##### Sections
You are here: Home Statistics Lecture with Adrian Raftery at Trinity College

# Statistics Lecture with Adrian Raftery at Trinity College

Adrian Raftery, one of the most highly cited mathematicians in the world, will be speaking to the Trinity College student maths society, Mathsoc, in October.
What Location: Dublin Adult Groups Oct 10, 2013 from 07:30 PM to 09:30 PM Trinity College Dublin vCal iCal

Adrian Raftery is one of the most renowned statisticians in the world, having developed new statistical methods for social and health sciences, as well as advancing a number of new modeling methods for use in a variety of systems. This Irish mathematician is a perfect representative for Maths Week Ireland during the International Year of Statistics, so we would urge you all to get out to hear this remarkable thinker.

Here is the abstract for his talk:

"Probabilistic weather forecasting consists of finding a joint probability distribution for future weather quantities or events. Information about the uncertainty of weather forecasts can be important for decision-makers as well as the public, but currently is routinely provided only for the probability of precipitation, and not for other weather quantities such as temperature, wind or amount of precipitation. It is typically done using a numerical weather prediction model, perturbing the inputs to the model (initial conditions, physics parameters) in various ways, and running the model for each perturbed set of inputs. The result is viewed as an ensemble of forecasts, taken to be a sample from the joint probability distribution of the future weather quantities of interest. The results are often uncalibrated, however.

I will review a principled statistical method for postprocessing ensembles based on Bayesian Model Averaging (BMA), that models the predictive distribution conditionally on the ensemble by a finite mixture model. I will describe applications to precipitation, wind speeds, wind directions, visibility and winter road maintenance, a multivariate decision problem. For probabilistic forecasting of an entire weather field, I describe a spatial extension of the BMA method that perturbs the outputs from the numerical weather prediction model rather than the inputs. Forecasts are available in real time at
www.probcast.washington.edu, and the R packages ensembleBMA and ProbForecastGOP are available to implement the methods."

Filed under: