Sept 13, 2016

Who I am

  • Neuroscience Researcher @UMich
  • Study brain connectivity & psychiatric disorders
  • twitter: @dankessler
  • web: www.dankessler.me
  • I use R for data wrangling and behavioral/fancier analyses (e.g. mixed effects)
  • New to Stan and Police Shooting data

Who I am not

  • Sociologist/Demographer
  • Expert on Stan
  • Well-trained Bayesian statistician
  • Person of Color
  • Police Officer

Acknowledgements

  • Mike Angstadt
  • Chandra Sripada
  • Kerby Shedden
  • Cody Ross
  • AARUG & Ann Arbor ASA
  • SPARK

What to Expect

  • Review Cody Ross's Method & Finding
  • Introduce Stan
  • Anatomy of a Stan program
  • Alternative Model for Police Shootings
  • Our very tentative results

Background

The Problem

The US has recently witnessed a number of high-profile deaths of African-Americans at the hands of police.



There is a pressing need to study this phenomenon quantitatively. Why?

  • Case reports are insufficient and could even be misleading
  • Better understand the causes
  • Help shape solutions

An Important Step Forward