STA 210B/ENV 251
Statistics and Data Analysis for the Biological Sciences

Objective
Present useful information obtained by data analysis of a public database. Make presentation accessible to a wide audience, say adults with at least a high school education. HTML format for publication on web is ideal, but paper format is acceptable.

Instructions
Discuss the background of the data source, its origin, purposes and limitations in use, application or generalization.  Use graphics, statistics and text to communicate patterns, sources of variation, and sources of uncertainty. Apply inferential procedures as appropriate. Explain why some inferences may not be appropriate.

Web resources below point to many excellent data sources. Identify one of interest. Your may consider other datasets, if you happen to have access. If you know of other good data sources on the Web, let me know so I can include it in the resource list.

You may work in small groups or alone. Expectations increase with group size.

Prepare background material for the October 8 due date. Include discuss of data source and attributes and variables of interest. Enumerate some important questions that may be illuminated through analysis of this database. Some graphics and summary statistics may be helpful at this stage.

The final stage, due December 11,  is to complete the data analysis. Present and interpret graphics and statistics. Furthermore, apply inferential procedures where they aid in answering study questions. If an inferential procedure in not appraise, do not report it. Rather, explain why the inference would be in appropriate.

For those who wish to publish their project on web, we will set up space in this web site. Know that this can be a valuable contribution to the quality of information in the Internet. No one will be required to post their reports.

Alternatives
If you have other ideas for a project, we may discuss them--the earlier, the better.

Due Dates

October 8

Introduction, data description, some data analysis

December 11

Complete report

Here are some sites we may use in class or may be useful for class projects. Please visit them for project ideas and general awareness. I have found these sites useful in my own research. This list will grow through the semester. Students are encouraged to propose other useful sites.

The Center for Environmental Information and Statistics provides introductory reports on most EPA data sources and reviews data quality.
http://www.epa.gov/ceisweb1/ceishome/digitallib

Right-To-Know Computer Network offers access to many EPA and other public databases.
http://www.rtk.net

Envirofacts Warehouse publishes online nearly all public EPA databases. It also includes easy, though limited, query forms.
http://mountain.epa.gov/enviro/index_java.html

The Bermuda Biological Station for Research, Inc. has nice oceanic data.
http://www.bbsr.edu/

North Carolina Vital Statistics, Institute for Research in Social Science, UNC, provides a public version of all vital records, except induced abortion case reports. These data may be used in epidemiology and environmental health research.
http://www.irss.unc.edu/ncvital/preface.html

Questions
Email me.