To discuss: the pointlessness of behavioural economics as modified classical economics, when large data applications make this a predictive science
Is there a behavioral stochastic process peculiar to human behaviour? If so, what does it look like mathematically? So far, the Brownian motion or Levy process paradigm has been used to describe aspects of behavioral stochastic processes. How can we embed behavioural parameters in stochastic processes? (flakey link)
A population of mis-specfied Bayesian learners? A bunch of partially informed voters? Distributed learners?
Things to think about here: Bounded rationality, rational inattention, institutions as stable orbits in behavioural systems, devious negotation strategies …
A fecund sub-field. See the risk perception page.
- Shalizi, C. R.(2009) Dynamics of Bayesian updating with dependent data and misspecified models. Electronic Journal of Statistics, 3, 1039–1074. DOI.