Stats 100B
Prof. Robert Gould

Project

As part of your final exam, you're required to turn in a written project.  This page will contain information about this project.  Keep checking it when you have questions about the project, because I'll add information as we create it.

Simply put, the project is as follows:
Analyze a data set.

You should not become frightened or intimidated by this project.  I hope you will have fun with it!

Timeline:

Task Due Date
Proposal Friday, April 23 (Week 3) 
Exploratory Analysis Monday, May 17  (Begin of Week 7)
Formal Analysis  Friday, May 28 (End of Week 8)
Written Report Monday, May 7 (Begin of Week 10)

The exact shape of the report will become clear as the quarter progresses, but right now you should plan on a 5 page paper, in addition to supporting graphics.

Proposal
This may be the hardest part!  You need to find a data set that you wish to analyze.  What to look for?  Find a field or topic that interests you.  Once you find a data set, identify one (maybe two) main "research questions" that you wish to answer.  Your analysis should be done with the intent of answering this question.  The goal is NOT to repeat an analysis already published, or even to confirm a published result.  (You might actually reach the opposite conclusion!)  Your aim is to demonstrate your understanding of the analytic tools we've discussed in class.

Your proposal should include:  A description of the data set, and the research problem.  I also  need to know where you got the data from.  I STRONGLY advise that you meet with me BEFORE April 23 to discuss the suitability of your data.  It's easy to choose a project that is too difficult to complete in one quarter.

You can also consider collecting your own data, but again I would strongly caution you to see me first. This can be a project in and of itself.

Exploratory Analysis
This will be a short (at most two page) description of your data, including graphical and numerical summaries.

Formal Analysis
This will be a discussion of the statistical models or procedures you used to determine statistical significance.

Written Report
We will discuss the outline for this in more detail later.  But it will include the three parts above, and also your interpretation of the results.
 

Looking for Data?  Try here first.