Poster Project Description - Statistics 514 - Fall 2010
Collect a research-type data set and analyze the data using methods that are covered in
our course. You should plan to use methods from at least two chapters in the text.
Get my approval before conducting your analyses. Your project is due in two parts. The
first two issues listed below must be written up and turned in by Friday, September 17,
while the final poster will be displayed in class near the end of the semester. Your
poster should address the following issues:
- General information about the topic.
- The general hypotheses of interest.
- Specify H0 and Ha for the tests of major interest.
- The goals of the study, i.e., what it would contribute to knowledge in the field. Also,
relate it to other studies already done in the field.
- What data will be used to address these hypotheses, how will the data be collected.
- Describe the analyses that will be conducted.
These first two sections (listed above) are due on Friday, September 17. They
will also appear on the final poster.
- Present the results of the analyses.
- Report information that you have learned about the data from exploratory analyses
(using, for example, Proc Insight). Generate some graphs or plots to describe the data.
- Analyze the data using SAS, or another language if appropriate. Present the main results
from the analyses.
- Discuss the implications of your results for this field, and compare your results to
other published results. (Most of this should follow from your results and the background
information in part 1)
You can use 3' x 4' foldout posterboards for taping sheets of paper.
More details to follow.
During our poster exhibit periods, each student will write comments about
posters. A small part of the project grade for each student will be based on these
evaluations of other posters.
- The first part of the project, the written description for early in the semester, is
informal and just to ensure that you have a viable idea for your poster.
- It is best if you can collect or generate your own data for the project. Data that
you obtain from other people you know is almost as good as data that you collect. If
these two options do not work out, you can obtain data from the web. However,
posters based on data from the web will generally get a (slightly) lower score than
posters based on your own data.