Professor Michael Goldstein

Professor in the Department of Mathematical Sciences

What do you do?

I’m a Bayesian statistician with over 50 years experience of developing foundations, methodology and applications. I have been a Professor of Statistics at Durham since 1990.

How are you involved in this area of science? 

I have over 30 years experience of working on problems of Uncertainty Quantification for complex physical systems, developing, with colleagues in the department, foundations (what do models tell us about the real world?), methodology (history matching and calibration, forecasting and decision making using computer models for the physical systems) and applications (such as natural hazards, climate change, pandemic modelling and energy policy).

What do you love about this topic?

The problems of UQ are pretty universal. Therefore, you work on challenging and very general technical, theoretical and philosophical problems which have immediate real world application across all areas of science.

How does this work deliver real-world impact?

All modelling has a large element of uncertainty - how does the model relate to the real world? What are the appropriate settings of the model parameters? How reliable are the real world data that we use to calibrate our model? How realistic are the effects of interventions in the model? Understanding such uncertainties is essential to the safe and effective use of models in the real world.