- Undergraduate Students
- Graduate Students
- Crop Science Courses
- Soil Science Courses
- Plant Breeding & Genetics Courses
- Why Study Crops?
- Why Study Soils?
- Current Students
- Scholarships, Financial Aid, & Other Funding
- Course Sites
- Research & Extension
- About Us
CROP 590: Experimental Design in Agriculture
Announcements will be posted in Canvas as needed.
Time and Place:
Lectures: MWF 8:00 CRPS 122
Recitation: H 8:00 – 9:20 am CRPS 150
Help Sessions (optional): T 8:00 – 8:50 am in CRPS 150
Instructor: Jennifer Kling
Telephone: (541) 737-8277
Office: CRPS 249
Office Hours: M 9:00 – 10:00 am
H 9:30 – 10:30 am
or by appointment
Teaching Assistant: David Cobertera
Office: CRPS 221
Office Hours: W 9:00 – 9:50 am
General Course Description
This course addresses the needs of the student preparing for a career in agricultural research or consultation and is intended to assist the scientist in the design, plot layout, analysis and interpretation of field and greenhouse experiments. Emphasis is placed on experimental designs used in agronomy and plant breeding research with more emphasis toward applied statistics rather than statistical theory. Many numerical examples and problems will be presented and the recitation will allow students to explore analyses using SAS and Excel.
There is no required text for this class. Recommended references are on reserve in the library.
Kuehl, Robert O. (2000) Design of Experiments: Statistical Principles of Research Design and Analysis, 2nd edition. Duxbury Press. (an excellent general reference, but uses slightly different notation than we do in class) Q182.3.K84 2000
Clewer, A. G. and D. H. Scarisbrick (2001) Practical Statistics and Experimental Design for Plant and Crop Science. John Wiley & Sons. (A good reference for those who are not too familiar with statistics; the emphasis on agricultural research is also very relevant for the course) QK51.C58 2001
Cody, Ronald P. and Jeffrey K. Smith (2006) Applied Statistics and the SAS Programming Language, 5th edition. Prentice Hall, New Jersey. QA276.4 .C53 2006
Petersen, Roger G. (1994) Agricultural Field Experiments: Design and Analysis. Marcel Dekker, New York. (Much of the lecture material was adapted from this text, but it contains some errors. Two copies of the text are on reserve in the library, should you need any clarification on lecture material.) S540.F5 P47 1994
Other Suggested References:
Bowley, Stephen (2008) A Hitchhiker’s Guide to Statistics in Plant Biology, 2nd ed., Any Old Subject Books, Guelph, Ontario, Canada.
Cochran, W. G., and G. M. Cox (1957) Experimental Designs, 2nd ed., Wiley, New York.
Cox, D. R. (1958) Planning Experiments, Wiley, New York.
Gomez, K. A. and A. A. Gomez (1984) Statistical Procedures for Agricultural Research, 2nd ed. Wiley, New York.
Little, T. M., and F. J. Hills (1978) Agricultural Experimentation, Wiley, New York.
Mead, R., R. N. Curnow, and A. M. Hasted (2003) Statistical Methods in Agriculture and Experimental Biology, 3rd ed., CRC Press, Boca Raton, Fl.
Montgomery, Douglas C. (1991) Design and Analysis of Experiments, 3rd ed., Wiley, New York.
Petersen, R. G. (1985) Design and Analysis of Experiments, Marcel Dekker, New York.
Quinn, G. P., and M. J. Keough (2002) Experimental Design and Data Analysis for Biologists, Cambridge University Press, Cambridge, UK.
Ramsey, F. L. and D. W. Schafer (2002) The Statistical Sleuth: A Course in Methods of Data Analysis, 2nd ed., Brooks/Cole, CA.
Snedecor, G. W., and W. G. Cochran (1980) Statistical Methods, 7th ed., Iowa State University Press, Ames, IA.
Sokal, R. R. and F. J. Rohlf (2011) Biometry: the Principles and Practice of Statistics in Biological Research, 4th ed., W.H. Freeman, New York, NY.
Steel, R. G. D., J. H. Torrie and D. A. Dickey (1997) Principles and Procedures of Statistics, 3rd ed., McGraw-Hill, New York.
Stroup, W. W. (2013) Generalized Linear Mixed Models: Modern Concepts, Methods and Applications, CRC Press, Taylor & Francis Group, Boca Raton, FL.
Zar, J. H. (2010) Biostatistical Analysis, 5th ed., Pearson Prentice Hall, Upper Saddle River, NJ.
Other SAS References:
Der, G. and B. S. Everitt (2002). A Handbook of Statistical Analyses using SAS, 2nd ed., Chapman & Hall/CRC.
