Overview
This course develops statistical modelling as a framework for describing relationships, explaining variation, making predictions, and quantifying uncertainty. Students follow the complete modelling cycle from formulating substantive questions and selecting variables to fitting models, checking assumptions, interpreting parameters, validating performance, and communicating conclusions.
Core topics include simple and multiple linear regression, categorical predictors, interactions, transformations, polynomial terms, model comparison, variable selection, multicollinearity, residual analysis, leverage, influence, and heteroscedasticity. The course also introduces generalized linear models, including logistic regression and count-data models, as extensions of the linear-model framework.
Students use statistical software and reproducible workflows to produce visualizations, diagnostic plots, confidence intervals, prediction intervals, hypothesis tests, and practical effect-size interpretations. Applications span business, science, health, and social research, with emphasis on distinguishing predictive from explanatory objectives, recognizing confounding and study limitations, and avoiding causal claims unsupported by research design.
Learning Outcomes
- Translate substantive questions into appropriate statistical models and identify relevant response, explanatory, and confounding variables.
- Estimate and interpret parameters in linear and generalized linear models using appropriate statistical software.
- Diagnose violations of model assumptions using residual analysis, leverage and influence measures, and diagnostic visualizations.
- Compare competing models using principled criteria, variable-selection methods, and predictive validation.
- Evaluate uncertainty, effect sizes, calibration, and out-of-sample performance in statistical analyses.
- Synthesize model results into accurate, reproducible reports for technical and non-technical audiences.
- Critique the limitations of statistical evidence and distinguish association, prediction, explanation, and causation.
Timetable
| Type | Length | Frequency | Period |
|---|---|---|---|
| Lecture | 2 hours | Weekly | All semester |
| Lab | 2 hours | Weekly | All semester |
| Tutorial | 1 hour | Fortnightly | All semester |
Assessment Schedule
| Type | Description | Weighting |
|---|---|---|
| Assignment | Statistical modelling assignments (4 × 7.5%) | 30.00% |
| Test | Practical data analysis tests (2 × 10%) | 20.00% |
| Deliverable | Reproducible modelling report | 15.00% |
| Exam | Final examination | 35.00% |
Prerequisites
Teaching Staff & Programs
This course is delivered jointly by faculty from the participating programs listed below. In line with the Douchewater Way, the University of Sexology tailors core instruction directly to each cohort's specific discipline — adapting curriculum to program needs rather than forcing students into a one-size-fits-all model. Learn more about our approach at The Douchewater Way.
