Although researchers do their best to prevent missing data, it remains a common issue in medical and epidemiological research. The extent to which missing data affects study outcomes and how best to deal with it depends on both the amount of missing data and the reasons why the data are missing. This three-day course covers both basic and advanced techniques for evaluating and handling missing data in medical and epidemiological research.
There are various methods available for dealing with missing data. Simple approaches include ignoring missing values or using regression models to estimate them. More advanced techniques, such as Multiple Imputation, offer more robust solutions. Multiple Imputation using the Multivariate Imputation by Chained Equations (MICE) procedure is a promising method that performs well across a range of data scenarios involving missing values. This technique generates multiple complete datasets, allowing statistical analyses to be performed on each one. The results are then combined using specific calculation rules (Rubin’s Rules). These steps will be discussed during the course, along with questions about the use of different methods for handling missing values in medical and epidemiological research. Attention will also be given to evaluating the success of the imputation strategy (imputation diagnostics).
Each course day begins with morning lectures, followed by computer practicals. During the practicals, participants will work with both basic and advanced methods for handling missing data, such as Multiple Imputation, using R (RStudio) and SPSS. Real-world epidemiological and medical example datasets will be used. In addition, participants will interact with an AI chatbot that simulates a clinical researcher facing a realistic missing data problem from clinical research practice.
Key takeaways:
- Examples of missing data in medical and epidemiological research
- Understand the mechanisms behind missing values: MCAR, MAR, and MNAR
- Learn how missing data affects statistical analyses and the implications
- Approaches to evaluating different data scenarios involving missing values
- Application of basic methods for handling missing data
- Deepen your understanding of the theory and practice of Multiple Imputation (MICE)
- Data analysis following Multiple Imputation
- Evaluating the imputation strategy (imputation diagnostics)
Start Date: 28 January 2026
Tuition fee: € 1.125,- includes lunch, coffee, and tea
Duration: 3 days
Time Commitment: 20–40 hours (exam optional)
Study Load: 2 ECTS
Location: Amsterdam, Frans Otten Stadium
Registration Deadline: 15 December 2025
Accreditation (if applicable): This course is accredited only for Dutch professionals: general practitioners, geriatric specialists, doctors for the mentally handicapped, medical specialist, social physicians, company doctors, insurance doctors, doctors for society and health.
The course “Missing data: consequences and solutions” (WV81) is accredited for 20 hours.
To qualify for these credits, there is an attendance requirement of 100%.