Regression models in medical research

Study facts

Course code	MEDSTAT2-B
Study level	PhD level
Belongs to	Department of Global Public Health and Primary Care

Course description

Language of instruction

Norwegian.

English if International PhD candidates

Course content

The aim of the course is to give an introduction to regression models that are used in medical and epidemiological research (Cox regression, logistic regression, linear (Gaussian) regression etc.). The course will give an understanding of applications and limitations of the methods. Furthermore, the students will learn to perform simple analyses, interpret output from statistical packages and present such results in scientific articles.

Learning outcomes

Knowledge

After completing the course, the students should be able to

- understand the difference between observational studies and randomized trials

- know about basic regression models (linear, logistic, Cox etc.)

- know about confounding and explain adjustment by using regression

- know about different representations of variables in regression models, and interpretations of regression coefficients

Skills

After completing the course, the students should be able to

- perform and interpret basic regression analyses using STATA

General competence

After completing the course, the students should

- have acquired good scientific practice and understanding of how to report data and numbers, for example not report selectively or exaggerate own results and their implications

Study period

Spring

Credits (ECTS)

3 ECTS credits

Specific terms

Course registration and deadlines

Course registration on Studentweb, deadline 1. February.

Pre-requirements

HELSTA, MEDSTAT1A, MEDSTA or equivalent. Knowledge about statistical packages

Form of assessment

Written exam, 3 hours.

Pass/fail

Who may participate

Ph.D. candidates

Addtional information

Supplementary course information

NB! All students must bring their own computer with STATA installed!

Programme

Lectures and practices.

5 days of teaching.

The exercises will be based on the program STATA, and this demands knowledge about using statistical packages.