The event is a training school, part of the HARMONY COST Action 18208 training activities, with introductory didactic teaching and hands-on practical sessions on Bayesian methods for true prevalence estimation & diagnostic test evaluation.
The following core topics will be covered:
1. Running basic models in JAGS
2. Apparent & true prevalence estimation
3. How to choose a prior distribution?
4. Diagnostic test evaluation with Hui-Walter models
Pre-course preparation work will also be provided as a prerequisite for attending the course and to provide a more thorough description of the topics that will be covered. Prior experience of Bayesian statistics or latent class methods is not expected, but basic statistical knowledge and R programming skills are expected. Participants will have to bring their own-laptops.
The primary learning objective of the school is that participants understand how to implement these methods on their own data, both in terms of the practice of Markov
chain Monte Carlo (MCMC) and how to interpret the results.