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:Estimating the heterogeneity distribution of willi
ngness-to-pay using individualized choice sets - V
andebroek\, M (KU Leuven)
DTSTART;TZID=Europe/London:20110831T160000
DTEND;TZID=Europe/London:20110831T163000
UID:TALK32591AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/32591
DESCRIPTION:Two prominent approaches exist nowadays for estima
ting the distribution of willingness-to-pay (WTP)
based on choice experiments. One is to work in the
usual preference space in which the random utilit
y model is expressed in terms of partworths. These
partworths or utility coefficients are estimated
together with their distribution. The WTP and the
corresponding heterogeneity distribution of WTP is
derived from these results. The other approach re
formulates the utility in terms of WTP (called WTP
-space) and estimates the WTP and the heterogeneit
y distribution of WTP directly. Though often used\
, working in preference space has severe drawbacks
as it often leads to WTP-distributions with long
flat tails\, infinite moments and therefore many e
xtreme values.\n\nBy moving to WTP-space\, authors
have tried to improve the estimation of WTP and i
ts distribution from a modeling perspective. In th
is paper we will further improve the estimation of
individual level WTP and corresponding heterogene
ity distribution by designing the choice sets more
efficiently. We will generate individual sequenti
al choice designs in WTP space. The use of this se
quential approach is motivated by findings of Yu e
t al. (2011) who show that this approach allows fo
r superior estimation of the utility coefficients
and their distribution. The key feature of this ap
proach is that it uses Bayesian methods to generat
e individually optimized choice sets sequentially
based on prior information of each individual whic
h is further updated after each choice made.\nBase
d on a simulation study in which we compare the ef
ficiency of this sequential design procedure with
several non-sequential choice designs\, we can con
clude that the sequential approach improves the es
timation results substantially.\n\n
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR