Examination arrangement

Course content

This course cover statistical methods for comparing mean values of a continuous, normally distributed variables between groups defined by one or two grouping factors (one-way and two-way ANalysis Of VAriance, respectively). For one-way ANOVA, strategies for dealing with multiple testing problems in pairwise comparisons between groups and a non-parametric alternative test (Kruskal-Wallis test) will briefly be covered. For two-way ANOVA, models both with and without an interaction term between the grouping factors (full factorial model) will be considered. Analysis of covariance (ANCOVA, linear regression in groups) for comparing adjusted rather than unadjusted mean values, is also part of the curriculum for this course. Evaluation of assumptions on the model and strategies for dealing with deviation from assumptions, will be covered. ANOVA models is within the family of general linear models, and similarities and differences between the ANOVA model and a (general) linear regression model will be highlighted. ANOVA models are typical in experimental research but can also be applied in observational studies.

Learning outcome

After successful completion of this course the student should

• have achieved theoretical knowledge on the methods and models covered by the course, including principles for estimation and hypothesis testing
• be able to choose an appropriate method or model to evaluate simple and more complex scientific questions
• be able to perform the data analyses by means of a statistical program package and be able to extract and interpret relevant information from the output from the analyses
• have knowledge on and be able to evaluate the inherent assumptions on the applied model or method
• be able to report the results from the statistical data analyses in a scientific medical journal

Learning methods and activities

Lectures and exercises in second part of spring semester. Practical data analyses by means of SPSS and/or STATA.

Recommended previous knowledge

Introductory course in medical statistics (KLMED8004 or equivalent), and familiarity with linear regression models (KLMED8014 or equivalent) is recommended. Some prior training in use of statistical software is also needed for successful completion of the course.

Required previous knowledge

Introductory course in medical statistics (KLMED8004, MH3003 or equivalent) is a requirement for this course.

Course materials

Lecture notes and other learning material posted by teacher.

Textbook by Rosner, B: "Fundamentals of Biostatistics", 8th ed. 2016.

Textbook/learning material may change.

Credit reductions