Advanced topics: What to do when you have a poor fitting model.
4. Advanced topics: How to compare several competing models.
2
HPS434 Psychology Research Methods (Advanced)
Week 7: Multilevel Modelling (reading: Field chapter 21)
1. Discussing multilevel modelling (MLM) and looking at when/why would it be used.
2. Examining key concepts (clustering, intra-class correlations (ICCs), centering).
3. Discussing Level 1 vs. Level 2 variables
4. Exploring random vs. fixed effects
5. Exploring cross-level interactions
6. Examining the modelling approach
7. Discussing effect size estimation in multilevel modelling
Week 8: Exploratory Factor Analysis (reading: Field chapter 18)
1. What is factor analysis and why do we use it?
2. What a factor analysis does, and how it works.
3. What is meant by Dimensions, Eigenvectors, and Eigenvalues.
4. Describing and naming the factors.
5. What the requirements for factor analysis?
6. When to stop extracting factors.
7. How to tell if a factor analysis has worked.
8. How to make the factors fit better.
Week 9: Multivariate Analysis of Variance (reading: Field chapter 17)
1. What is MANOVA and when should you use it?
2. What do we need to know to understand MANOVA?
3. How many participants do we need for MANOVA?
4. How do I interpret the assumptions of MANOVA?
5. How do I interpret the results of a MANOVA?
