Instructor
Dr. Drew Tyre
Office: Hardin Hall Rm 416
Phone: 402-472-4054
E-Mail: atyre2@unl.edu
https://drewtyre.rbind.io
Time: Lectures & Lab: online (see below for details)
Office hours: M 10-12pm, W 10-12pm, F 2-5pm or by appointment
Index
(Click on the areas above for more detail)
Technical Requirements
In order to take this course, you must have:
- An Internet connection and a browser (see below for supported browsers)
- Microsoft Word
- PowerPoint
- Adobe Acrobat Reader
- USB headset with a microphone (The built-in microphone on a laptop is not sufficient.)
- R Version 3.4.0 or higher and RStudio Version 1.0.143 or higher (see setup guide)
The current version of Canvas works with the following web browsers:
- Internet Explorer 11; Edge 39 and 40
- Safari 9 and 10
- Chrome 59 and 60
- Firefox 53 and 54
- Flash 25 and 26
- Respondus Lockdown Browser
The technology skills you will need to succeed in this course are a basic familiarity with your Web browser, e-mail, word processing, and the ability to locate specific information on the Internet. You must also know or learn how to use Canvas courseware.
Login Instructions
https://canvas.unl.edu Log in using your Canvas username and password.
Description
We will cover a broad sample of statistical topics relevant to ecologists; the intent is to provide an introduction enabling student to intelligently follow a seminar or scientific paper utilizing these methods. Depending on the needs and interests of the students we will enable students to conduct analyses on their own for a subset of topics. Across all topics we will emphasize modern methods of model selection/multi-model inference and relevant study design questions. Topics will include generalized linear and additive models, mixed models, and survival analysis. We will use the software package R. Each student will present a data analysis problem of their choice, implement an ecological analysis, and prepare a written paper summarizing the analysis and results.
Prerequisites
Graduate standing or permission of instructor; STAT 801 or equivalent; Prior Experience with “R” software.
You should be familiar with basic hypothesis testing using a t-test, ANOVA and simple Linear Regression.
Learning Objectives
By the end of the course the students will be able to:
- Identify and summarize statistical results as presented in peer reviewed articles
- Compare and contrast the outputs of a model selection processes based on Frequentist or Information Theoretic methods
- Use R to conduct model based analyses of ecological data
- Combine statistical results and ecological knowledge to support a conclusion
- Evaluate the presentation of statistical results in written and verbal form
Students will have the opportunity to
- Critically discuss modern literature on ecological data analysis.
- Use modern methods to analyze their own data.
- Practice asking for and giving accurate and useful assistance from the R-help community
Instructor’s Role
This course is offered fully online, in an asynchronous fashion. I will have online “office hours” using Adobe Connect Monday at 10 - 12 pm, Wednesday at 10-12 am and Friday between 2 and 5 pm. At other times I will read items posted in the discussion groups within 24 hours of posting during the week, and within 48 hours over the weekend. I will respond if needed to clarify a question or comment, answer a question, or clarify a response by another course participant. If you send in a question via email, I will repost it in a discussion thread and answer it there. You will get your answer much more quickly by posting in the discussion thread directly.
I am also available by telephone at the number above during the week, generally between 8:30 am and 4:30 pm. If I am not at my desk, I typically respond to voice mail messages within 4 hours.
Textbooks
Required: Alain F. Zuur, Elena N. Ieno, Graham M. Smith. 2007. Analysing
Ecological Data. New York ; London : Springer.Required: David R. Anderson. 2009. Model-Based Inference in the Life
Sciences: A Primer on Evidence. Springer, New York, NY. 180 pp.Larkin A. Powell and George A. Gale. 2015. Estimation of Parameters for Animal Populations: A primer for the rest of us. Caught napping publications, Lincoln, NE. available online
Alain F. Zuur, Elena N. Ieno, Erik H.W.G. Meesters. 2009. A
beginner’s Guide to R. New York; London : Springer.Garret Grolemund and Hadley Wickham. 2016. R for Data Science.
Published online.
Note: All of the texts are available electronically through the UNL library or online . The Zuur et al (2009) Beginners guide is a bit dated. Grolemund and Wickham is better. But I am assuming that you know the basic concepts of running R code, getting help, manipulating data and making plots.
Hardware and Software Requirements
Any modern pc or mac should be able to run all of the software we will use in this course. An internet connection is needed to access course materials on Blackboard, and submit assignments. Participating in the online help sessions requires an internet connection, a microphone, and speakers. The integrated microphone and speakers on a laptop are typically not sufficient, but a cheap pair of earbuds will reduce or eliminate issues with feedback. A USB headset that combines headphones and a microphone is optimal. A webcam, either integrated or standalone, also helps interaction online because I can see when you’re not getting it even if you’re not telling me in words!
All of the statistical software we will use is available as open source. Links to software can be found here.
Assessment / Grading
Lab assignments 10%
In many weeks you will complete a lab assignment that will walk you through various steps in using R and analyzing data. These formative assignments contribute to your grade, but generally you will earn full points simply for completing all the steps.
Homework assignments 30%
There are 8 homework problems; generally these will require you to conduct an analysis of a provided dataset and interpret the results in written form. Due dates are Tuesday of the week indicated in the course schedule.
Paper discussions 20%
In each module there will be one or more opportunities to discuss papers either about that analysis or that use that analysis. These will occur online, as required by the course schedule. They will be graded on the basis of 2 components - preparedness and participation. Preparedness will be assessed by having each student post to a discussion thread a direct quote from each paper.
Project 40%
The project will involve a more thorough analysis and writeup of a particular dataset. In the first weeks of the course students will present a dataset of their choice; students without a dataset to analyze should visit with the instructor as soon as possible. These initial pre-proposals will be short (< 2 pages), and should include the following information:
- What is the ecological hypothesis or model of interest?
- What variables were measured?
- What do you THINK the best analysis is?
These pre-proposals should be posted to a Blackboard discussion thread. Your grade for the pre-proposal will include a component for participation in online discussions of projects; the pre-proposal and discussion together are 25% of the project grade. Midway through the course I expect a written proposal for the analysis – this will be two to three pages and essentially form a draft introduction and methods/materials section for the final paper. This written proposal is worth another 25% of your grade. On DECEMBER 5, 2017 you will post a narrated powerpoint or flash video to Blackboard giving a formal conference style presentation of your project – the maximum length is 10 minutes. This is worth 25% of your project grade. The final paper will be due DECEMBER 12, 2017 at 5pm Central Time. The form of the paper should be a brief research article formatted as a manuscript suitable for submission to the journal of your choice (e.g. Journal of Wildlife Management, Biometrics). Note the final paper is in lieu of an exam, and is worth 25% of the project grade.
Note that I am not grading attendance at the synchronous sessions. You are welcome to skip those or jump ahead as you wish.
Grading Scale
The total points assessed will be translated into letter grades as follows: <60 F, 60-69 D, 70-79 C, 80-89 B, 90-100 A. I do not use minus grades, and give plus grades to scores in the top 20% of each band.
Course Schedule
Module 1
| Week | Topic | Assignment Due |
|---|---|---|
| 1 – Aug 21 | Introductions, setup, Review linear models I | |
| 2 – Aug 28 | Review of linear models II | |
| 3 – Sep 4 | Model Selection & Power | Linear Models |
| 4 – Sep 11 | Model Selection AIC, BIC and friends | Preproposal |
Module 2
| Week | Topic | Assignment Due |
|---|---|---|
| 5 – Sep 18 | Generalized Linear Models | |
| 6 – Sep 25 | Generalized Additive Models | Mt Lofty Birds |
| 7 – Oct 2 | NO CLASS - DR TYRE AWAY | |
| 8 – Oct 9 | What’s the smoothest path? | Preproposal Discussion |
Module 3
| Week | Topic | Assignment Due |
|---|---|---|
| 9 – Oct 16 | FALL BREAK No Class | |
| 10 – Oct 23 | Mixing it up I | What’s the Best Shape |
| 11 – Oct 30 | Mixing it up II | Project Intro/methods |
| 12 – Nov 6 | Choosing a mixed model |
Module 4
| Week | Topic | Assignment Due |
|---|---|---|
| 13 – Nov 13 | Time to Event Data | Herbivore Shadows |
| 14 – Nov 20 | THANKSGIVING BREAK | |
| 15 – Nov 27 | Topics TBD | |
| 16 – Dec 4 | Topics TBD |
Note: I reserve the right to deviate from this schedule if required. However, I will not make any reading or assessment due earlier; I will only postpone due dates or cancel assessments altogether.
Course Policies
Late Assignments
Unless you have a good reason (“my computer’s down” doesn’t qualify), I cannot give full credit for late assignments - it is not fair to everyone else. Work received up to one week late after the due date will lose a grade (10%). Work received more than one week late up until the last day of class will lose two grades (20%). All assignments will be turned in via Canvas so they will be timestamped. Always keep a digital or hard copy of assignments you turn in. All paper discussion assignments must be turned in on time; no late summaries will be accepted.
Academic Integrity Statement
Students are expected to adhere to guidelines concerning academic dishonesty outlined in Article III B.1 of University’s Student Code of Conduct. A first offense will result in a 10% penalty on the assignment. A second offense will result in a grade of zero for the assignment. A third offense will result in a grade of F for the course. Students are encouraged to contact the instructor for clarification of these guidelines if they have questions or concerns. The SNR policy on Academic Dishonesty and procedures for appeals are available here.
Netiquette
Core rules of Netiquette: http://www.albion.com/netiquette/corerules.html
Students with Disabilities
Students with disabilities are encouraged to contact the instructor for a confidential discussion of their individual needs for academic accommodation. It is the policy of the University of Nebraska-Lincoln to provide flexible and individualized accommodation to students with documented disabilities that may affect their ability to fully participate in course activities or to meet course requirements. To receive accommodation services, students must be registered with the Services for Students with Disabilities (SSD) office, 132 Canfield Administration, 472-3787 voice or TTY.
In case of emergency
Fire Alarm (or other evacuation)
In the event of a fire alarm: Gather belongings (Purse, keys, cellphone, N-Card, etc.) and use the nearest exit to leave the building. Do not use the elevators. After exiting notify emergency personnel of the location of persons unable to exit the building. Do not return to building unless told to do so by emergency personnel.
Tornado Warning
When sirens sound, move to the lowest interior area of building or designated shelter. Stay away from windows and stay near an inside wall when possible.
Active Shooter
Evacuate: if there is a safe escape path, leave belongings behind, keep hands visible and follow police officer instructions.
Hide out: If evacuation is impossible secure yourself in your space by turning out lights, closing blinds and barricading doors if possible.
Take action: As a last resort, and only when your life is in imminent danger, attempt to disrupt and/or incapacitate the active shooter.
UNL Alert: Notifications about serious incidents on campus are sent via text message, email, unl.edu website, and social media. For more information go to: http://unlalert.unl.edu.
Additional Emergency Procedures can be found here: http://emergency.unl.edu/doc/Emergency_Procedures_Quicklist.pdf
HELP!!
Canvas
Various student resources are available for any issues you experience with Canvas® courseware and any other technical problems that might arise during the course of the semester. You can find a list of helpful resources at the bottom left Help link on your Canvas home page.
Library Services
UNL distance students have access to a tremendous resource-UNL’s Library Services
This web site can also be accessed directly at: http://iris.unl.edu/
After that you will be at the Iris Main Page.
