We return to another case study from the short course Simulation-Based Inference for Epidemiological Dynamics (SBIED). Chapter 18 is Lesson 7 of SBIED. We will focus on two new topics arising in the case study:
Non-likelihood model criticism. So far, we have emphasized likelihood-based tools both for model fitting and diagnostic criticism. Here, we consider other statistics.
Forecasts using POMP models can combine uncertainty due to stochasticity in the latent process, the measurement noise, and unknown parameters. We see how this plays out in an example.
Slides | |
Annotated slides | |
Notes | |
R script | R |
Recording, Chapter 18 | (40 min) |
Model construction and analysis script | R |
Supplement: constructing the Ebola models | HTML |
Back to course homepage
Acknowledgements
Source code
for these notes