Description: Essentially all statistical problems can be formulated as regression problems: the problem of quantifying the relationship between a dependent variable and one or more independent variables. Surprisingly many statistical problems encountered in clinical practice can be succesfully handled with a small set of "core regression techniques", alongside an understanding of the rationale and limitations of statistical regression in general. The present course is a case-based introduction to these core regression techniques, with an emphasis on common features rather than differences.

Topics covered will include the following:

- Linear regression (including the t-test)

- Analysis of variance
- Logistic regression
- An introduction to Cox regression for survival data

The course includes computer practical exercises. Upon completion of the course, the student will be able to perform basic regression analyses in a suitable statistical software program. The student will also obtain a broad foundation for learning and applying other and more advanced regression techniques.

Literature: To be announced
Prerequisites: Knowledge of statistics (including confidence intervals and P-values), at the level of the PhD course "Quantitative research methods: an introductory guide for clinicians".

Evaluation: Written assignment

Organizer: Anders Gorst-Rasmussen, PhD, senior biostatistician

Lecturers: To be announced

ECTS: 2.4 (3 days)

Time: 4., 11. 18 June 2015

Place: Forskningens Hus, Sdr. Skovvej 15, 9000 Aalborg, room 106

Zip code: 9000

City: Aalborg

Number of seats:

Deadline: 15 May, 2015