The department coordinates and carries out the Statistics courses in three bachelor programs of the FHML, as well various statistics courses at the master and PhD level.  All courses use a mix of lectures, computer practicals, and tutor groups or practical lectures/workshops.
Furthermore, the department contributes lectures and practicals in various courses of the bachelor program Medicine, and advises master students of Medicine on statistical issues in their research internship (WESP).  

Below is a summary of our courses and their contents.

 

Bachelor Health Sciences

 

Course code and title: B-GZW1026: Introduction to statistical methods for data analysis

Coordinator: Dr. Shahab Jolani

Contents:
The focus is on statistical concepts and techniques that play a role in summarizing and describing observed variables and relationships between variables, as well as generalizing the results for a larger group of people than the observed group. The first theme of this course is to summarize the observed data. The second theme is the testing concept. The third theme pertains to various basic statistical techniques that are used to analyse observed data.

 

Course code and title: GZW3024: Advanced Statistics and Research Methods

Coordinator: Dr. Math Candel (Dept. Methodology & Statistics)
Co-coordinator:  Dr. Ludovic van Amelsvoort (Dept. Epidemiology)

Contents:
The course addresses advanced statistical analysis techniques and methodological issues relating to four themes:
1. Quantitative research into causal relations between determinants and health related outcomes;
2. Research into the quality of measurements and measurement devices;
3. Preparing and planning of quantitative research;
4. Critical reading and assessment of the quality of a scientific article.

Statistical techniques:
Multiple linear and logistic regression and their relation with ANCOVA and cross table analysis respectively, techniques for reliability and validity assessment of measurements (Cronbach’s alpha, test-retest reliability, intraclass correlation, sensitivity and specificity, ROC curves), marginal linear models for longitudinal data, power and sample size calculations for some basic analysis techniques and designs.

Methodological issues:
Research designs, information and selection bias, confounding, effect modification, methods for systematic literature review, interpretation of meta-analysis (funnel plot, forest plot, pooled effect estimates), Bradford Hill criteria for causality, choice of an appropriate analysis technique.

Software used:
SPSS and Gpower    

 

Bachelor Biomedical Sciences

 

Course code and title: BBS1003: Introduction to statistical methods for data analysis

Coordinator: Dr. Sophie Vanbelle

Contents:
The focus is on statistical concepts and techniques that play a role in summarizing and describing observed variables and relationships between variables, as well as generalizing the results for a larger group of people than the observed group. The first theme of this course is to summarize the observed data. The second theme is the testing concept. The third theme pertains to various basic statistical techniques that are used to analyse observed data.

 

Course code and title: BBS2007: Statistics II

Coordinator: Dr. Bjorn Winkens

Contents:
Linear regression analysis, analysis of variance, logistic regression analysis, repeated measures analysis.

 

 

Bachelor European Public Health

 

Course code and title: B-EPH1018: Introduction to statistical methods for data analysis

Coordinator: Dr. Shahab Jolani

Contents:
The focus is on statistical concepts and techniques that play a role in summarizing and describing observed variables and relationships between variables, as well as generalizing the results for a larger group of people than the observed group. The first theme of this course is to summarize the observed data. The second theme is the testing concept. The third theme pertains to various basic statistical techniques that are used to analyse observed data.

 

 

Course code and title: EPH2008 and EPH2009: Statistics Trajectory

Coordinator: Drs. Gavin van der Nest

Contents: The Methodology, Epidemiology and Statistics horizontal trajectories (MES) focus on methodological aspects involved in planning, conducting and interpreting empirical, quantitative research. They are meant to familiarize students with the mentality of working with problems, of developing a framework for thinking patterns and strategies for problem solving. In the statistical part students will learn to integrate statistical elements within the problem solving.The second year focuses particularly on ‘Statistical Modelling’. Emphasis is given to two modelling approaches commonly used in Public Health and Medical investigations: Linear and Logistic Regression.

 

 

Master  catch-up course FHML / premaster course Mental Health

 

Course code and title: FHML0001 / GZW3301: Blended learning course Statistics

Coordinator: Dr. Math Candel

Contents: The course is on statistical concepts and techniques that play a role in describing and summarizing observed variables and their relations, and on generalizing the result of the observed group of persons (sample) to a much larger group (population). There are three themes: (1) How to summarize data, (2) How to test hypotheses and thus draw conclusions about the population, and (3) Which basic statistical techniques to use for analyzing the data ?

