Wake me up, when September ends...
In the past few years, the month of September has become really busy for me.
The RSS conference usually happens in the first week of the month and I have happened to go quite often, recently — last year, I gave a talk on our missing data in health economics work (which Andrea is about to complete, at least in terms of his PhD…). This year (in fact, on Thursday, this week), I’m going again — this time to Cardiff, where I’ve been invited to talk about my work on elections forecast (some examples of which are here, here or here). I’ll be talking about the model I did for the 2017 UK General Election — I think it’ll be interesting, because while I’m interested in politics, in general, I’m not really a professional psephologist, while the session will probably feature some people whose main interest is not so much in the modelling, as in the political science implications of it… I’m curious to see how it goes!
After the RSS, I will give a few more presentations in the next few weeks.
Title: Quick & clean: computationally efficient methods for Value of Information measures
Abstract: Recently, there has been much research devoted to developing computationally efficient methods for various measures of the Value of Information in health economics, including the Expected Value of Partial Information (EVPPI) and the Expected Value of Sample Information (EVSI). I will present two sets of methods, one based on computationally efficient Gaussian Process regression based on Integrated Nested Laplace Approximation to compute the EVPPI and the other based on “moment-matching” to compute the EVSI. Both methods draw on existing methodologies but expand them by providing general-purpose algorithms that can be applied on a wide range of real-life modelling structures. I will present the methods using toy and real-life examples and discuss their advantages and limitations with respect to applicability in practice.
Then, I’ll be teaching on the UCL course on missing data in health economics — again related to Andrea’s work. My talk is on the last day of the course (21st) — I am not sure whether there are still places on the course, but I enjoyed giving my session last year, so hopefully there’ll be more fun!
Finally, I’ll be in beautiful Leuven to teach on the Summer School on Advanced Bayesian Methods. My two-days will be, you guessed it, on Bayesian methods in health economics — I think I’ll go through some of the more basic aspects and then perhaps extend to some interest applications (e.g. in survival analysis or missing data).
All this before the ISPOR in Barcelona in November — where I’ll speak at a couple of sessions. But more on this later — after September has ended…