At the end of this course, successful students will be able to
- Design and conduct an experiment that exhibits both a treatment design and randomization design that allow for the testing of differences between the levels of a single or multiple treatments of interest.
- Given a description of an experiment, correctly identify common design elements, including (a) Crossed factorial designs with interactions, (b) Nested factorial designs, (c) Blocking factors, (d) Nuisance variables, (e) Split-plot designs, (f) Repeated measures, and (g) Random effects.
- Specify an appropriate statistical model for observations resulting from a designed experiment exhibiting the elements in item 2.
- Identify estimable terms in a statistical model for an experiment, find the least squares estimator of estimable terms, and specify the statistical distribution of the estimator.
- Conduct and correctly interpret statistical hypothesis tests for the overall effect of a treatment and for the effects of contrasts.
- Correctly employ methods for multiple comparisons to control the experimentwise error rate when multiple hypothesis tests are conducted.
- Examine model assumptions using residual plots and a description of the experiment. Apply remedial measures such as transformations to the response when such transformations improve adherence to modeling assumptions.
- Analysis of variance for single factor designs,
- Analysis of variance for multifactor designs,and
- Response surface methodology.
Dr. Ephraim Hanks is the primary author of these course materials.
This course will use the statistical software program SAS. See the Statistical Software page for more information.
A.Dean and D. Voss. (1999), Design and Analysis of Experiments. ISBN-13: 978-1475772920 (available for free download from the PSU Library website)
Applied Linear Statistical Models by Kutner, Nachtsheim, Neter, and Li, 5th Edition. (this text is recommended as a reference, but not required).
- STAT 200, STAT 240, STAT 250, STAT 301 or STAT 401