BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260415T193420EDT-8880vUxa7U@132.216.98.100
DTSTAMP:20260415T233420Z
DESCRIPTION:Title: Model-assisted analyses of cluster-randomized experiment
 s\n\nAbstract:\n\nCluster-randomized experiments are widely used due to th
 eir logistical convenience and policy relevance. To analyze them properly\
 , we must address the fact that the treatment is assigned at the cluster l
 evel instead of the individual level. Standard analytic strategies are reg
 ressions based on individual data\, cluster averages\, and cluster totals\
 , which differ when the cluster sizes vary. These methods are often motiva
 ted by models with strong and unverifiable assumptions\, and the choice am
 ong them can be subjective. Without any outcome modeling assumption\, we e
 valuate these regression estimators and the associated robust standard err
 ors from a design-based perspective where only the treatment assignment it
 self is random and controlled by the experimenter. We demonstrate that reg
 ression based on cluster averages targets a weighted average treatment eff
 ect\, regression based on individual data is suboptimal in terms of effici
 ency\, and regression based on cluster totals is consistent and more effic
 ient with a large number of clusters. We highlight the critical role of co
 variates in improving estimation efficiency\, and illustrate the efficienc
 y gain via both simulation studies and data analysis. Moreover\, we show t
 hat the robust standard errors are convenient approximations to the true a
 symptotic standard errors under the design-based perspective. Our theory h
 olds even when the outcome models are misspecified\, so it is model-assist
 ed rather than model-based. We also extend the theory to a wider class of 
 weighted average treatment effects.\n\n\n	Speaker\n\n\nPeng Ding is an Asso
 ciate Professor in the Department of Statistics\, UC Berkeley. He obtained
  my Ph.D. from the Department of Statistics\, Harvard University in May 20
 15\, and worked as a postdoctoral researcher in the Department of Epidemio
 logy\, Harvard T. H. Chan School of Public Health until December 2015. Pre
 viously\, he received his B.S. (Mathematics)\, B.A. (Economics)\, and M.S.
  (Statistics) from Peking University.\n\nhttps://mcgill.zoom.us/j/83436686
 293?pwd=b0RmWmlXRXE3OWR6NlNIcWF5d0dJQT09\n\nMeeting ID: 834 3668 6293\n\nP
 asscode: 12345\n\n\n	\n		 \n			 \n		\n	\n\n
DTSTART:20211022T193000Z
DTEND:20211022T203000Z
SUMMARY:Peng Ding (UC Berkeley)
URL:https://www.mcgill.ca/mathstat/channels/event/peng-ding-uc-berkeley-334
 313
END:VEVENT
END:VCALENDAR