Postdoctoral Scholar Position in Bayesian Models of Human Forecasting Judgments

No replies
Guest

A postdoctoral position is available within the Department of Cognitive
Sciences at the University of California, Irvine to develop Bayesian
models for the aggregation of human forecasts. Forecasts will involve
unconditional probability estimates (e.g. “What is the probability that
event X will happen before date Z?”), conditional probability estimates
(e.g. “What is the probability that event X will happen if Y happens?”)
as well as magnitude estimates (“How large will X be at date Z?”) from a
large group of human forecasters.

One goal in this research project is to develop Bayesian cognitive
models that can measure individual differences in skill and expertise
and correct for systematic errors and biases in human judgment. The
second goal is to build aggregation models that can combine the
estimates from multiple individuals while taking into account cognitive
errors and individual differences. The project is part of a forecasting
tournament organized by IARPA. In this tournament, multiple teams are
developing elicitation and aggregation methods to forecast events on the
basis of human judgments. Teams are evaluated on the forecasting
accuracy of a common set of questions.

The applicant will work in the Memory and Decision-Making Laboratory
(“Madlab”) at the University of California, Irvine, and will primarily
interact with Professor Mark Steyvers. In addition, there is the
possibility of interacting and collaborating with Professor Michael Lee
and other team members at six other universities who are part of the
project.

Requirements: The applicant must have a Ph.D. degree in Cognitive
Sciences, Computer Science, Statistics, Decision Sciences, Engineering,
or related field and have expertise in computational modeling using
probabilistic approaches. The applicant must have excellent computer
skills in Matlab or R programming. Experience with probabilistic
graphical models, Bayesian networks, and Markov chain Monte Carlo (MCMC)
techniques is preferable. The applicant is expected to play to a key
role in the development of journal and conference publications.

Salary is commensurate with experience. The appointment can start as
early as 9/23/2012, but we will consider candidates who can start at a
later date.

Application procedure – Please send a letter of application, curriculum
vitae, and the names of three references to:

Professor Mark Steyvers
Department of Cognitive Sciences
University of California, Irvine
Irvine, CA 92697-5100
mark.steyvers@uci.edu

The University of California, Irvine is an equal opportunity employer
committed to excellence through diversity.

--


Mark Steyvers
Department of Cognitive Sciences
University of California, Irvine
2316 Social & Behavioral Sciences Gateway Building
Irvine, CA 92697-5100
(949) 824-7642 Phone
(949) 824-2307 Fax
mark.steyvers@uci.edu
http://psiexp.ss.uci.edu/research

************************************************************************
ISBA now maintains the bayes-news and Valencia email lists; you are
receiving this message as you have opted-in to receive email from
bayes-news, the Valencia list or the ISBA forums. To opt out or change
your email subscriptions please login at http://bayesian.org/user. Go
to the My Account menu and select Forum Email Integration. Check the
forums to which you wish to subscribe, then save your settings. You
may view past and present content at any time by visiting
http://bayesian.org/forum