This project is funded by the UK Natural Environment Research Council. It is buying out some of my time to be seconded to the Department of Meteorology, at the University of Reading, and join Professor Ted Shepherd’s group.
The recent COP26 marked a notable shift in the level of public and private-sector attention being paid to climate change, and a corresponding shift from a focus on policy-making (which is left to the policy-makers) to a focus on action across a variety of public and private sectors. This has highlighted the need for casting climate information within a very diverse decision-making space.
One impediment to doing so is that climate change scientists are still overwhelmingly stuck within the paradigm of frequentist statistical practice (Shepherd, 2021). Incorporating physical reasoning (so important to climate change science) within statistical practice and decision making can be accomplished by making prior assumptions, data choices and contrasting models explicit, by using the Bayesian framework. A similar resistance to Bayesian approaches exists within psychology and neuroscience, which are anchored on versions of the frequentist General Lineal Model framework. Arguably, from this inferential blind side stems a big part of the so-called “reproducibility crisis”.
By establishing bridges between climate change science and psychology, we aim to formulate a motivated argument for a shared practice, built from the critical comparative analysis of both frequentist and Bayesian frameworks, in psychology and in climate-change science.
- Shepherd, T. G. (2021). Bringing physical reasoning into statistical practice in climate-change science. Climatic Change, 169(1), 2. https://doi.org/10/gncq98.