Thursday, 28 May 2015

Beta unblockers

A couple of weeks ago, we've uploaded the new version of BCEA on CRAN, to include the function implementing our method for the computation of the EVPPI based on INLA-SPDE $-$ I've also already mentioned this here.

While this is a stable version, we are still continuously testing many of the functions and so I thought I'd keep a beta version on the BCEA website (I've uploaded both a .tar.gz and a .zip file). I will continue to modify this beta version in the next few months, including minor changes/improvements $-$ I don't think these will really affect the basic use of BCEA, but may be relevant in terms of advanced users, for example for customisation of the graphs.

So, BCEA users out there: do tell us what you really, really want $-$ we may even try and implement it for you...

Thursday, 21 May 2015

Bayes 2015

This week I'm in Basel for Bayes 2015. As usual lots of interesting talks and a very healthy mix of perspectives $-$ if perhaps a bit less so than usual in terms of topics. I like this conference as it's always very helpful to get interesting ideas $-$ often people do work in areas that are mostly unrelated with what I am working on, but there are commonalities and ideas for potential collaborations.

In keeping with last year's theme (when we tried hard to find Bayes' tomb in Bunhill Fields), almost by chance I stumbled on Jacob Bernoulli's tomb, yesterday during the city tour.

We had already decided that next year's conference will be in Leuven (but the news is now the social even has been also decided: a beer sampling tour) and we've also "volunteered" Virgilio to have the 2017 edition in Castilla-La Mancha $-$ I guess we'll need to find an angle to prove that Don Quixote was a Bayesian... 

Monday, 18 May 2015

That time of the year...

Slightly later than last year, but, like every year, that time is coming. Yes: Eurovision again. From our point of view, it's of course being a lot quieter than last year, although the paper is still going strong. 

But we've had two nice surprises: first we've been asked to give a radio interview on Australian radio. Why on earth, do you say? I'm glad you asked! Well, apparently, Australians looove the ESC $-$ just to give you an idea, I think the radio programme is usually focussed on serious elections, but this week they dedicated the whole show to the ESC! 

Since this is the 60th edition, Australia have been invited to participate. So they'll feature later this week in Vienna and the people at Radio Adelaide have asked me to discuss our results (the podcast for the full programme is here $-$ I'm on at around minute 15:00). If you get over how nasal my voice sounds and keep listening, you will also learn that the University of Melbourne has also recently activate a module on Eurovision! May be we have a career lined up...

The second interesting news is that we've been contacted by Taylor and Francis (the publisher of the Journal of Applied Statistics). They have had this amazing idea to promote the paper by turning it into a cartoon $-$ here's a draft version (I think that the final one will be out shortly).



I think this is a super-cool idea $-$ it's nerdy-fun and conveys the sense of the paper in a very clear way. Also, I really like the sketch of me!

Wednesday, 13 May 2015

Webinar

Yesterday, I have given a webinar (is it even how you say it? "give a webinar"? Anyway...). It was organised by Mapi and I spoke about using the analysis of the value of information in health economic evaluation. The link to the complete webinar is here.

ICTM Conference

I've been asked to advertise the upcoming International Clinical Trial Methodology conference $-$ this year it will be held in Glasgow. Oddly enough, this will be the second time in a row that the conference is held in Scotland (the 2nd edition was in Edinburgh, two years ago).

I have enjoyed both past editions (the first one in Bristol in 2011), so I think I'll try and go to this one too.  

Saturday, 2 May 2015

SPDEVPPI (2)

Following up on our paper, which I've mentioned in the previous post, we've also updated our BCEA package to implement our SPDE-INLA method for the computation of the EVPPI. This is currently a very advanced beta version (available for download here or here) $-$ we have done quite a few tests and all seems to work OK. 

We are also working on writing a more detailed and user-friendly guide to the function implementing the EVPPI, which should make it easier to replicate the examples and actually work on more applied cases.

Saturday, 25 April 2015

SPDEVPPI

We've just arxived our paper on efficient computation for the Expected Value of Partial Perfect Information (EVPPI) based on SPDE-INLA. The EVPPI is a decision-theoretic measure of the impact of uncertainty in some of the parameters in a model on the final decision, informed by current evidence. Basically, it measures how much one should be willing to pay to gather new information to reduce uncertainty in the future outcomes. As such, it can be used to prioritise research and thus has been advocated as a very useful tool in health economic evaluation. Trouble is that it can be very difficult (or even impossible) to compute analytically and even a simulation approach may require an impracticable number of simulations.

The paper is part of Anna's PhD and in it we draw heavily on previous work on Gaussian Process (GP) regression to compute the EVPPI done by Mark Strong and colleagues at Sheffield. Our main idea is to express the GP regression model for the estimation of the EVPPI using a "fictional" spatial problem. As we show in the paper, this allows us to make use of clever models which simplify the computations and we can use INLA to obtain the results in a super-fast way.

As we show in the paper, our method can compute the EVPPI in a matter of seconds and this is virtually irrespective of the number of parameters involved. More importantly, there's a very large reduction in the computational time, in comparison to other non-parametric methods. Also, the accuracy of the estimation is very good.

We're implementing this into the next release of BCEA, which we plan on having ready in a matter of a few weeks!

Monday, 20 April 2015

There's no I in Mutual

Today I've received an email from a prospective PhD candidate, who says that he (or she) would like to do his (or her) PhD under my supervision on a topic of mutual interest. Except his (or her) interests are in Physics or Applied Mathematics.

I know I'm being a bit mean here and that there's no reason why physicists or mathematicians can't work on Bayesian statistics. But this person actually goes on to state that their expertise is in Rheology and Dynamics of Complex Fluids e.g. particle suspension, droplet and polymer suspension and various other multiphase flows. That I find it a bit more complex to qualify as a set of mutual interests (to mine!)...