Final Exam: The Union Makes Us Strong
36-402, Advanced Data Analysis
Due at 10 am on Monday, 9 May 2011
Instructions
You will be sent a data set (CSV format) by e-mail to your Andrew account.
Each data set is slightly different. Work only with your own. It should have
625 rows and 8 columns. If you have not received a data set, or cannot open
it, or it has the wrong format, contact Prof. Shalizi by 9 am on Wednesday, 27
April. If you do not do so, the presumption will be that you have received and
can read your data.
Your work for this exam will be a formal report. You will be graded equally
on the technical accuracy with which you employ your chosen statistical tools;
the quality of the reasons you give for selecting those tools (and not others) and
for supporting your conclusions; and the skill with which you use words, graphs
and numbers to communicate. Be clear, be concise, and use your own words.
Divide your report into four marked sections: introduction and data sum-
mary; methods; results; conclusions. You may sub-divide these, but you must
have these four sections; they will be weighted equally.
1. Introduction Describe the data and the problem. This can b e brief, but
should be comprehensible to someone who has not read this assignment.
Include any exploratory analyses you do to guide your choice of methods.
2. Methods Describe your methods. Give enough detail that someone who
had taken 401 but not 402 would understand. Explain why your methods
are suitable to the problem — how that statistical analysis answers this
non-statistical question. Be explicit about the assumptions your methods
make about the data-generating process, and how (if at all) the assump-
tions can be checked.
3. Results Give the results of your statistical analysis. As appropriate, in-
clude checks on model assumptions, and on the quality of fits to the data.
Describe the results in words, accompanied by numbers and/or graphs as
needed — raw or minimally edited R output is unacceptable.
4. Conclusions Relate your statistical results to substantive, scientific con-
clusions. Discuss the statistical significance of your results, their scientific
or practical significance, and the uncertainty in your conclusions. As far
1
