糖心TV Complexity Science Events
Complexity Centre and MathSys CDT events carry priority over room D1.07.
To book D1.07 please email Sheetal dot Sharma at warwick dot ac dot uk
Please note that your event booking is for D1.07 only. The adjacent common room is a private area for the MathSys Centre that cannot used as part of your booking.
Complexity Forum: Nicholas Watkins
Speaker: Nicholas Watkins (British Antarctic Survey)
Title: When is a power law not a power law-and why do we care?
Abstract:
The discovery of the Gaussian distribution, its subsequent mathematical explanation via the central limit theorem, and its physical embodiment in equilibrium statistical mechanics, changed both theoretical and applied science in a very fundamental way. Not all naturally occurring variables are Gaussian, however, and in particular many follow heavy-tailed distributions such as power laws. There is no analogous single limit theorem that explains them all, although partial explanations such as first-passage times or preferential attachment are well established. More remains to be done and much effort is currently going into new, rich models and paradigms for the observations, and into better statistical inference. I will briefly introduce the above topic as a framework in which to review work over the last 4 years in BAS's Natural Complexity project, where apparent heavy tails have sometimes been explained by modifying methods like first passage (space physics) or preferential attachment (biological networks); sometimes by newer paradigms like superstatistics (ionospheric radar data); and, occasionally, as being something quite other than a power law (the foraging of the wandering albatross). I will also speak about the corresponding problem of long-ranged temporal correlation and the student project(s) we are offerring in this area.