Littell, R. C., G. A. Milliken, W. W. Stroup, R. D. Wolfinger, and O. Schabenberger (2006) SAS for Mixed Models, 2nd ed., SAS Institute, Inc., Cary, NC.
Littell, R. C., W. W. Stroup, and R. J. Freund (2002) SAS for Linear Models, 4th ed., SAS Institute, Inc., Cary, NC.
We will be using Canvas for announcements, submitting most assignments, lab quizzes, and posting grades. We will also have a general Q&A discussion forum in Canvas throughout the term. You are encouraged to post questions on course content there. Your instructor will monitor the discussion board and respond within 24-48 hours. Responses from other students are also welcome.
To access Canvas, go to the link below and enter your ONID username and password:
There is an online student guide for using Canvas:
This course will be listed as CROP_590_001_W2016.
Most of the course material for this class is maintained on an external website (separate from Canvas) that can be accessed and used as a reference throughout the year.
Links to the course website are also provided within the Canvas site, for your convenience.
Additional links to websites related to Experimental Design and Statistics are also available in Canvas.
Students should have an introductory understanding of statistical methods including the ideas of interval estimation, significance testing, simple linear regression and correlation. Familiarity with such common statistical tables as Student’s t, F, and chi-square is expected. The necessary mathematical background is minimal. At most, a knowledge of college algebra is required.
Take the online Survey in Canvas at the beginning of the term to provide your instructor with information about your statistics background and interests.
Assessment/Evaluation of Student Performance
|Recitations (lab quizzes and attendance)||10%|
|Proposal for experiment (poster)||15%|
|Final group project||5%|
Grades will be assigned according to the following point system:
|97-100 = A+||87-89 = B+||77-79 = C+||67-69 = D+||<=59 = F|
|93-96 = A||83-86 = B||73-76 = C||63-66 = D|
|90-92 = A-||80-82 = B-||70-72 = C-||60-62 = D-|
There will be five graded assignments in this class, which will be due one week after they are assigned. Unless otherwise specified, you are expected to complete the assignments in Excel or with comparable spreadsheet software. You should include enough detail in your calculations so that the instructor can determine how you got your answers. You may check your answers with the Excel analysis toolpak or other software, but you are expected to use basic Excel functions to solve the problems. It is acceptable to consult with your classmates as you solve the problems if you choose to do that, but the work that you submit must be your own. Your completed Excel spreadsheets should be uploaded as an Assignment in Canvas.
You will have the opportunity in Recitation to gain some hands-on experience with SAS analyses. You will not be expected to turn in work from your recitation sections, but attendance is required. Self-assessments (quizzes) will be available in Canvas to encourage you to review the lab material and ensure that you have understood the major concepts presented each week. You will have two attempts to take the quizzes. You will also need to be able to write simple SAS programs in order to do some of your assignments later in the term, and you may be asked to interpret SAS output on exams.
You may bring one 8.5” x 11” piece of paper and a calculator with you to each exam. You may write any formulas or notes that you think you will need on the front and back of the paper. Exams are comprehensive, but emphasis will always be on the material since the last exam. For the second midterm and final, you may bring the 8.5” x 11” papers that you prepared for earlier exams, along with a new sheet for the exam that you are taking.
The format for the final will be similar to your midterm exams. In addition, the final will include an experimental design synthesis problem that will be given to you during deadweek. You will be presented with a particular scenario and asked to describe the best experimental design to meet the objectives of the experiment. You should think about the scenario and come up with a solution in advance, but the specific questions that you will need to answer about the design will not be known until you take the exam.
The essential concepts for this class will be presented during the first eight weeks of class. During Week 9, students will be expected to select one advanced topic, review the video presentation, and respond to the corresponding study questions. Students are welcome to complete more than one option if they wish. The schedule for the week is light to permit students to focus on preparations for the term projects that will be presented during the last week of class.
Week 10 of the class will be devoted to term projects. Details of expectations for the term projects are provided in separate instructions. Briefly, these are synthesis activities with the following components:
Individual Term Projects – Description of a plan for an experiment of your choosing presented in the form of a poster. You will also be asked to critique some of the projects created by your classmates.
Group Project: Data Analysis – Analysis of data for a combined experiment using SAS. You will be divided into groups of about four students and each group will be given a data set to analyze. If anyone has a data set that you think would be suitable and you are willing to share, please contact your instructor at the beginning of the term. Groups may be self-selected by notifying your instructor earlier in the term. Otherwise, you will be assigned to a group.
Group Project: Presentatation of Results – Summary and interpretation of the data that you have analyzed. Each group will present their results, and students will be asked to comment on the work of their peers.
Instructional Objectives and Student Learning Outcomes:
Upon completion of the course, students should be able to:
- Identify objectives of a field, greenhouse or laboratory experiment and outline the scientific methods that would be used to meet those objectives.
