BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Theory and applications of proper scoring rules - Philip Dawid (St
 atistical Laboratory)
DTSTART:20130130T163000Z
DTEND:20130130T180000Z
UID:TALK41560@talks.cam.ac.uk
CONTACT:Robin Evans
DESCRIPTION:Proper scoring rules encourage honest assessment of personal p
 robabilities.  They can also be used to define general entropy functions\,
  discrepancy functions\, M-estimators\, etc.\, and to extend composite lik
 elihood methods.\n\nWhen the sample space is a real interval\, a proper sc
 oring rule is termed local (of order m) if it depends only on the first m 
 derivatives of the quoted density at the actually realised value.  We have
  characterised all proper local scoring rules and shown that (excluding th
 e log score) they can be computed without requiring the normalising consta
 nt of the density. This property is valuable for many purposes\, including
  Bayesian model selection with improper priors.\n\nDawid\, A. P. (1994)  P
 roper Measures of Discrepancy Uncertainty and Dependence with Applications
  to Predictive Experimental Design.\n<http://www.ucl.ac.uk/statistics/rese
 arch/pdfs/139b.zip>\n\nParry\, M.\, Dawid\, A. P. and Lauritzen\, S. L. (2
 012). Proper local scoring rules.  Ann. Statist. 40\, 561-92. <http://www.
 statslab.cam.ac.uk/~apd/papers/AOS971>\n\nDawid\, A. P. and Musio\, M. (20
 12). Estimation of spatial processes using local scoring rules.  Advances 
 in Statistical Analysis. doi:10.1007/s10182-012-0191-8
LOCATION:MR5\, CMS
END:VEVENT
END:VCALENDAR