BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Comparing factor models with conditioning information - Seok Young
  Hong (Lancaster University Management School) 
DTSTART:20221013T120000Z
DTEND:20221013T130000Z
UID:TALK175169@talks.cam.ac.uk
CONTACT:107888
DESCRIPTION:We develop a framework to conduct asymptotically valid tests f
 or comparing factor models with conditioning information. The tests are ba
 sed on a metric analogous to the squared Sharpe ratio improvement measure 
 that is used to gauge the extent of model mispricing in an unconditional s
 etting. We propose an estimator for the metric and study its limiting prop
 erties in detail\, establishing the asymptotic normality. An advantage of 
 our framework is that it can be applied without an a priori knowledge of t
 he persistence nature of the conditioning variables. We accommodate a rang
 e of dependence classes\, including stationary\, near stationarity\, integ
 rated\, and local-to-unity. An application of our methodology to major mod
 els shows that the conditional versions of the Stambaugh and Yuan (2017) f
 our-factor model and the Daniel\, Hirshleifer\, and Sun (2020) three-facto
 r model are the best performers.
LOCATION:CJBS\, Fadi Boustany LT 
END:VEVENT
END:VCALENDAR