Sunday, June 07, 2020

Six of the best books to help understand Covid-19 data

Hannah Fry is an Associate Professor in the Mathematics of Cities at the Centre for Advanced Spatial Analysis at University College London. She works alongside a unique mix of physicists, mathematicians, computer scientists, architects and geographers to study the patterns in human behaviour - particularly in an urban setting. Her research applies to a wide range of social problems and questions, from shopping and transport to urban crime, riots and terrorism.

Her latest book is Hello World: Being Human in the Age of Algorithms.

At the Guardian, Fry tagged the best books to help you understand numbers and help demystify Covid-19 data. One title on the list:

It’s hard to imagine a moment in history more driven by numbers. Suddenly we’re all poring over reams of data, while debates over the merits of mathematical models are front page news. But while some are flexing new-found expertise in logarithmic axes and inflection points, those of us who have been in the game a bit longer flinch at this new epidemic of brash certainty. We know the traps that are easy to fall into when you let numbers be your guide.

One graph that made me roll my eyes compared per capita death rates for the UK, the EU, China and the US. (Why lump all EU countries together? Are comparisons between the UK and China, with 20 times its population, useful?) This is an old trick – divide anything by hundreds of millions and it’s going to skew the picture, but anyone who has read Darrell Huff’s 1954 classic, How to Lie With Statistics, will know to be wary of statistical sleight of hand.

Read about another entry on the list.

--Marshal Zeringue