BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251028T134033EDT-1582Tivne3@132.216.98.100
DTSTAMP:20251028T174033Z
DESCRIPTION:'Efficient Learning under Ambiguous Information'\n\nMira Frick 
 (Yale)\n	(with Ryota Iijima and Yuhta Ishii)\n  	November 11\, 2022\, 3:30 t
 o 5:00 PM\n	Leacock 429\n\nHost: Larry Epstein\n	Field: Theory\n\nAbstract:
 \n	We provide a systematic approach to compare different belief-updating ru
 les under ambiguity\, based on analyzing their performance in learning set
 tings. We consider a decision-maker (DM) with maxmin expected utility pref
 erences who observes many signals about an unknown state of the world\, an
 d then solves a decision problem based on her updated beliefs. Capturing s
 ignal ambiguity\, the DM perceives a set of possible signal structures. A 
 belief-updating rule maps sequences of signals to sets of posteriors about
  the state\, and the DM chooses optimally based on her worst-case posterio
 r. We measure the learning efficiency of each updating rule by considering
  the DM’s induced worst-case expected payoff\, evaluated from an ex-ante p
 erspective. Thus\, updating rules with higher learning efficiency can be v
 iewed as displaying less dynamic inconsistency. We provide a simple charac
 terization of the learning efficiency of each updating rule. This has the 
 following main implications. First\, in stationary environments (i.e.\, wh
 en signal draws are conditionally i.i.d.)\, we show that learning efficien
 cy is maximal if (and\, in a sense\, only if) the DM uses maximum-likeliho
 od updating\; in contrast\, the widely used full-Bayesian updating rule is
  generically (potentially highly) inefficient. Second\, in non-stationary 
 environments (i.e.\, when signal structures can vary over time)\, we show 
 that learning efficiency is maximal if (and\, in a sense\, only if) the DM
  uses a maximumlikelihood updating rule that (mis)perceives the environmen
 t to be stationary.\n
DTSTART:20221111T203000Z
DTEND:20221111T220000Z
LOCATION:Room 429\, Leacock Building\, CA\, QC\, Montreal\, H3A 2T7\, 855 r
 ue Sherbrooke Ouest
SUMMARY:Mira Frick (Yale)\, 'Efficient Learning under Ambiguous Information
 ' 
URL:/economics/channels/event/mira-frick-yale-efficien
 t-learning-under-ambiguous-information-340868
END:VEVENT
END:VCALENDAR