Registration for a live webinar on 'Chronic inflammation, immune cell trafficking and anti-trafficking agents' is now open.See webinar details
Bayesian methods in health economics: formulating input uncertainty 5
A selection of talks on Methods
Artificial intelligence in medicine: history & state of the art
- Prof. John Fox
- University of Oxford, UK
Understanding statistics in epidemics and pandemics: lessons learned from COVID-19
- Prof. Sarah Ransdell
- Nova Southeastern University, USA
International biobanking: overview of key practices and policies
- Dr. Jim Vaught
- Editor in Chief, Biopreservation & Biobanking, USA
Hello, I'm Tony O'Hagan. Welcome to the fifth and last talk in my series, Bayesian Methods in Health Economics. This one is entitled Formulating Input Uncertainty.
Let's just quickly review one more time the outline of the whole course. The first two talks were about Bayesian methods in general, and then the final three have been about the use of Bayesian methods in health economic evaluation. In Part 3, we introduced the ideas of health economic evaluation and issues around uncertainty. We talked a bit about measuring uncertainty when the analysis is of cost-effectiveness data from clinical trials but pointed out that the main way that health economists do evaluations is through economic modelling. The fourth talk introduced economic modelling, and talked about the principles of probabilistic sensitivity analysis and dealt with a large part of how you do that, and this final talk concerns one more issue about probabilistic sensitivity analysis (PSA), which is how do we express the uncertainty on the inputs to the economic model?
This talk is organised as follows: we begin by looking at the general ideas about expressing uncertainty on inputs, and look again at the vaccine example from the previous talk. We then move on to three more technical issues about uncertainty and inputs. The first is data gaps, which is where the information we have doesn't relate quite to the parameter that we want to express uncertainty about for our model. Then we'll go into correlation, where two or more inputs are related to each other, and finally, we'll talk about how we express uncertainty about utilities.