BEGIN:VCALENDAR
VERSION:2.0
PRODID:talks.ox.ac.uk
BEGIN:VEVENT
SUMMARY:Posterior Effects in Linear Random Coefficients Models  - Christop
 he Gaillac (University of Oxford)
DTSTART;VALUE=DATE-TIME:20231020T141500
DTEND;VALUE=DATE-TIME:20231020T153000
UID:https://new.talks.ox.ac.uk/talks/id/94a1149b-c33f-4dc4-a49a-6e0257b49c
 92/
DESCRIPTION:Accurately measuring heterogeneous effects is key to improving
  public policy design. We focus on predicting individual heterogeneity in 
 linear random coefficients models\, conditional on the sample. One applica
 tion is estimating how sensitive each teacher's value-added is to their kn
 owledge of the program\, conditional on the latter and their students' tes
 t scores. We establish two new characterizations of these posterior effect
 s\, depending on whether the covariates are continuous or discrete. The fi
 rst expresses these effects directly as a function of the data. Our associ
 ated series estimator is minimax adaptive\, with various alternatives prov
 iding some robustness to the baseline assumptions. The second formulation 
 characterizes the distribution of the random coefficients in terms of mini
 mum distance\, which is then used to compute the posterior. The associated
  estimator is consistent and implementable using optimal transport. Our me
 thods reveal highly heterogeneous effects\, identify the teachers most lik
 ely to benefit from training\, thus providing tools to make personal devel
 opment more cost-effective. \nSpeakers:\nChristophe Gaillac (University of
  Oxford)
LOCATION:Manor Road Building (Seminar Room A or https://zoom.us/j/93054414
 699?pwd=NEFiL2ZNc0t5N3ZIUTE2VEh5OXhZUT09)\, Manor Road OX1 3UQ
TZID:Europe/London
URL:https://new.talks.ox.ac.uk/talks/id/94a1149b-c33f-4dc4-a49a-6e0257b49c
 92/
BEGIN:VALARM
ACTION:display
DESCRIPTION:Talk:Posterior Effects in Linear Random Coefficients Models  -
  Christophe Gaillac (University of Oxford)
TRIGGER:-PT1H
END:VALARM
END:VEVENT
END:VCALENDAR