AMS 582, Design of Experiments
Discussion of the accuracy of experiments, partitioning sums of squares, randomized
designs, factorial experiments, Latin squares, confounding and fractional replication,
response surface experiments, and incomplete block designs. Co-scheduled as AMS 582
or HPH 699.
Prerequisite: AMS 572
3 credits, ABCF grading
NOT BEING OFFERED FOR THE FORESEEABLE FUTURE
Recommended Text:
"Design and Analysis of Experiments, 10e Enhanced eText with abridged Print Companion"
by Douglas C. Montgomery, Wiley Publishing; ISBN: 978-1119593409 (earlier editions are acceptable)
Fall Semester
Learning Outcomes:
1) Extend knowledge of probability theory.
* Central chi-square and central F-distributions.
* Non-central chi-square and non-central F-distributions.
* Multiple comparisons procedures including Bonferroni’s inequality, Scheffe’s
multiple comparison procedures, and Tukey’s multiple comparison procedures.
* Decomposing chi-square sums of squares.
* Expected value and variance of sums of squares.
2) Learn classical statistical designs.
* One-way layout.
* Randomized block designs.
* Latin squares, Graeco-Latin squares, hyper Graeco-Latin squares including
designs with replications.
* Two and three way layouts.
* designs.
* Random effect models.
* Mixed models.
3) Power and sample size computations.
4) Learn the statistical computing package of the student’s choice and apply it to obtain the statistical model that generated a set of synthetic data.