SUBJECT
Title
Statistical methods in healthcare analyses
Type of instruction
lecture
Level
master
Faculty
Part of degree program
Credits
4
Recommended in
Semester 2
Typically offered in
Spring semester
Course description
The course covers advanced statistical methods for health care research. The course is applied in the sense that is focused on estimating models and interpreting the results, rather than understanding the detailed mathematics behind the methods.
Topics include:
- simple and multiple linear regression,
- model development,
- assessment of goodness-of-fit,
- logistic regression,
- logistic regression in case-control studies,
- logistic regression for prediction,
- Poisson-regression,
- Cox-regression,
- summarising evidence, meta-analysis.
Each method is introduced by examples from the scientific literature. Applicability of each method, model assumptions, checking model assumptions, and interpretation of the results are covered in the lectures. Students perform exercises by STATA and MetaXL related to all topics.
Readings
- Kirkwood B, Sterne JAC. Essential medical statistics. Blackwell Science, Oxford, 2006.
- MetaXL user guide
- PRISMA guideline. http://www.equator-network.org/
- Cottingham J, Hunter D. Chlamydia trachomatis and oral contraceptive use: a quantitative review. Genitourin Med. 1992 Aug;68(4):209-16.
- Colditz GA, Brewer TF, Berkey CS, Wilson ME, Burdick E, Fineberg HV, Mosteller F. Efficacy of BCG vaccine in the prevention of tuberculosis. Meta-analysis of the published literature. JAMA. 1994 Mar 2;271(9):698-702.
- Groenwold RH, Rovers MM, Lubsen J, van der Heijden GJ. Subgroup effects despite homogeneous heterogeneity test results. BMC Med Res Methodol. 2010 May 17;10:43.