- Describe approaches that a researcher can use to reduce experimental error in agricultural experiments. Select suitable plot sizes, shapes, and placement to control experimental error.
- Determine when blocking is needed and demonstrate how blocks are arranged in field experiments.
- Generate random numbers, summarize data, create graphs and perform simple statistical calculations using Excel (or comparable spreadsheet software).
- Describe the assumptions required for a valid ANOVA and apply diagnostic tools to determine if the assumptions are met. Utilize appropriate data transformations and discuss other approaches for analyzing data that do not satisfy ANOVA assumptions.
- Design an experiment, compute the components of an Analysis of Variance (ANOVA) using formulas in Excel, and interpret the results for the following experimental designs:
- Completely Randomized Design
- Randomized Complete Block Design
- Latin Square Design
- Split-Plot Design
- Strip-Plot Design
- Use SAS to import and analyze data, create graphs and interpret output for all of these experimental designs.
- Compare treatment means using appropriate mean separation techniques.
- Calculate the power of an experiment to detect differences among treatments. Determine optimal plot size and the number of replications needed to meet experimental objectives.
- Explain the difference between fixed and random effects and be able to interpret computer output from mixed model analyses.
- Distinguish nested and cross-classified factors in an experimental design. Explain the difference between subsampling and true replication. Compute an ANOVA for a nested design that includes subsamples using SAS and interpret the output.
- Design factorial experiments and compute an ANOVA using Excel and SAS. Explain the meaning of main effects and interactions and show how they impact the interpretation of results.
- Form appropriate orthogonal contrasts to answer specific questions raised by an experiment. Perform tests of significance and interpret results.
- Explain the purpose of repeated measures analyses and identify experimental circumstances for which they would be appropriate.
- Perform a combined analysis of data from multiple experiments using SAS and interpret the output.
- Select an efficient experimental design to meet the objectives of an experiment and justify your choice of designs.
Outline of Topics Covered
Week 1 Basic Principles and Review of Statistics
- Types of experiments
- Steps in experimentation
- Review of hypothesis tests and t tests
- Terminology used in field experiments
- Control of experimental error
- Types of variables
Week 2 Field Plot Fundamentals and Completely Randomized Designs
- Plot shape and orientation
- Border effects
- The importance of randomization
- Completely Randomized Design
Week 3 Experimental Design Strategies and Randomized Complete Block Designs
- Monday, Jan. 18 – Martin Luther King holiday (no class)
- Concepts of replication and blocking
- Randomized Block Design
- Optimum and convenient plot size
- Number of replications and power calculations
Week 4 Refining the Model
- Assumptions of the ANOVA
- Checking ANOVA assumptions and transformations
- Fixed, random, and mixed models
- Introduction to Generalized Linear Mixed Models
- First Test (on material from Weeks 1, 2, and 3) – Friday, Jan. 29, 2016
Week 5 More Designs + Mean Comparisons
- Latin Square Design
- Structured versus unstructured experiments
- Mean separation techniques
- Factorial experiments
- Main effects and interactions
Week 6 Factorial Experiments and Contrasts
- Orthogonal contrasts
- Regression in the ANOVA
- Orthogonal polynomial contrasts
Week 7 Different Plot Sizes within an Experiment
- Split-plot designs
- Strip-plot designs
- Repeated measures
- Second Test (material from Weeks, 4, 5, and 6) – Friday, Feb. 19, 2016
Week 8 Nested Designs and Combined Experiments
- Nested (hierarchical) designs
- Combined experiments (multilocational trials)
Week 9 Advanced Topics (Choose one option) + Project Work
- Option 1: Augmented Designs
- Option 2: Incomplete block designs, Lattice designs
- Option 3: Covariance analysis
- Option 4: Matrix algebra and regression
- Group Project - analysis of a combined experiment
Week 10 Final Projects
- Student proposals - poster session, Mon., March 7, 2016
- Presentation of group projects
- Final: Thursday, March 19, 2015 at 6:00 pm in CRPS 122
Tentative Recitation Schedule
Week 1 Introduction to SAS; Review of basic statistics
Week 2 One-Way ANOVA (CRD) (Excel and SAS)
Week 3 Two-way ANOVA (RBD), Power calculations
Week 4 ANOVA Assumptions, Transformations, Mixed Models
Week 5 Latin Square Design, Multiple Comparison Tests
Week 6 Factorials and Orthogonal Contrasts
Week 7 Split Plot, Strip Plot, Repeated Measures
Week 8 Across Site Analyses (Combined Experiments), Subsampling
Week 9 Special Topics: Augmented Designs, Covariance Analysis
Week 10 Special Topics: Lattice Designs