Design of Experiments for QbD
Course Description
Statistical experimental design, also known as Design of Experiments or DOE, is a core component of QbD (Quality by Design), Robust Design, Lean 6 Sigma, and 6 Sigma quality initiatives. This DOE course will cover the fundamental aspects of experimental design and the practical application of those designs. The major topics to be covered include screening DOEs (fractional factorial designs) for the efficient identification of important factors, response surface/optimization designs (CCD, Box-Behnkin, etc) for identifying the optimum factor settings for your problem, and how to choose and construct the appropriate design.
Other practically important aspects of DOE will be discussed throughout the course including the identification of factors for investigation, identification of (potential) sources of variation, characterization of the measurement system, proper execution of the DOE experiments, statistical evaluation of factor significance and construction of the model, and uses of the regression models. Special attention will be paid to developing designs that work well with multivariate calibration methods, including cross-validatable designs and selection of candidate reference samples based on measured values (reduceNNsamples). Examples will be used throughout the course to illustrate the various aspect of the DOE modeling process. Examples will be used throughout the course to illustrate the various aspect of the DOE modeling process. The course includes hands-on computer time for participants to work example problems using PLS_Toolbox and MATLAB.
Prerequisites
None, but some exposure to statistics is very helpful, including hypothesis testing, ANOVA, and regression analysis.Linear Algebra for Chemometricians, MATLAB for Chemometricians or equivalent experience highly recommended.
Course Outline
- Introduction
Why design experiments? - Screening Designs
Identification of important factors
Fraction Factorial Deisgns
Response Surface/Optimization Designs - Practical Aspects
Identifying sources of variation
Proper execution of experiments
Evaluation of significance
Construction of a model - Working with Multivariate Calibration
Designing for cross-validation
Selection of samples for reference measurement