Thursday 06 Oct 2016Statistical Science Seminar: Ensemble averaging and mean squared error

Jonty Rougier - University of Bristol

H103 14:30-16:30


In fields such as climate science, it is common to compile an ensemble

of different simulators for the same underlying process.  It is a

striking observation that the ensemble mean often out-performs at least

half of the ensemble members in mean squared error (measured with

respect to observations).  In fact, as demonstrated in the most recent

IPCC report, the ensemble mean often out-performs all or almost all of

the ensemble members across a range of climate variables.  This paper

shows that these could be mathematical results based on convexity and

averaging, but with implications for the properties of the current

generation of climate simulators.


Add to calendar

Add to calendar (.ics)