Statistics for Environmental Science
Spring 2007

ECOL 562, BIOL 562, ENST 562

• Course Details

  Instructor: Jack Weiss, Curriculum in Ecology, 218 Miller Hall, 962-5930, jack_weiss@unc.edu

  Meetings: 4 lectures hours per week split between classroom and computer lab

Meeting Times —MW 12-1 pm, 10 Peabody Hall and F 12-2 pm, 322 Saunders Hall

Text: Manly, Bryan F. J. 2001. Statistics for Environmental Science and Management. Chapman & Hall/CRC Press: Boca Raton, FL

Software: R, a freeware implementation of the S language. The R home page is http://www.r-project.org. The software can be downloded from http://cran.r-project.org

Website: http://www.unc.edu/courses/2007spring/enst/562/001/

Office Hours: I'm available at any time on M, W, and F. I generally will be working on consulting projects on T and Th and so will be unavailable. My office is in 218 Miller Hall (home of the Carolina Environmental Program). Miller Hall is on the corner of McCauley and Pittsboro, next to the Carolina Inn.

Evaluation: Weekly homework, midterm, and final

Registration Details: Seats are reserved separately for ECOL 562 (7 seats), BIOL 562 (7 seats), and ENST 562 (15 seats). If the course is closed for one of these listings, try registering for one of the other two.

• Overview of the Course

  An introduction to statistical methods for environmental scientists. This course takes basic statistical concepts and extends them to topics of special relevance in environmental fields. Familiarity with the standard parametric approaches of statistical analysis such as hypothesis testing is assumed. The course is intended to serve as a transition between what is typically taught in an undergraduate statistics course and what is actually needed to successfully analyze data in the environmental sciences. Special emphasis is placed on avoiding pitfalls that can lead to invalid statistical analyses. The ideal enrollee is an upper level undergraduate student who has already taken an introductory statistics course and wishes to see the modern application of statistics to environmental science and ecology.

• Prerequisites

  The prerequisites are modest, a one semester undergraduate or high school course in statistics (the equivalent of UNC Stat 31) and some exposure to the concepts of calculus. If you have never studied statistics, this is probably not the course for you. Having said this I think it is quite possible to obtain the requisite background through self-study before the course begins. I expect you to be familiar with (as in heard of and can quickly relearn) the following ideas:

  1. elementary probability theory including permutations and combinations, probability rules (for a union, intersection, etc.), the concepts of marginal and conditional probabilities (especially the latter), and the formulas and motivation for the normal, binomial, and Poisson probability distributions,
  2. the standard parametric approaches to hypothesis testing, e.g., one and two-sample t-tests, etc., and
  3. elementary linear regression in which there is a single response and a single predictor.

  Just about any elementary statistics text covers this material. The book Introduction to the Practice of Statistics by David S. Moore and George P. McCabe, the text that is used in undergraduate statistics courses at UNC, is an adequate choice as is any other text written at this level. Personal favorites of mine include Statistics with Applications to the Biological and Health Sciences by M. Anthony Schork and Richard D. Remington (any edition) and Biometry by Robert R. Sokal and F. James Rohlf.

• Statistical Software

  No familiarity with statistical software is assumed. We will be using R, a free implementation of the S language, available for free download at http://cran.r-project.org. R runs on all major operating systems, including Windows, Unix, and Mac OS X. R is a state-of-the-art modern statistical package actively supported by the worldwide scientific community. It is not easy to use but it has become the de facto standard for scientific research. Although I've used many statistical packages in my career and even spent a number of years working for the SAS Institute, I now do all my work using R. Our lecture sessions in Saunders Hall will include hands-on instruction in the use of R. In addition there are many online resources and published textbooks in the use of R. Links to these appear on the course web site.

• Course Content

  We will essentially work through Manly's book plus explore a few additional topics. We will cover the following.

1. Overview of basic statistical methods
2. Statistical distributions important in ecological modeling: binomial, Poisson, negative binomial, normal, lognormal, gamma, and exponential.
3. Sampling procedures
4. Regression
5. Likelihood theory and its applications in regression
6. Generalized linear models: Poisson regression, negative binomial regression, logistic regression, and others
7. Model comparison: information-theoretic alternatives to significance testing
8. Strategies of statistical modeling
9. Randomization tests and the bootstrap
10. Multiple testing issues
11. Bayesian approaches to data analysis
12. Environmental monitoring and impact assessment
13. Regression models for temporally and spatially correlated data: random coefficient models (multilevel models)
14. Spatial data analysis

Course Home Page