The structure of the project should be in the form of an article, and include
the following items:

a title
an abstract
an introduction section
a few sections of main content
a discussion section

Figures and tables should appear in the main body of the article. 

Code should appear in an appendix. 



Project topics can involve data analysis, computation, and/or theory. 
A theory article could take the form of a review of two or three 
articles or book chapters. 

Some suggested project topics include the following:

1. MLEs and Bayesian estimation for data from the matrix normal distribution. 
MLE estimation for the matrix normal distribution can be done with an 
interative procedure. For this project, you will implement this procedure
in R. Also, Bayesian inference for the matrix normal model is very 
straightforward. In this project you will also need to write R code 
to obtain the Bayes estimate, and compare it to the MLE. 

2. Classifier selection using cross-validation: Select a multivariate dataset 
with one categorical variable and at least three continuous variables. 
Using the continuous variables, construct a classifier for the categorical 
data. You will need to decide whether or not to assume a constant variance 
across groups, and also which continuous variables to include in your 
classifier. Make these evaluations using cross-validation. 

3. Variable selection in regression. Select a multivariate dataset 
that has a p-dimensional outcome variable and at least q=3 explanatory 
variables. Perform hypothesis tests to evaluate the effect of each 
of your explanatory variables. Also, perform cross validation to assess
the predictive performance of each explanatory variable. 

4. An analysis of data that are of interest to you, using some of the methods
discussed in class.

5. Bayesian estimation for the multivariate regression model. 

6. Copula modeling 

7. Something else of interest to you, and discussed with me. 


I'll be adding potential topics to this list this week. You are 
encouraged to start thinking about what you would like to do ASAP.