Postdoctoral Positions at Columbia and Berkeley: “Practical Tools for Multilevel/Hierarchical Modeling”

Andrew Gelman, Jingchen Liu, and Sophia Rabe-Hesketh are looking for two fulltime postdocs, one to be based at the Department of Statistics, Columbia University, and the other at the Graduate School of Education, University of California, Berkeley.

The positions are funded by a grant entitled “Practical Tools for Multilevel/Hierarchical Modeling in Education” (Institute of Education Sciences, Department of Education). The project addresses modeling and computational issues that stand in the way of fitting larger, more realistic models of variation in social science data, in particular the problem that (restricted) maximum likelihood estimation often yields estimates on the boundary, such as zero variances or perfect correlations. The proposed solution is to specify weakly informative prior distributions – that is, prior distributions that will affect inferences only when the data provide little information about the parameters. Existing software for maximum likelihood estimation can then be modified to perform Bayes posterior modal estimation, and these ideas can also be used in fully Bayesian computation. In either case, the goal is to be able to fit and understand more complex, nuanced models. The postdocs will contribute to all aspects of this research and will implement the methods in C and R (Columbia postdoc) and Stata (Berkeley postdoc).

Both locations are exciting places to work with research groups comprising several faculty, postdocs, and students working on a wide range of interesting applied problems. The Columbia and Berkeley groups will communicate with each other on a regular basis, and there will be annual workshops with outside panels of experts.

Applicants should have a Ph.D. in Statistics or a related area and have strong programming skills, preferably with some experience in C/R/Stata. Experience with Bayesian methods and good knowledge of hierarchical Bayesian and/or “classical” multilevel modeling would be a great advantage.

The expected duration of the positions is 2 years with an approximate start date of September 1, 2010.

Please submit a statement of interest, not exceeding 5 pages, and your CV to either Andrew Gelman and Jingchen Liu ([email protected]) or Sophia Rabe-Hesketh (Graduate School of Education, 3659 Tolman Hall, Berkeley, CA 94720-1670, [email protected]), stating whether you would also be interested in the other position. Applications will be considered as they arrive but should be submitted no later than April 1st.

This is in addition to, but related to, our other postdoctoral positions. A single application will work for all of them.

2 thoughts on “Postdoctoral Positions at Columbia and Berkeley: “Practical Tools for Multilevel/Hierarchical Modeling”

  1. I am in the final year of the PhD at the University of Valencia. My research is focussed on prediction with objective priors using reference analysis.
    I am planning to get the degree at the end of this year.
    I would like to know if there is any option of a postdoctoral position starting after Sept 1st, 2010.
    Regards,
    Lizbeth

Comments are closed.