Advanced Analytical Epidemiology

The courses of Nutritional Epidemiology and Public Health are interesting for professionals who are conducting or using nutritional and/or health/disease research among various research target groups like patients, elderly or f.i. regional populations. It is also suitable for teachers in nutrition and/or health education, policy makers of (inter)national organisations or governments, managers of food or pharma industries that develop specific (medical) nutrition for target groups and the courses are furthermore open to anyone who wants to engage a career in the work field of nutritional epidemiology and public health. A solid background in statistics is needed and please pay attention to the specific prerequisite knowledge that is written below.

Prerequisite knowledge

Before you start this online master's course you should be able to:

+understand and calculate effect measures (e.g., IP, IR, IPR, IRR, OR, PAR);

+interpret regression coefficients from multiple linear regression and simple logistic regression;

+perform basic statistics in R by writing R script (in R studio).

These learning outcomes are related to the combined courses Introduction to Analytical Epidemiology and Public Health, Advanced Statistics and Intermediate Analytical Epidemiology: Confounding and Effect Measure Modification (see under Related Courses in the right-hand column).

• Execute and interpret data analysis using linear regression models, logistic regression models, general and generalized linear models, mixed models, and Cox proportional hazard models
• Execute and interpret stratified analysis
• Adjust for confounding and identify effect modifiers using both stratified analysis and statistical modelling
• Systematically organize and document data analysis to study diet-disease associations, using the statistical program R (Studio)

In this online master's course, you will study diet-disease associations in the general population or specific patient groups while applying appropriate epidemiological data analyses such as logistic regression, Cox proportional hazard models and mixed models while handling confounding and effect measure modification.

Knowledge about how to obtain a valid answer to a research question is a prerequisite for everybody conducting observational research. Confounding and effect measure modification are topics that should be dealt with during data analysis. The data analysis of case control studies and several types of longitudinal studies are prerequisites for a successful conduct of a master thesis and an essential skill for epidemiologists.

Activities

This course is an online course at master level that you follow in a cohort. Learners participate at different time points and from different time zones, as most learners also have a job. The programme therefore offers learning activities that allow you to supervised self-study at your own pace, with deadlines for assignments, and can include knowledge clips, e-learning modules, online individual and group exercises and assignments, online discussions, and in some courses occasionally live question hours through MS Teams at specific dates and times. There are no online live classes. The exam has a fixed date.

This course is quite time-intensive and requires approximately 20 hours per week for the average participant. There are assignments with deadlines.

Software used in this course:

R, including R studio.

Self-Paced Online Course Getting Started with R

You need to have a good basic understanding of statistics, and you need to have experience with software 'R'. If the latter is not the case, you can follow the Self-Paced Online Course Getting Started with R first. For more information and registration, please check the document linked in the right-hand column.

Literature

All course material will be available in the learning environment and includes amongst others:

+Kleinbaum, D.G. (2012) Introduction to Survival Analysis, chapter 1.

+Dos Santos Silva, I. (1999), Cancer epidemiology: Principles and Methods, chapter 12.

+Hedeker, D. (2006) Longitudinal data analysis, chapter 1

Upon successful completion - passing the exam -, a digital Micro-credentials certificate (EduBadge) with 3 study credits (ECTS) is issued. The EduBadge certifies the learning outcomes of short-term learning experiences, marking the quality of a course.

+Remote proctored exam with closed and open questions.

+Remote proctored exam with RStudio.

Participation in the exam is optional. If you decide not to participate in the exam, you do not qualify for a certificate and/or micro-credential.