BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Seminar,Class/ Workshop
DESCRIPTION:Gonzalo Vazqauez-Bare - University of Michigan\n\nIdentificatio
n and Estimation of Spillover Effects in Randomized Experiments\n\nAbstract
: This paper employs a nonparametric potential outcomes framework to study
causal spillover effects in a setting where units are clustered and their p
otential outcomes can depend on the treatment assignment of all the units w
ithin a cluster. Using this framework\, I define parameters of interest and
provide conditions under which direct and spillover effects can be identif
ied when a treatment is randomly assigned. In addition\, I characterize and
discuss the causal interpretation of the estimands that are recovered by t
wo popular estimation approaches in empirical work: a regression of an outc
ome on a treatment indicator (difference in means) and a regression of an o
utcome on a treatment indicator and the proportion of treated peers (a redu
ced-form linear-in-means model). It is shown that consistency and asymptoti
c normality of the nonparametric spillover effects estimators require a pre
cise relationship between the number of parameters\, the total sample size
and the probability distribution of the treatment assignments\, which has i
mportant implications for the design of experiments. The findings are illu
strated with data from a conditional cash transfer pilot study and with sim
ulations. The wild bootstrap is shown to be consistent\, and simulation evi
dence suggests a better performance compared to the Gaussian approximation
when groups are moderately large relative to the sample size.
DTEND:20180130T181000Z
DTSTAMP:20181219T032613Z
DTSTART:20180130T164000Z
GEO:42.447319;-76.480995
LOCATION:Ives Hall\, 111
SEQUENCE:0
SUMMARY:Junior Recruitment Workshop: Gonzalo Vazqauez-Bare
UID:tag:localist.com\,2008:EventInstance_3267942
URL:http://events.cornell.edu/event/junior_recruitment_workshop_gonzalo_vaz
qauez-bare
END:VEVENT
END:VCALENDAR