Statistical Ecology

Stat 555, Fall 2009
WSU Vancouver

Instructor:         Dr. Brian Tissot

Internet:           E-mail:Tissot@wsu.edu    
 Web: http://www.vancouver.wsu.edu/fac/tissot/cl/stat555/
 

References:     Underwood, A. J. 1997. Experiments in Ecology: their logical design and interpretation using analysis of variance. Cambridge University Press,  Cambridge, Univ.

                         Plus additional books and papers from the scientific literature  (website)

Prerequisites for the course:
Stat 412, Biometry, or the equivalent or consent of the Instructor;
computer experience; experience in Minitab, SAS, Primer and Excel preferred.      

Tentative Lecture Schedule

                                                                                      Required           Recommended
     Lecture                      Topic                                 Reading                 Reading

Grading:

Class discussion & participation................................................................. 10%

Paper discussion lead & participation........................................................ 10%

Paper discussion reviews (2)...................................................................... 20%

Homework (10-12)........................................................................................ 30%

Project Presentation..................................................................................... 10%

Project Report................................................................................................ 20%

I Use a 90%=A, 80%=B, 70%=C, 60%=D, <50%=F plus/minus grading system

Academic Integrity:  Academic integrity is the cornerstone of the university and will be strongly enforced in this course.  Any student found in violation of the academic integrity policy will be given an “F” for the course and will be referred to the Office of Student Conduct.  For additional information about WSU’s Academic Integrity policy/procedures please contact (360) 546-9573. 

Disability Accommodation:  Accommodations may be available if you need them in order to fully participate in this class because of a disability. Accommodations may take some time to implement so it is critical that you contact Disability Services as soon as possible.  All accommodations must be approved through Disability Services, located in the Student Resource Center on the Lower Level of Student Services Center (360) 546-9138.

Emergency Notification System:  WSU has made an emergency notification system available for faculty, students and staff. Please register at myWSU with emergency contact information (cell, email, text, etc). You may have been prompted to complete emergency contact information when registering for classes on RONet. In the event of a Building Evacuation, a map at each classroom entrance shows the evacuation point for each building. Please refer to it. Finally, in case of class cancellation campus-wide, please check local media, the WSU Vancouver web page and/orhttp://www.flashalert.net/. Individual class cancellations may be made at the discretion of the instructor. Each individual is expected to make the best decision for their personal circumstances, taking safety into account. 

Important Dates and Deadlines: Students are encouraged to refer to the academic calendar often to be aware of critical deadlines throughout the semester.  The academic calendar can be found atwww.registrar.wsu.edu/Registrar/Apps/AcadCal.ASPX.  Questions regarding the academic calendar can be directed to the Office of Student Affairs in VSSC 100 or call 360-546-9559.

Campus Safety Information

WSU Vancouver Campus Safety Plan: http://safetyplan.vancouver.wsu.edu/

WSU Vancouver Public Safety web site: www.vancouver.wsu.edu/police

WSU Vancouver ALERTS web site: http://www.vancouver.wsu.edu/alerts/

Description of Assignments

Research Paper Discussions

As a compliment to the text we will discuss papers from the scientific literature during the course of the semester. The general goals of this exercise are to introduce the primary research literature and to critically examine scientific research. These sessions will also allow us to openly discuss the statistical subjects at issue which in turn will help you to understand the course material.

Each paper will be introduced by 1 or 2 students who will lead the discussion. Obviously, the lead person(s) must have a good grasp of the content of the paper which generally requires several readings of the paper and a formulation of discussion strategy. The rest of the class should read the paper at least once and be able to contribute intelligently to the discussion.

A suggested format for the lead person is a follows. Remember, however, that 15 minutes is allotted to the review so make sure that important points are discussed first.

Please don’t simply summarize the paper.
We have all read it so focus on key issues!

Part 1:Overview: general overview of paper

INTRODUCTION (1 min)

State the authors and title of the paper. What is the general topic of the paper? Be sure to define any terms or concepts used in the paper that haven't been discussed in class. Is it a research paper, a review, or a theoretical paper? What hypotheses were the authors testing (if any)? Was the general question raised by the paper a good one?

Part 2:Start discussion: begin critique of paper by making points or posing questions that are discussed by the class (REMEMBER: this is a discussion, don't talk the entire time!)

METHODS (»2-3 min) if appropriate

How were the data collected? Were any experiments performed? Were they designed properly? Did the experiments adequately test the stated hypotheses? Were the methods explained in sufficient detail to understand what was done? Where there any implicit assumptions that were critical and untested?

RESULTS & DISCUSSION (»9-10 min)

What were the results of the study? Were they clearly presented? Were the results adequate to address the questions raised? Were the stated hypotheses evaluated properly? Were the appropriate statistical analyses performed? Were they properly interpreted? What were the shortcomings of the study? Do you agree or disagree with the overall conclusions? Were additional questions raised by the study? If so, what are they and how could we study them?

Conclusion (»1-2min)

In a single sentence summarize the basic results of the paper. Do you agree or disagree with this result? Why or why not?

Paper Reviews (2) –no longer than 2 pages long (single spaced)

NOTE: Paper reviews are due one week after they are discussed in class

Ecology -- GUIDELINES FOR REVIEWERS

Quality peer reviews are essential for insuring the quality of scholarly journals. Your evaluation will play a major role in our decision as to whether to accept a manuscript for publication. We place a great deal of trust in you. We trust you to be prompt, fair, respectful of the rights of the authors, respectful of our obligations to the readership, and to evaluate the manuscript carefully and in depth. At the same time, on behalf of the ESA membership, we are very grateful for the time and effort you invest in the review process

Please be aware that Ecology has moved to tighter, shorter articles than has been the case in the past. As we have made this transition, many articles have been rejected without review because they were too long to fit in the current look of the journal. The article you have reviewing may have been previously rejected because it was longer than 30 pages (including absolutely everything except that which is destined for the digital Ecological Archives), and has now been shortened in the resubmission.

Confidentiality

This manuscript is a privileged communication. Please do not show it to anyone or discuss it, except to solicit assistance with a technical point. If you feel a colleague is more qualified than you to review the paper, do not pass the manuscript on to that person without first requesting permission to do so. Your review and your recommendation should also be considered confidential.

Conflicts of Interest

If you feel you might have difficulty writing an objective review, please return the paper immediately, unreviewed. If your previous or present connection with the author(s) or an author's institution might be construed as creating a conflict of interest, but no actual conflict exists, please discuss this issue in your confidential comments to the editor. If in doubt, feel free to contact the Subject-matter Editor who requested your review.

Comments for the Author

Identify the major contributions of the paper. What are its major strengths and weaknesses, and its suitability for publication? Please include both general and specific comments bearing on these questions, and emphasize your most significant points.

General Comments should address the following:

• Importance and interest to this journal's readers
• Scientific soundness
• Originality
• Degree to which conclusions are supported
• Organization and clarity
• Cohesiveness of argument
• Length relative to information content
• Whether material should be moved to the digital appendices
• Conciseness and writing style
• Appropriateness for the targeted journal and specific section of the journal

Specific Comments:

Support your general comments, positive or negative, with specific evidence. Remember that a review lacking substance will generally have less impact than a review that is well-reasoned and rich in content. You may write directly on the manuscript (or embed comments in a digital copy of the manuscript), but please summarize your remarks in "Comments for the Author(s)." Comment on any of the following matters that significantly affected your judgment of the paper:

1. Presentation -- Does the paper tell a cohesive story? Is a tightly reasoned argument evident throughout the paper? Where does the paper wander from this argument? Do the title, abstract, key words, introduction, and conclusions accurately and consistently reflect the major point(s) of the paper? Is the writing concise, easy to follow, interesting?

2. Length -- What portions of the paper should be expanded(?), condensed(?), combined(?), and deleted? (Please don't advise an overall shortening by X%. Be specific!)

3. Methods -- Are they appropriate(?), current(?), and described clearly enough(?) that the work could be repeated by someone else?

4. Data presentation -- When results are stated in the text of the paper, can you easily verify them by examining tables and figures? Are any of the results counterintuitive? Are all tables and figures necessary(?), clearly labeled(?), well planned(?), and readily interpretable?

5. Statistical design and analyses -- Are they appropriate and correct? Can the reader readily discern which measurements or observations are independent of which other measurements or observations? Are replicates correctly identified? Are significance statements justified? For further advice, consult ourGuidelines for Statistical Analysis and Data Presentation.

6. Errors -- Point out any errors in technique, fact, calculation, interpretation, or style. (For style we follow the "CBE Style Manual, Fifth Edition," and the ASTM Standard E380- 93, "Standard Practice for Use of the International System of Units." - An abbreviated version may be downloaded from theASTM website.)

7. Citations -- Are all (and only) pertinent references cited? Are they provided for all assertions of fact not supported by the data in this paper?

8. Overlap -- Does this paper report data or conclusions already published or in press? If so, please provide details.

Fairness and objectivity

If the research reported in this paper is flawed, criticize the science, not the scientist. Harsh words in a review will cause the reader to doubt your objectivity; as a result, your criticisms will be rejected, even if they are correct! Comments directed to the author should convince the author that (1) you have read the entire paper carefully, (2) your criticisms are objective and correct, are not merely differences of opinion, and are intended to help the author improve his or her paper, and (3) you are qualified to provide an expert opinion about the research reported in this paper. If you fail to win the author's respect and appreciation, much of your effort will have been wasted.

Anonymity

You may sign your review if you wish. If you choose to remain anonymous, avoid comments to the authors that might serve as clues to your identity. Unless you indicate otherwise (such as by signing your remarks for the authors), we will assume you wish to remain anonymous.

Annotating the manuscript

If you wish to remain anonymous, beware of inserting comments on the pdf, as that may reveal your identity. If you wish to write comments on a printed copy of the manuscript, you could scan in the document and send it as an attachment with your review, or indicate in your comments to the editor that you are mailing it, and send it to our office.

Ecology Guidelines for Statistical Analysis and Data Presentation

Basic philosophy -- These rules and suggestions proceed from two principles. (1) Authors are free to perform and interpret statistical analyses as they see fit. (2) The reader needs to be provided information sufficient for an independent assessment of the appropriateness of the method. Thus, the assumptions and (or) the model underlying unusual statistical analyses must be clearly stated and results must be sufficiently detailed. On occasion, more detail than warranted for the final publication may have to be provided to reviewers to allow them to make an informed judgment. The purpose of statistical analysis is to increase the conciseness, clarity and objectivity with which results are presented and interpreted, and where an analysis does not serve those ends it probably is inappropriate.

Data description -- Sampling designs, experimental designs, data-collection protocols, precision of measurements, sampling units, experimental units, and sample sizes must be clearly described. Reported information usually includes the sample size and some measure of the precision (standard errors or specified confidence intervals) of estimates, although this may not be necessary or possible in all instances especially for unusual statistics. Graphical data presentation is encouraged. Carefully composed graphs often permit the reader to decide at a glance if data are in danger of violating statistical assumptions.

Assumptions -- It is important that the author be satisfied that the assumptions behind any statistical analysis are sufficiently met and that, at least where unusual assumptions are made, unusual procedures are used, or unusual types of data are involved, and that the reader be provided with sufficient information to judge whether any departures from assumptions are severe enough to vitiate the conclusions. The amount of detail provided in any particular instance will depend on the centrality of the statistical test to the conclusions.

Reporting of analyses -- The specific statistical procedure must always be stated. If a statistics program or program package was used, a complete citation (including version number) should be given. If necessary, the author should indicate which procedure within a package was used and which method within a procedure was chosen. Such citations may be even more important for reviewers than they are for readers. Unusual statistical procedures need to be explained in sufficient detail, including references if appropriate, for the reader to reconstruct the analysis. To denote levels of significance, actual P values are generally more informative than symbols such as * and **.

If conclusions are based on an analysis of variance or regression, information sufficient to permit the construction of the full analysis of variance table (at least degrees of freedom, the structure of F-ratios, and P values) must be presented or be clearly implicit. Where ambiguity is possible, the authors must indicate which effects were considered fixed or random and why.

Effect size and biological importance must not be confused with statistical significance. Power analyses (determination of type II error rates, ß) occasionally can be very useful, especially if used in conjunction with descriptive procedures like confidence intervals. Such tests are not always routine; for complex or unusual statistical designs, descriptions of such tests should be sufficiently detailed.

Project Report & Presentation

Project report: the intention is to focus on the data analysis and interpretation, not on writing a complete scientific paper. The paper should include a very brief introduction for context, a description of the data collection, and a major focus on statistical analysis, results and interpretation.

Details:

·       This is to be presented in a standard scientific paper format.

·       There should be an introduction but it can be very short (1 page) with a list of general questions and/or hypotheses to be addressed.

·       Literature should be cited primarily on the statistical methods used with some reference to majoe points of interpretation. Papers discussed in class that are relevant should be cited.

·       All elements of experimental design should be explicit and you should indicate how you would redesign your study to address shortcomings.

·       The paper should be double-spaced and at least 10 pages in length. Include MINITAB/SAS/Primer printout in the report but incorporate everything into the paper through text, figures and tables.

·       Grading Rubric:

a.     Experimental design (30%)

b.     Data analysis (40%)

c.     Interpretation (20%)

d.     Initiative (10%)

Final presentation: you will have 10 min  to summarize the highlights of your paper using a PowerPoint presentation with 2 mins for questions. Handsouts of important analyses are strongly encouraged.