Workshop: An Introduction to History Matching with Emulation using the R-package (hmer)
Complex infectious disease models are widely used by epidemiologists to improve our understanding of transmission dynamics and disease natural history, and to predict the possible effects of interventions. As the complexity of such models increases, however, it becomes increasingly challenging to robustly fit them to empirical data.
History matching with emulation is a calibration method that has been used to calibrate models in a wide range of fields, including epidemiology, galaxy formation, and climate science. It can be used for any type of mathematical model, but is particularly useful for complex models, with long run times and/or large numbers of inputs and outputs, that often cannot be calibrated using other available methods. We have developed a new, user-friendly software package, hmer, that implements history matching with emulation, making it straightforward to calibrate models using this approach.
In this one-day in person workshop, we will introduce you to the history matching and emulation framework, and guide you through using the technique to calibrate models using hmer. In this workshop, we will focus on calibrating deterministic models and the mean of stochastic model runs. We will also briefly discuss using hmer to calibrate the variance of individual stochastic model runs, which will be explored in more detail in a future workshop.
The workshop will be run by a combination of members of the Centre for Mathematical Modelling of Infectious Diseases at the London School of Hygiene & Tropical Medicine, and external speakers from Durham University and the University of Exeter. It will consist of hands-on, practical tutorials, interspersed with short presentations.
The workshop will be suitable for anyone with a basic knowledge of mathematical modelling and R.
Tutors
Tutors at the workshop will include:
Travel bursaries
We have a small number of travel bursaries available for UK-based students to attend the course. Please indicate on the registration form if you would like to be considered for a bursary.
Programme
- 10.30: Welcome (coffee and tea)
- 11.00: Introduction to History Matching with Emulation
- 12.00: Lunch break
- 13.00: Guided R-practical on the calibration of deterministic models (part 1)
- 14.30: Coffee and tea break
- 15.00: Guided R-practical on the calibration of deterministic models (part 2)
- 16.30: Brief discussion on the calibration of stochastic models
- 17.00: Closing
Admission
Contact
