About the Course
The design and analysis of experiments, using plants, animals, or humans, are an important part of the scientific process. Proper design of an experiment, apart from its proper analysis and interpretation, is important to convince a researcher that your results are valid and that your conclusions are meaningful. Were enough subjects (experimental units) tested, for example, to detect the desired difference? Were enough replications used to be able to draw wide inferences? Were proper procedures used to randomize the treatments to the experimental units or, if you prefer, the experimental units to the treatments?
We will start with a review of statistics: basic definitions, linear regression, and analysis of variance. The course will then focus on the fundamental principles of design, e.g., the experimental unit, replication, and randomization, and on characteristics of several important designs, e.g., completely randomized and randomized block designs. We will consider fixed, random, and mixed models; the relative efficiency of designs; and the size of the sample to make a valid test. We will discuss methods to test treatment effects, e.g., planned orthogonal contrasts and unplanned multiple comparisons, and how these methods might influence your design. We will also discuss use of blocking versus use of covariates in analysis of variance.
Active Learning Format
To engage you in developing your skills in experimental design, the course is in the format of “active learning” -- a combination of an informative PowerPoint® lecture, with worked examples, followed by a practical group exercise. During the first two days, there will be exercises to practice the theory of designing experiments. The last day is devoted to specific “real-life” problems from you, the participants, who will present and discuss your designed experiments.
By the end of this course, you should see improvement in your ability to:
• understand the principles and theory of designing experiments
• understand and use the terminology of experimental designs
• present and discuss the concept of an experimental design
• cooperate in a team environment
• work quickly
It is not the intention of the course to teach the “statistical analysis” of the experimental design, which we believe, for the most part, simply follows from the design itself. Emphasis will be on the design of the experiment, not on its analysis.
The Target Audience
The course is designed for researchers who have some experience in designing experiments: those who are at the beginning of their scientific careers, and those who have more experience and want to refine their statistical skills. We assume knowledge of descriptive statistics, hypothesis testing, simple and multiple regression, and analysis of variance. We urge participants who do not have that knowledge to review those topics before the start of the course. Scientists from various disciplines are welcome to attend.
A workbook (reader) will include notes from the PowerPoint® presentations and exercises.
Wiebe J. Koops
Design of Experiments 7 - 9 October 2015
Provisional Program (1)
09.00 - 09.15 Opening remarks and introductions
09.15 - 10.30 Statistics review and exercise
10.30 - 10.45 Coffee/Tea
10.45 - 12.00 Sample size, more sample size, and exercise
12.00 – 12.30 Introduction to theory of design
12.30 - 13:30 Lunch
13.30 - 14.30 Basic definitions for design and exercise
14.30 - 14.45 Expected mean squares
14.45 – 15.15 Completely randomized design and exercise
15.15 - 15.30 Coffee/Tea
15.30 - 16.30 Orthogonal contrasts in Anova and exercise
16.30 - 17.00 Writing statistics
09.00 - 10.00 Randomized complete block design
10.00 - 10.15 Coffee/Tea
10.15 – 10.45 Exercises
10.45 - 11.30 Using blocks or covariates in Anova
11.30 - 12.30 Exercises
12.30 - 13.30 Lunch
13.30 – 14.45 Split-plot design and exercise
14.45 - 15.30 Latin square design
15.30 - 15.45 Coffee/Tea
15.45 - 17.00 Latin square design and exercises
09.00 – 10.15 Real-Life problems
10.15 - 10.30 Coffee/Tea
10.30 - 11.15 Work on real-life problems in groups
11.15 - 12.30 Presentations of real-life problems by groups
12.30 - 13.30 Lunch
13.30 - 14.45 Real - life problems
14.45 - 15.00 Coffee/Tea
15.00 – 15.45 Work on Real - life problems in groups
15.45 - 16.45 Presentations of real - life problems by groups
16.45 – 17.00 Closing remarks and evaluation
(1) Times are approximate.
For WIAS PhD students with an approved TSP € 125 (WIAS pays 75% of the fee)
For other PhD students and WIAS staff there is a fee of € 500
All others pay € 750
Location: in Wageningen (exact location to be announced later)