Overview
Advanced Biostatistical Modelling develops the theory and application of regression, longitudinal, survival, multilevel, causal, and Bayesian methods for complex health and biomedical studies. Topics include generalized linear models, logistic and Poisson regression, overdispersion, mixed-effects models, generalized estimating equations, repeated-measures analysis, censoring, truncation, competing risks, frailty models, and time-dependent covariates.
Students design and execute reproducible analyses using authentic datasets and statistical software. Emphasis is placed on estimands, study design, confounding, effect modification, missing data, model diagnostics, validation, sensitivity analysis, multiplicity, and transparent reporting. Health-specific interpretation includes odds ratios, risk ratios, hazard ratios, incidence rates, absolute effects, clinical relevance, and the distinction between statistical and practical significance. Advanced modules address propensity scores, marginal structural models, mediation, causal inference, penalized regression, high-dimensional methods, and hierarchical or Bayesian modelling, alongside ethical, privacy, regulatory, and human-subjects considerations.
Learning Outcomes
- Select and justify statistical models aligned with study design, outcome type, estimand, and sampling structure.
- Formulate and fit generalized linear, mixed-effects, longitudinal, survival, and competing-risks models using appropriate statistical software.
- Evaluate model assumptions, diagnostics, goodness of fit, calibration, predictive performance, and sensitivity to influential observations.
- Estimate and interpret relative and absolute effects, interaction, effect modification, incidence rates, hazard functions, and measures of clinical relevance.
- Analyze clustered, repeated, censored, truncated, longitudinal, and time-dependent data using appropriate inferential methods.
- Manage confounding, missing-data mechanisms, multiplicity, and selection bias through defensible design and analytical strategies.
- Apply propensity-score, marginal structural, mediation, and observational causal-inference methods while identifying their assumptions and limitations.
- Construct reproducible analysis workflows with documented code, versioned outputs, transparent reporting, and privacy-conscious data practices.
- Critically evaluate published biomedical studies for methodological validity, interpretive accuracy, reproducibility, and ethical compliance.
- Communicate complex statistical findings accurately to clinicians, biomedical researchers, and public-health professionals through technical reports and oral presentations.
Timetable
| Type | Length | Frequency | Period |
|---|---|---|---|
| Lecture | 2 hours | Weekly | All semester |
| Lab | 2 hours | Weekly | All semester |
| Tutorial | 1 hour | Fortnightly | All semester |
| Workshop | 2 hours | Fortnightly | Second term |
Assessment Schedule
| Type | Description | Weighting |
|---|---|---|
| Assignment | Analysis plan and estimand specification | 10.00% |
| Assignment | Reproducible modelling exercises (4 × 5%) | 20.00% |
| Test | Diagnostic and model-comparison practical test | 15.00% |
| Assignment | Critical appraisal of a published biomedical study | 15.00% |
| Deliverable | Technical report using an authentic health dataset | 25.00% |
| Capstone | Oral presentation of the final analysis | 15.00% |
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.