- Schedule of Classes - July 17, 2019 9:11PM EDT
- Course Catalog - July 17, 2019 9:12PM EDT
Course information provided by the Courses of Study 2019-2020.
Statistical analysis of experimental data and processes, and the design of experiments are increasingly critical in new product design and manufacturing. Approximately the first 40% of the course will review the fundamentals of probability and statistics through formal axioms and computational use of bootstrap and Monte Carlo methods. The review will be in the context of industrial processes and is at the level of the Dekking text, with occasionally deeper views of subjects such as the origins of the Gaussian distribution and the derivation of the central limit theorem. Common probability distribution functions, including binomial, Poisson, exponential, Gaussian, Weibull, and Cauchy-Lorentz are discussed with examples. These principles are then applied in three segments to critical applications in engineering. Data analysis and model parameter estimation are covered (25%), including characterization of sources of error and uncertainty, least squares fitting, and parameter correlation. Formal design of experiments (DOE) methodology is covered (25%) for identifying key parameters and extracting trends in product and process development. Finally, the course will cover statistical process control (10%), as practiced in industry to establish and maintain manufacturing yield.
When Offered Fall, Spring.
Prerequisites/Corequisites Prerequisite: MATH 2930 and MATH 2940, some familiarity with statistics/probability, programming competence.
Or send this URL: