BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Causal Inference from 2-level factorial designs -
Dasgupta\, T (Harvard)
DTSTART;TZID=Europe/London:20110830T143000
DTEND;TZID=Europe/London:20110830T150000
UID:TALK32561AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/32561
DESCRIPTION:A framework for causal inference from two-level fa
ctorial and fractional factorial designs with part
icular sensitivity to applications to social\, beh
avioral and biomedical sciences is proposed. The f
ramework utilizes the concept of potential outcome
s that lies at the center stage of causal inferenc
e and extends Neyman's repeated sampling approach
for estimation of causal effects and randomization
tests based on Fisher's sharp null hypothesis to
the case of 2-level factorial experiments. The fra
mework allows for statistical inference from a fin
ite population\, permits definition and estimation
of parameters other than "average factorial effec
ts" and leads to more flexible inference procedure
s than those based on ordinary least squares estim
ation from a linear model. It also ensures validit
y of statistical inference when the investigation
becomes an observational study in lieu of a random
ized factorial experiment due to randomization res
trictions.\n\n\n
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR