Syllabus

Course name:            Statistical Models Applied in Science

Credits:                      3

Lecture/Lab:             Fall: W 17:00 – 19:50

Instructors:                Bogdan Strimbu (office hours: W →16:00 – 17:00)

Email:

Additional office hours can be arranged by appointment. Contact the instructors by email.

Description:

Examination of regression techniques and assumptions used to develop static and dynamic equations of tree and stand attributes

Prerequisites: Any Introductory Statistics class with C or above or instructor approval.

Learning Objectives:

• Examine assumptions and their impact on linear regression. A model is defined not only by its fit to data, basically shape, but also by the fulfilment of the assumptions on which computations are executed. The students will learn:
  • To identify whether or not the assumptions are met
  • To examine the consequences of violating assumptions
  • To minimize the consequences of assumption violations
• Nonlinear modeling. Linear models are very rare encountered in real applications. To this end we will focus on non-linear models as the natural generalization of linear models. The students will lean the foundation of
  • mixed models
  • nonlinear models
  • systems of simultaneous equations
  • generalized linear models
  • parsimonious nonlinear models
• Select an appropriate model. The students will identify a solution for a real problem. The problem will be either an aspect of their research or a given problem of interest in forestry.

The statistical theory will be discussed in the context of modeling and implemented in exercises and homework assignments. At the completion of the class the students will have a personalized library of models, as well as an extensive references to be used in subsequent analyses.

Learning Outcomes

• Develop linear and nonlinear models
• Choose among possible nonlinear models
• Enhance skills on using modeling software, such as R or SAS

Statement Regarding Students with Disabilities

Accommodations for students with disabilities are determined and approved by Disability Access Services (DAS). If you, as a student, believe you are eligible for accommodations but have not obtained approval please contact DAS immediately. DAS notifies students and faculty members of approved academic accommodations and coordinates implementation of those accommodations. While not required, students and faculty members are encouraged to discuss details of the implementation of individual accommodations.

Course Materials

All materials used in this course are accessible on Box. If you require special accommodations, please contact Disability Access Services (DAS).

Expected Student Conduct

The Office of Student Conduct and Community Standards Student detailing university policies on conduct governs the class. The information can be accessed at http://studentlife.oregonstate.edu/sites/studentlife.oregonstate.edu/files/code_of_student_conduct.pdf.

Academic Integrity

Students are expected to comply with all regulations pertaining to academic honesty. For information on Academic Dishonesty you could contact the office of Student Conduct and Mediation. Academic or Scholarly Dishonesty is defined as an act of deception in which a Student seeks to claim credit for the work or effort of another person or uses unauthorized materials or fabricated information in any academic work or research, either through student's own efforts or the efforts of another.

Academic Dishonesty cases are handled initially by the academic units, following the process outlined in the University's Academic Dishonesty Report Form.

Grading

The grades will be computed as a weighted average between 7 assignments, a midterm, and one project. The weights determining the final grade are:

• Assignments - each 5% 35 %
• Midterm                         20%
• Final 20%
• Project 25%

Numerical grades will be converted to letter grades using the following scale:

Project

Each student will have to complete a project that consists of at least one model applied to a real dataset. The project could be based on the student research or I will provide the data. The project should be delivered as a standalone paper, fulfilling all the requirements for publication in a peer reviewed journal. To this end, the project should have an Introduction, which state the problem and the objective of the project. A separate chapter should be dedicated to data acquisition and post-processing, if there is a need for that. In the same chapter, or as a separate chapter, a section should be dedicated to modeling and model assessment. Following the modeling section / chapter is the Results chapter, where the main findings are presented. The Discussions expands the Results chapter by going into the details of the relationship between the overall objective and the model. The project should conclude with at least half page Conclusions.

Learning resources

• Books:
  • Kutner, M.H., C.J. Nachtsheim, J. Neter, and William Li. 2005. Applied Linear Statistical Models. 5th Edition. McGraw-Hill/Irwin, Boston. ISBN 0-07-238688-6.
  • Draper, N.R. and H. Smith. 1998. Applied Regression Analysis, 3rd Edition. John Wiley & Sons, Inc. New York. 706p.
  • Kmenta, J. 1997. Elements of Econometrics, 2nd Edition. University of Michigan Press, Ann Arbor. 786p.
  • Weiskittel, A.R., D.W. Hann, J.A. Kershaw, Jr., J.K. Vanclay. 2011. Forest growth and yield modeling. Wiley-Blackwell, Oxford, 415p. Available for online reading from OSU library website: http://osulibrary.orst.edu/.
  • Venables, W.N., Smith, D.M., and the R Core Team, 2015. An Introduction to R. Available online: http://cran.r-project.org/doc/manuals/R-intro.pdf
  • Chambers and Hastie (1993) Statistical models in S
• Software:
  • R
  • SAS

Topics

• Simple linear regression: estimation, assumptions
• Multiple linear regression: estimation, assumptions
• Nonlinear models:
• Mixed effects models
• Nonlinear regression
• Systems of simultaneous equations
• Generalized linear models
• Parsimonious nonlinear models