Thanks for a great 2023 Online DOE Summit!

Stat-Ease hosts the premier annual conference on practical applications of industrial design of experiments (DOE). Check back in 2024 for information about the next DOE conference.

Missed it?

All our presenters' abstracts are listed below, along with links to their bios & slides, and the recording on our YouTube channel. Or, click the link below to go straight to the playlist on YouTube!

2023 Online DOE Summit Playlist on our channel: Statistics Made Easy by Stat-Ease

Tuesday, October 24, 2023

Masterful experiment delivers delectable chocolate chip cookies

Mark Anderson, Stat-Ease
Watch the recording | View the slides

Kicking off the 2023 Online DOE Summit, Mark’s presentation is sure to hold your attention while demonstrating key DOE tools and methodology. He spells out a delightful baking experiment that illustrates advanced statistical tools for:

• Combining mixture components with process factors
• Dealing with hard-to-change variables.

His talk also provides inspiration for coming up with clever ways to measure sensory attributes such as cookie crispiness. Attend this talk for the fun and the education!

Application of DOE in the Development of an Alcoholic Beverage

Doug Scott, Optimal Formulations LLC
Watch the recording | View the slides

Craft seltzers, sodas, teas, and ready to drink cocktails (RTD’s) have recently gained popularity in the alcoholic beverage industry. This trend is an effort to offer products and experiences for those that do not enjoy craft beer, or desire an alternative to beer for a change of pace. These products are typically offered in many different flavor varieties which can change seasonally or with the introduction of new flavors over time. The relative simplicity of these formulas lends itself well to the application of Design of Experiments for fast, efficient, and thorough formulation understanding.

The primary measures for development of products such as these is experientially based: attribute and liking grading. Sensory data is inherently variable and subjective, and can be difficult to analyze and interpret. No single analysis approach can be guaranteed to tell the whole story; this is particularly true if the formulas contain polarizing ingredients and if preference is the primary measure. In this presentation, a watermelon-lime-mint flavored vodka soda is explored via DOE in a trained sensory panel. The study design is a split-plot combined design with 3 flavor components and total flavor load as variables. Multiple analysis approaches will be shared which collectively elucidate the behavior of the system and aid in the identification of a polarizing flavor component.

What Teaching and the Practice of DOE Teaches Us About Deriving Meaning from any Data

Steve Zagarola, Northwest Center for Performance Excellence (NWCPE)
Watch the recording | View the slides

The most effective experimenters are those that have a fundamental grasp of five basic tenets of effective experimentation. Practicing those tenets as we design and interpret experiments will inevitably lead to a realization of some universal truths about any exercise whose goal is to derive meaning from any data -- whether via a designed experiment or passive observation.

In this presentation, Steve Zagarola illustrates that truth with an example of introducing the five basic DOE tenets to novice experimenters. In the teaching example, he capitalizes on series of successfully completed experiments whose objective was to optimize one manufacturer’s parts design for robustness to variation to the inevitable variation in their customers’ manufacturing processes. The presentation begins with a basic description of DOE and its utility, introduces a case study used to demonstrate the five fundamental tenets of effectively designed experiments and concludes by reflecting on what the tenets and their practice tell us about deriving meaning from any data – how to view it, the pitfalls, what to look for and how to view what we learn from the data.

Wednesday, October 25, 2023

DoE in the field of nuclear waste management

Erik Coppens, Belgian National Agency for Radioactive Waste and Enriched Fissile Materials (ONDRAF/NIRAS)
Watch the recording | View the slides

In the frame of the safe disposal of nuclear waste, ONDRAF/NIRAS (Belgium) has submitted a license application for the exploitation of a near surface facility for the disposal of short-lived low and intermediate level waste. A significant part of waste intended to be disposed of in the surface repository is Pu-contaminated. The mobility of Pu through engineered barriers, like concrete or mortar, is highly affected by the sorption properties of these barriers surrounding the waste in the disposal facility. The presented case studies aim to quantify the sorption of Pu to an engineered barrier while coping with multiple uncertainties. The experimentation included a factorial screening study, followed by response surface studies, with further augmentation with replication and validation points.

RSM Saves the Circuit Board

Richard Williams, Stat-Ease
Watch the recording | View the slides

A computer circuit board manufacturer encountered issues using commercial thermal interface materials for adhering heat transfer lids onto computer chips. A problem-solving team was brought in to evaluate the situation. Multiple causation theories were proposed, and the lead root cause concept was evaluated using a 3-factor response surface (RSM) DOE. Thermally conductive adhesives transfer heat emitted by chips to the external environment. However, sporadic excessive voids in the adhesive had degraded performance and led to scrapping computer chips at the manufacturer. An effective solution was urgently needed. The RSM confirmed root cause, provided processing guidelines to the circuit board manufacturer, and allowed adhesive specifications to be created by using tolerance interval valuation. Implementation of the finding resulted in complete elimination of excessive adhesive voids.

The Latest & Greatest in Design-Expert® and Stat-Ease® 360

Dr. Martin Bezener, Stat-Ease
Watch the recording | View the slides

After decades of continuous development, Design-Expert® software (DX) leads the field for making design of experiments (DOE) easy for scientists and engineers. In response to many requests from loyal users to expand our statistical toolkit, we are proud to now produce Stat-Ease® 360 (SE360). With DX at its core, SE360 adds advanced features for statistics and engineering, as well as sophisticated application-programming-interface (API) tools. This webinar provides a briefing on the major innovations now available with SE360, and bit of what's in store for the future.