Statistics II
Full course description
Within psychology, there is a tradition of experimentally oriented research, although quasi-experiments and correlational research also frequently occur. The data to be analysed are often quantitative, such as test scores and response times. The most accepted statistical analysis method for quantitative data from experimental research is analysis of variance (ANOVA), and the most common for correlational research is regression analysis. During this course, students familiarise themselves with the logic and application possibilities of analysis of variance and, to a lesser degree, with regression analysis. Treatment of these topics will build on one-way ANOVA and regression analysis as taught in the first academic year. The guiding principle here is the distinction between within subjects (WS) and between subjects (BS) designs, and the distinction between experimental, quasi-experimental and correlational research.
The course consists of six one-week modules. Students will learn about the design and corresponding analysis model through a combination of lectures, seminars, tutorials and the SPSS practical.
- Module 1: Review of one-way BS design, one-way ANOVA, multiple comparisons.
- Module 2: The orthogonal (‘balanced’) two-way BS design, two-way ANOVA, interaction, main effects, simple effects, relations with the unpaired t-test;
- The non-orthogonal (‘unbalanced’) two-way BS design, two-way ANOVA, confounding and adjustment.
- Module 3: BS experiments and quasi-experiments with a covariate, such as age or pretest score, analysis of covariance (ANCOVA), the two functions of a covariate (increasing power, correcting for confounding).
- Module 4: Correlational research, regression analysis with multiple predictors.
- Module 5: The one-way within subject (WS) design, repeated measures ANOVA using the univariate, epsilon-adjusted method, or the multivariate method.
- Module 6: The two-way WS design, the split-plot (BS*WS) design for BS experimentation with repeated post tests and WS experimentation with a BS factor, repeated measures ANOVA for these designs.
The corresponding practical for this course is: SPSS II
The final assessment for this course is a numerical grade between 0,0 and 10,0.
Course objectives
Students are able:
- to explain the logic and aspects of analysis of variance and correlational research and regression analysis (incl. one-way between group analysis of variance, multiple comparisons, orthogonal versus non-orthogonal designs, two-way between group analysis of variance, main and interaction effects, confounding problems, analysis of covariance, multiple regression analysis, one-way within groups analysis of variance, univariate versus multivariate analysis models, two-way within group analysis of variance, split plot analysis);
- to apply the methods to analyse of variance on a dataset and interpret the results;
- to perform a multiple regression analysis on a dataset and interpret the results.
Prerequisites
Admission requirement: on reference date March 15 of the relevant year Statistics I has to be completed