Statistically designed experiments are the efficient allocation of resources to maximize the amount of information obtained with a minimum expenditure of time and effort. Design of experiments is applicable to both physical experimentation and computer simulation models. This course covers the principles of experimental design, the analysis of variance method, the difference between fixed and random effects and between nested and crossed effects, and the concept of confounded effects. The designs covered include completely random, randomized block, Latin squares, split-plot, factorial, fractional factorial, nested treatments and variance component analysis, response surface, optimal, Latin hypercube, and Taguchi. Any experiment can correctly be analyzed by learning how to construct the applicable design structure diagram (Hasse diagrams).
Course prerequisites: 
Multivariate calculus, linear algebra, and one semester of graduate probability and statistics (e.g., 625.403 Statistical Methods and Data Analysis). Some computer-based homework assignments will be given.
Course instructor: 
Bodt

View Course Homepage(s) for this course.

Course all programs: 
Applied and Computational Mathematics
Data Science