BLOGS
StatsMadeEasy Blog
My wry look at all things statistical and/or scientific with an engineering perspective.
|
|
FAQ
In a pickle: How to design a mixture experiment with only two microbials at a time
Original question from a Food Scientist:
“We have done our screening and have identified 5 antimicrobials that could work to extend the shelf-life of one of our products. We would like to run a mixture design to help us determine the best antimicrobial combinations and amounts in the product. When I set up the design, the software is formulating with a combination of all 5 antimicrobials. I wanted to know if there is a way or how I can write a constraint that will only design a maximum of two antimicrobials in the pickle at a time. The water amount will float to achieve 100% ingredients in the finished product.”
Answer:
First off, if you can see your way clear to allowing all 5 antimicrobials (AMs) for experimental purposes only, you will be best off, IMO. This will provide a predictive model most expeditiously and solidly. Assuming you see two-component synergism and/or antagonism this will be evident by the two-letter terms in the coded model being significant with the signs being positive or negative; respectively. Then when you do the numeric optimization, systematically do what-ifs on two of the AM's at a time by setting all others equal to zero.
If you really must only put in two antimicrobials, do a combined design of three mixture components—AM1, AM2 and water, with the two AMs specified by the 10 possible combinations (5 take 2) laid out as a categorical factor.
|
|
EVENT ALERT
2021 Online DOE Summit
The Stat-Ease 2021 Online DOE Summit will be presented September 28-29 from 10am to 2pm US Central Time. It features an impressive lineup of experts providing valuable briefings on cutting-edge statistical tools, methodology and inspiring case studies:
- (Keynote Day 1) Martin Bezener (President & CTO, Stat-Ease):
Stat-Ease® 360 Widens the Horizon of Its World-Class DOE Software
- Gregory Hutto (Wing Operations Analyst, US Air Force):
The Tooth Fairy in Experimental Design: White Lies We Tell Our Software
- Drew Landman (Professor, Old Dominion University):
An I-Optimal Split-Plot Design for eVTOL Tilt-Rotor Performance Characterization
- Jason Pandolfo (Research Scientist, Quaker Chemical):
Using Logistic Regression to Predict the Stability of Metalworking Fluid Emulsions in Varying Water Quality Conditions
- (Keynote Day 2) Hank Anderson (VP Software Development, Stat-Ease):
Python Integration with Stat-Ease 360 - A Tutorial
- Oliver Thunich (Statistics Consultant, STATCON GmbH):
Adjusting a DOE to Unpredictable Circumstances
- Steven Mullen (Senior Scientist, Cook Medical):
Improving Process Understanding of an IVF Cell Culture Incubator via Response Surface Methodology
- Gregory Perrine (Research Scientist, Georgia-Pacific):
Debonder Formulation Optimization Using a KCV Mixture/Process Design in Paper Handsheets
|
|
WEBINAR ALERT
Free webinars—Sign up now to take Advantage
This coming October 13, I will present "Breakthrough DOE Tools for Elastomer Science and Technology". For a description and link to the free registration, follow this link.
On November 10, Martin Bezener will provide a briefing on space-filling designs and Gaussian-process modeling for deterministic computer experiments—new tools coming with the release of Stat-Ease 360. More details and a registration link for this enlightening talk will be posted soon to our Events/Webinars webpage.
Click here to view the times, descriptions and registration links for all upcoming live webinars. Sign up now to advance your DOE know-how!
|
|
WORKSHOP ALERT
Sharpen up on DOE—Enroll before classes fill
You can do no better for quickly advancing your DOE skills than attending a Stat-Ease workshop. Our expert instructors provide you with a lively and extremely informative series of lectures interspersed by valuable hands-on exercises. Enroll early to ensure your spot!
See this web page for the complete schedule of upcoming Stat-Ease courses. To enroll in the workshop that suits you best, click Register on that webpage, or click here to contact us.
PS If you lead a group of 6 or more colleagues, save money and customize content via a private workshop. For a quote, please contact us.
|
|
“Our success at Amazon is a function of how many experiments we do per year, per month, per week, per day. [However,] it's not an experiment if you know it's going to work.”
—Jeff Bezos
|
|
Stat-Ease, Design-Expert and Statistics Made Easy are registered trademarks of Stat-Ease, Inc.
Circulation: Over 4000 worldwide
|
|
|
|