STAT 503X Assignment 3 Email and SPAM

STAT 503X Assignment 3
Email and SPAM
Due: in class Mar 28, 2003
This assignment requires you to construct a report on the classcollected spam data. The major question you need to address is:
Which indicators can be used to classify email as spam or not
And then secondly, you need to write down two additional questions
that might be addressed by this data. These questions should be
done ahead of any analysis of the data.
The data is available on the public class web page:∼dicook/stat503/spam.html
in excel, tab-delimited text, and comma-delimited text formats.
You will need to present your results in tabular and graphical
form, and concisely summarize the major findings, following the case
study formats used in the class. The grade for the assignment will
depend on neatness of the report, how comprehensive is the analysis
(are your questions answered), clarity of results presentation, and
preciseness of final conclusions.
The page limit for the report is 7 pages, reasonably large type,
and an appendix containing supporting material, additional results,
and code for the analysis.