Projects

Students will work in pairs to carry out projects involving application of the statistical computing methods covered in the course to problems of their own choosing. I will be happy to work with you at each stage of your project. Examples of possible types of projects are:

• Design and carry out a simulation study to compare the properties of two or more statistical procedures
• Code an MCMC sampler in R and use it to fit a model to a real dataset. Use WinBUGS to fit the same model to the same dataset. Use the R package BOA to analyze the output of both your sampler and WinBUGS. Verify that the results match.
• Learn to use two or more R packages that we have not studied as a class. Apply them to perform useful analyses of a real dataset.
• Choose a research question and find data to address it. Use SAS to "clean" and prepare the data and to carry out an analysis.

Projects will be carried out in three phases. Please meet with me at least once while you are working on each phase.

• Project proposal (due 10/30) This is a detailed description of what you plan to do, including question(s) to be addressed, software to be used, methods to be applied.
• Project interim report (due 11/13) This informal report will indicate that your project is ``on track." All computing should be completed at this point. The interim report will include results obtained thus far and a brief summary (hand-written is O.K.) of what they mean and what remains to be done. In addition, each member of the project team will list which tasks they have performed for the group.
• Project presentation (must be posted or submitted by 12/04)

  The final form of the project must be prepared in L^ATEX. This can be either

  • a paper to be posted on the course web page (send PDF file to me for posting)
  • slides to accompany an oral presentation to the class (use computer and projector in the classroom)
  Presentations will be given in class during the week of 12/04.