Bayesian Inference - Fall 2009 - Final exam

The final exam will be a team project on a topic selected by the team. The topic can either be a Bayesian analysis of an important and challenging data set or methodological work on topic of interest to Bayesians, perhaps a simulation study comparing several methods. The projects are to be done in groups of 1-2 chosen by the instructor (with student input). They are to result in thorough but concise, professional quality technical reports of not more than 10 (8 for students working individually) double-spaced pages (not including the raw data, computer outputs and R or WinBUGS codes) followed by a 15 minute seminar style presentation.

Project abstract due: November 9

One-page proposals are due in class by the deadline stated above. These proposals should list your team members and spell out briefly the main goal of the study, your basic approach, and the role of each team member. Also include the day(s) your group prefers to present the project (11/30, 12/2, 12/4, or 12/16). Pick a subject that interests you (preferable on a topic of your future/current dissertation)! IMPORTANT: The problem you choose should not be something that you have already done! For example, if you have already taken the written prelim exam, you should not use the same topic here; you should identify a completely new problem. Similarly, if you are carrying out simulations as part of your dissertation research already, you should not use this as the basis for your project. Some part of your instructor's reaction to your project will also inevitably reflect the originality of your topic, so choose it with some care. This project need not be computationally expensive nor require a huge time investment in data collection. But it does need to show careful planning, good logic and the Bayesian analysis concepts discussed in the course. If you are having trouble identifying a topic, please see the instructor as soon as possible.

Final report due November 30

After experimenting make a thorough but concise report of your entire investigation. Include at least: Simply attaching a ream of computer printout is not what is meant by ``major findings''. The main body of the report should include only the end products of any statistical calculations. Write the report as if a busy manager were going to read it. Statistical jargon for the sake of statistical jargon will not be well received.

Grading

Team average scores for these projects will be assigned according to the following schedule: Presentation schedule