 

 

Master Global Health

 

Course code and title: MGH4002 and MGH4006: Methodology and Statistics I and II

Coordinator: Drs. Gavin van der Nest

Contents: Students will revise/become acquainted with various research paradigms within the fields of public and global health (covering qualitative, quantitative and mixed methods). Focus is given to the development of a solid understanding of the whole research process and its basic components: literature review, formulation of research questions, selection of an appropriate design (and awareness of its limitations), data collection, analysis and translational synthesis (interpreting numerical findings and reporting them concisely and intelligibly). Advanced statistical techniques covered are: Multiple linear and logistic regression models, Factor Analysis, Reliability and Validity of questionnaires.

 

 

Master Epidemiology

 

Course code and title: EPI4923 – Advanced Statistical Analysis Techniques

Coordinator: Dr. Sophie Vanbelle

Contents: analysis of (co)variance, linear regression analysis, logistic regression analysis, survival analysis, analysis of repeated measurements, choice of the appropriate statistical technique in relation to the study design.

 

 

PhD courses

 

Course code and title: 0006: Introduction to Inferential Statistics

Coordinator: Dr. Shahab Jolani

Contents: The objective of this course is to familiarize the participants with statistical reasoning, its importance in evidence-based science as well as to hone a critical awareness of its shortcomings. Focus will be given to simple inferential techniques. They are the most frequently applied tools by researchers carrying out comparative/exploratory studies of quantitative nature. The basics of hypothesis testing and its associated techniques stand in the foreground (t-tests, ANOVA and non-parametric alternatives, chi-square test, basics of simple and multiple regression and repeated measures ANOVA).

 

Course code and title: 0008: Regression analysis, Statistics part 2

Coordinator: Dr. Bjorn Winkens

Contents:

In this course we elaborate on the topics discussed at the end of the Introduction to Inferential Statistics. This means that we start with correlation and linear regression analysis and discuss these topics using practical examples which also deal with issues that often occur in practice, such as spurious correlations, confounding and measurement error. To be able to apply these analysis methods to your own data, each lecture is followed by a practical session in which the participants can work on an assignment using the statistical program SPSS. Next to linear regression analysis, also logistic regression analysis and analysis of variance (ANOVA) will be discussed in the same manner. In practice, it is very important to be able to choose a suitable analysis model. Therefore, some guidelines for modeling strategies to obtain a final model on which the conclusions will be based, will be presented as well.

 

Course code and title: 0823: Multilevel Analysis of Longitudinal Data (MALD)

Coordinator: Dr. Shahab Jolani

Contents:
This course covers recent developments in the analysis of longitudinal data. For multilevel designs (e.g. first level of observations are nested within a randomly selected second level sample of subjects), standard regression techniques lead to biased model-parameter estimates and incorrect standard errors. Biased regression parameter estimates typically occur if the subjects were not measured at the same time points (unbalanced data) and if missing observations are involved. Due to the multilevel structure, more sophisticated models should therefore be used to account for the correlation between observations. Moreover, correlated data often occur due to memory effects when subjects were measured repeatedly across time. This type of correlation is called “serial correlation”. In this course, the main emphasis is on linear models with random effects and possibly serial correlations.  Special attention will be given to the analysis of longitudinal intervention-studies, where the objective is to evaluate some treatment effect. A distinction will be made between statistical methods to analyse longitudinal data from experiments and those from quasi-experiments.

 

Course code and title: 0830.  Survival Analysis

Coordinator: Dr. Sophie Vanbelle

Contents:  Analysis of the relations between survival  times and prognostic factors.

 

 

Course code and title: 0836. Introduction to linear structural equations modeling (Lisrel)

Coordinator: Dr. Nick Broers

Contents: 
Structural equations modelling (SEM) is the term used to describe the general multivariate method of conducting factor analyses, multiple linear regression analyses and path analyses. SEM can be used for testing and evaluating complex causal models in observational studies. These models may contain multiple independent, dependent and mediating variables (interactions and categorical dependent variables can be problematic depending on the software used). SEM can also be used for confirmative factor analysis. The objective of this course is to introduce the user to the many possibilities and limitations of SEM and to practice this method using real datasets. This is done with LISREL, the oldest known computer program for SEM.