Case Studies and White Papers

Success with DOE

Published: April 2004
Author: Mark Anderson

A basic primer, taken from "DOE Simplified" text, on underlying statistics and simple forms of DOE.

Publication: Quality

Published: March 2004
Author: Joseph Albanese

Changing and then re-testing just one parameter at a time still seems to be the norm for the formulation chemist, but it is not the most productive approach. In fact, this shotgun approach increases the probability of missing the best possible finished product. A more reliable and expedient method of optimizing a formulation is by design of experiments (DOE).

Publication: Cosmetiscope

Published: March 2004
Author: Exatec LLC

Researchers at Exatec, LLC, determined that the oscillating sand test reveals better wear assessment information for polycarbonates. This finding has allowed the company to optimize coating processes.

Publication: Paint & Coatings Industry

Published: March 2004
Author: Stepan Co.

To simplify formulation tasks when searching for hot-melt solutions, Stepan Co. developed a design of experiments (DOE) mapping' approach to their new ortho-phlathic-based polyol products. They wanted to discover how the products work within their specific applications. Requires login to view.

Publication: Adhesives & Sealants Industry

An Efficient Approach to Cell Culture Medium Optimization - A Statistical Method to Medium Mixing

Published: January 2004
Authors: J Gifford, A Albee, Z.W. Deeds, B Delong, K Kao, J.S. Ross, M.V. Caple

Sigma-Aldrich Biotechnology used mixture-DOE to increase cell growth and productivity for a particular recombinant CHO clone. Their simple, yet powerful, media-mixing experiments, combined with DOE software, allowed the researchers to rapidly elucidate an optimal medium mixture.

Publication: The NY Chapter Society of Cosmetic Chemists' newsletter

Combining Computer-Aided Statistical Design of Experiments with Traditional Design of Experiments to Meet EC2000 Criteria

Published: January 2004
Author: David Mills

New ABET criteria require that chemical engineering students be able to モdesign and conduct experiments. Experimental design may be interpreted as either developing methods and procedures to achieve experimental goals, or as statistical Design of Experiments (DOE). Auburn University's Dept. of Chemical Engineering incorporates both approaches in their unit operations lab course to satisfy EC2000 criteria and achieve beneficial learning outcomes.

Publication: American Society for Engineering Education

Published: January 2004
Author: Timothy Ebert

Mixture design is used to develop a predictive model for estimating an entire range of glaze colours with far fewer test tiles than are normally required.

Publication: Ceramics Technical

Keys to Successful Designed Experiments

Published: January 2004
Author: Shari Kraber

We can improve experimentation results by studying organizations that have experienced both frustrations due to poor experimentation methodology and satisfaction from successful applications. This paper identifies eight factors essential to successful experimentation. A solid understanding of these key factors is the foundation to a successful design of experiments program.

Unearthing Optimum Soil Treatments

Published: January 2004
Author: Steve Trost

Weak subgrade soils are often chemically treated, or modified, to add strength and stability to support the heavy construction vehicles required for building highways. DOE was used to develop a treatment that enabled contractors to quickly establish stable subgrades.

Publication: Hard Hat News

Practical versus Statistical Aspects of Altering Central Composite Designs

Published: July 2003
Author: Mark Anderson

For many central composite designs (CCDs), particularly large ones, the usual alphas put the axial points outside the region of operability. A CCD with an alpha of one, known as a "face centered design" (FCD), avoids this problem by drawing the axial point back onto the face of the hyper cube. However, as the number of FCD factors increase, the correlation among the squared terms in the quadratic in the face-centered cube also increases. For k>5 this causes the variance inflation factors (VIFs) associated with the squared terms to become quite high. As a compromise between FCD and standard CCD, this white paper provides the case for a "practical" alpha of the fourth root of the number of factors (k). For k of 5 or more, this practical alpha balances statistical properties with operational necessities.

Publication: 2003 Joint Statistical Meetings Roundtable Luncheon