HNH-32903 Intermediate Analytical Epidemiology: Confounding and Effect Measure Modification


Credits 3.00

Teaching methodContact hours
Knowledge clip0
Individual Paper0
Independent study0
E-learning material0
Course coordinator(s)dr. ir. AM Berendsen
Lecturer(s)prof. dr. ir. E Kampman
prof. dr. ir. P van 't Veer
Examiner(s)dr. ir. AM Berendsen

Language of instruction:


Assumed knowledge on:

Before you start this course you should be able to:

- describe the characteristics of major study designs (i.e., cohort study, case-control study, cross-sectional study);
- understand and calculate effect measures (e.g., IP, IR, IPR, IRR, OR, PAR);
- explain the concepts causality, validity, external validity, internal validity, selection bias, information bias, confounding, effect measure modification, stratification, precision, and bias;
- analyse an association between an exposure and a continuous outcome;
- interpret regression coefficients from linear regression;
- perform basic statistics in R by writing R script (in R studio).

These learning outcomes are related to the courses HNH-28803 Introduction to Analytical Epidemiology and Public Health, HNH-30403 Integration of Evidence I, MAT-25303 Advanced Statistics (online) and HNH-32403 Observational Designs and Assessment of Validity.

Continuation courses:

HNH-33403 Advanced Analytical Epidemiology


Note: This course cannot be combined in an individual programme with HNH-37306 Applied Data Analysis.
This course focuses on how to identify confounding and effect measure modification and how to deal with confounding and effect measure modification in the data analysis. The main focus will be on confounding.

Learning outcomes:

After successful completion of this course students are expected to be able to:

- identify confounding and effect measure modification by stratification;

- adjust the association for confounding by calculating a pooled estimate;

- identify confounding and effect measure modification by linear regression modelling;

- apply linear regression modelling to adjust an association for confounding and to increase precision;

- understand and appreciate the difference between the epidemiological and statistical approach;

- identify potential confounding variables and effect measure modifying variables based on literature and include this in a data analysis plan;

- understand and apply logistic regression, and interpret the results;

- understand the principles of energy adjustment;

- understand the relevance of energy adjustment because of correction for diet composition, removal of external variation in intake, or confounding;

- understand methods to adjust for energy, including the multivariate, density, and residual approach;

- apply the approaches for energy adjustment in R;

- interpret the coefficients of each of the three energy adjustment approaches.


Knowledge clips, e-module, individual assignment, group discussion.


Remote proctored written exam, consisting of a theoretical exam (60%) and a practical exam (20%)and an individual assignment in the form of a data analysis plan (20%) will be part of the examination.


All course material will be available in the learning environment. 

- Medical statistics at a glance by Petrie & Sabin, chapter 27, 28, 29 & 30;
- Essential Epidemiology, an introduction for students and health professionals by Webb & Bain, chapter 8;
- Modern Epidemiology by Rothman, chapter 11.

Compulsory for: MNHDLNutritional Epidemiology and Public HealthMSc1DL