Upcoming events with Professor Matt Wand – May 10-17

Please sign up at this link and join Matt as many times as you wish during his visit May 10 – May 17!

(meetings can be over coffee, a walk, in his temporary visiting office in the Department, etc.)

Everyone is welcome to join in on any activity/meeting during Professor Wand’s visit to the Department!

Matt Wand Professor Matt Wand, Distinguished Professor of Statistics in the  Statistics and Data Science Group at the University of Technology Sydney, Australia, will be visiting the Department of Biostatistics from May 6 through May 17 (inclusive) as part of a  6-month sabbatical.  Dr. Wand was an Associate Professor of Biostatistics in the Department from 1997-2002.  He will be delivering a short course on variational approximations to  members of the Cai Lab and a seminar within the Harvard Data Science Initiative and will also offer a colloquium talk in the Department of Biostatistics on mixed models (see below).  More about Professor Wand can be found here.


Professor Wand is looking forward to catching up with old colleagues, former students and postdocs, as well as meeting as many new faces as he can while here.  He will be available for 1-1 meetings and visits, group lunches and even frisbee, between Friday May 10 and Friday May 17, for anyone in the broader Department community who would like to join him (approximate schedule/signup).

Department of Biostatistics Colloquium Talk:

Thursday, May 16 from 4-5pm, with happy hour to follow.


Matt Wand, University of Technology Sydney, Australia

Generalized linear mixed models were born in the early 1990s as the love child of linear mixed models (1950s) and generalized linear models (1970s). Now, in the 2020s, every day ends with the publication of around 3-4 new papers on the topic. Despite their ever-increasing ubiquity, there has been very little in the way of asymptotic theory for the maximum likelihood estimators of generalized linear mixed model parameters. Apart from simple conveyance of estimator behavior, there are the usual payoffs concerning statistical inference, sample size calculations and optimal design. This talk will describe new results concerning the generalized linear mixed model leading terms, and is joint with Jiming Jiang, Aishwarya Bhaskaran and Luca Maestrini. Ramifications concerning variational approximation will also be mentioned.