STAT 534 - Ecological Statistics

Fall 2017

Syllabus and other useful information

Useful Information

• Lecture: Tu/Th 3:40 - 5:00, Mol. Bio. 1428
• Instructor: Dr. Philip Dixon, pdixon at iastate.edu, 2121 Snedecor, 4-2142
• Office Hours: Thursday, noon - 1
• Review / Help: during office hours or set up a time to meet with me
• Questions?: Please feel free to e-mail me anytime (pdixon at iastate.edu) with questions or comments.
• Class Web site: http://www.public.iastate.edu/~pdixon/stat534
Copies of the syllabus, homework assignments, data sets and example programs will be available here.
• Text: None
• Reading materials: Various assigned readings will be available in the Statistics Dept. Office. Visit the front desk to borrow the material to make a copy.
• Learning Outcomes: By the end of the course, students will be able to:
• Use statistical methods to answer ecological questions, focusing on population ecology
• Understand the statistical theory for those methods.
• Apply classical and modern statistical inference to some non-standard problems.
• Apply statistical methods and theory to novel problems.
4 Homework sets: 100 points each.
No tests.

Homeworks are due at 5pm on the assigned date. Late homework will be penalized 5 points per day late.

• Computing:
This course emphasizes data analysis to answer questions. This will require using statistical computing packages. Unfortunately, no one package does everything well. You may use whatever tools are appropriate to do the necessary computations. I expect that most of you will use R; I provide help with R. In particular, I will distribute examples of R code (and SAS if helpful) on the class web site. Some of you may be familiar with specialized programs developed for certain parts of the course (e.g. Program MARK for estimation of population parameters). You are free to use that program, but I will not lecture about it.

Course Outline:

```
Weeks  Dates         Topic

1-6   Aug 21-Sep 29   Estimation of population parameters
(population size, survival, detectability)
Mark recapture and related methods

7-9  Oct 2-Oct 20  Population modeling
Matrix models
Integral population modeling
Environmental variation and Population Viability Analysis

10-12  Oct 23-Nov 10   Combining models and data
Bayesian hierarchical modeling
Models with density dependence
Integrated population modeling

13-15  Nov 13 - Dec 8 To be determined by class interest

15                    Likely to include HW 4 presentations

Possible topics for the last three weeks:

Your suggestions, especially methods or problems specific to your
research
Further extensions of topics already discussed.
Spatially explicit Capture recapture
Passive tags (genetics, hair snares, camera traps)
Behavioural statistics, especially analysis of event sequences.
Resource selection / habitat preference analysis
Home range estimation and related issues
Ecological ordination (analysis of species composition data)

```

Details:

Readings: Assigned readings will provide background, additional details, or another presentation of the lecture material. Citations will be distributed in lecture. The Statistics Department Main Office will have a master copy that you can borrow. It will help if you read the assigned material soon after the appropriate lectures.

Homework: Statistics is best learnt by doing. The homework problems are chosen to give you practice in using the methods, interpreting the results, and understanding the theory. The intent is to understand and be able to apply lecture concepts, so discussion with friends and classmates is encouraged. However, you must write up your own solutions. Copying papers is not a good way to learn and will not be tolerated.

There will be an assignment every 3 weeks or so, i.e. two on mark-recapture, one on population modeling, and one on combining models and data. Each assignment will have four problems. Two, perhaps three, will focus on data analysis and interpretation. Two, perhaps one, will focus on the theory. If there are two theory problems, one may be replaced by summarizing a paper from a list I provide.

Some data analysis problems will provide practice using and interpreting methods discussed in class. Others will be labelled "major data analysis". These will give you a data set and ask you to make some conclusions. You will need to decide how you want to analyze the data. These problems should be written up as reports to your manager. The report should include a one (perhaps two) paragraph executive summary, a methods section that describes the methods you used, and a results section that includes appropriate tables and figures. For some problems you will need to choose an appropriate analysis. You may consider various analyses. Only report results from the analysis you believe is most appropriate; your methods section should include a discussion of what you considered and how you made your choice of method.

The last homework assignment (on hierarchical modeling) will require you to work in team, preferably 2 people with a mix of backgrounds. You will choose a problem, develop and fit a hierarchical model, then present your results to the class. These presentations will occur during the last week of classes and potentially the final exam time.

Syllabus statements: Syllabus statements on academic dishonesty, disability accomodation, dead week, harassment and discrimination, religious accomodation, and contact information for academic issues are in Syllabus statements.docx.

Details specific to Stat 534:
Academic dishonesty: On homework assignments: I encourage you to help each other interpret the homework problems, write code, debug code, and interpret the output. You may share code, but I encourage you to understand that code even if you didn't write it. I do require you to write your answers in your own words.
Dead week: Presentations on your hierarchical modeling project will be scheduled during dead week and potentially during the regularly scheduled final exam period.