Module 5: Sample Size Calculations


Dates - Venue - Description - Target audience - Exam
Course prerequisites - Teachers - Course material - Fees - Enrol


February 6, 13, 20 and 27, March 6, 2017, from 5.30 pm till 9.30 pm.


Faculty of Science , Site Sterre, Krijgslaan 281, Building S9, Ghent.


In the design of scientific studies/experiments, sample size determination is of utmost importance. Large enough samples have to be used so that an effect that is of practical significance has a high chance of being detected from the study.

Whether researchers wish to perform their own sample size calculations or rely on experts to do them, a good understanding of the principles and the necessary input parameters is important.

We aim to help structure the problem, find ways to determine input parameters and show how to perform the necessary calculations in R.

This course starts with a general introduction to sample size calculation methods based on the type of outcome or design of interest. In addition different considerations (such as effect size en power) or other factors affecting sample sizes will be discussed.

Sample size calculation applets will be presented. A brief introduction to the R software will accompany the set-up and all subsequent computations will be done within the R environment.

The second phase redirects the sample size calculations to 2 classical domains: the design of clinical trials and the design of surveys.

Under survey design, different sampling methods will be outlined (probabilistic and non-probabilistic) and sample size calculations adapted to these will be presented for various kinds of outcomes and specific design choices. In addition, sample size calculations will be presented for studies set up to evaluate performance of diagnostic tests as well as clustered surveys, e.g. of farms or treatment centers.

For clinical trials, more stringent requirements are imposed in different phases of research from early safety testing over dose finding and confirmatory studies to postmarketing surveillance. In each phase one balances practical feasibility with the need to control errors and protect patients in and beyond the study that is being conducted.

In this course, steps for computing sample sizes for different phases of a clinical trial design will be outlined with practical examples.

Practical sessions and specific simulation exercises in R will allow participants to explore different scenarios and software apps.

Target audience

This course targets participants with little to no experience in sample size calculations who want to learn to design a powerful study.


Participants can, if they wish, take part in an exam. Upon succeeding in this test a certificate from Ghent University will be issued to participants with a university degree at the bachelor level or an equivalent degree.

To qualify for reimbursement from the UGent Doctoral Schools one must attend all classes and pass the exam. Visit the ICES website and your DS website for further information. Additional conditions and procedure.

Course prerequisites

The course is open to all interested persons.

Knowledge of basic statistical concepts and experience with other programming languages are considered and advantage, but not required for following the course.


Foto Lizzy De LobelLizzy De Lobel (Stat-Gent Crescendo, Consulting UGent) studied Mathematics, Statistical Data Analysis and Statistical Genomics at Ghent University, where she also worked as teaching assistant. She has been consultant for the Stat-Gent consortium for several years. Her experience in teaching and consulting on study design and analysis will contribute greatly to this course.

Foto van Emmanuel AbatihEmmanuel Abatih is post-doctoral fellow at Ghent University and works as statistical consultant for FIRE (externe link) and Stat-Gent Crescendo (externe link). He served as statistical analyst at the Institute of Public Health in Brussels in 2005 and obtained a PhD in Life Sciences in 2008 at the University of Copenhagen. He worked for the Institute of Tropical Medicine in Antwerp, as post-doctoral assistant on topics including: space-time analysis, diagnostic test evaluation, transmission dynamic modeling and risk analysis. He can rely on several years of experience as teacher in a wide range of courses in statistics and epidemiology. He has (co-)supervised over 30 masters and 7 PhD students and has experience with R, python, SATSCAN, SAS, SPSS and STATA.

Course material

  • Copies of slides.


    A different price applies, depending on your main type of employment.

    EmploymentModule 5Exam
    Private sector/industry1 800 30
    Non-profit, government, university outside AUGent2 360 30
    (Doctoral)student outside AUGent2 280 30

    1 If three or more employees from the same company enrol simultaneously for this course a reduction of 10% on the module price is taken into account.

    2 AUGent-staff and AUGent doctoral students who pay through use of an SAP internal order/invoice can participate at these special rates.

    Enrol for this course