BLOGS
StatsMadeEasy Blog
My wry look at all things statistical and/or scientific with an engineering perspective.
|
|
FAQ
Just the Trick to Constrain a Subset of Ingredients
Original question from a Senior Research Scientist:
“I want components A, B and C in my ink formulation to be kept between 4 and 8 percent in total, while keeping component D in a range of 1.5 to 5 percent. Help!”
Answer from Stat-Ease Consultant Shari Kraber:
“This can be handled easily with Design-Expert® software (DX) tools for multilinear constraints. Begin with a new Mixture Optimal (Custom) design. Dial up 5 components with the Total set at 100 %. For the individual constraints enter A, B, C each at 0-8% (DX will adjust the lower levels later), D at 1.5 to 5% (as you specified) and E from 0 to 100% (this provides ‘slack’ for the four primary ingredients). Click the [Edit constraints…] button and enter 4 < A+B+C < 8. After giving this the OK and pressing Next twice (due to multiple adjustments being required), DX will work out the correct ranges (if feasible). Press OK to accept.
Then proceed through the remainder of the design-building wizard to set up your mixture experiment. Easy!”
PS The multilinear constraint (MLC) tool is incredibly useful for crafting design spaces. It is ideal for processes that require avoidance of extreme conditions, e.g., too high a temperature for too long burning the product. For example take a look at this Design-Expert Optimal Design Tutorial. Formulators such as this ink chemist do very well by applying MLCs. An example that strikes home to me as a Minnesotan is mosquito repellant: Formulators can apply MLCs to vary the relative composition of various deterrents while keeping its total within a reasonable range relative to the lotion. Other uses for MLCs that come to mind are searching for synergistic combinations of surfactants, viscosifiers and the like—vital subsets in overall product recipes.
With input from my co-authors, I wrote up a complete section on MLC’s for Formulation Simplified : See Chapter 6, “Getting Crafty with Multicomponent Constraints”, page 101. If you run mixture experiments, I recommend you read this.
- Mark
|
|
WEBINAR ALERT 1
“DOE Crash Course for Experimenters”
This newly developed presentation by Stat-Ease Consultant Shari Kraber on September 30 at 10 AM CDT provides a briefing on DOE. It lays out what’s in it for experimenters who only know the traditional one-factor-at-a-time (OFAT) scientific method. If you practice OFAT (or know of others who do so), step up your design of experiments (DOE) know-how (or theirs) via this ‘heads up’ on multifactor testing. Shari will demonstrate what makes statistical DOE so effective for accelerating R&D. Register via this link (and/or please pass it along to those you know who experiment OFAT). If you cannot make it this time, watch for future dates of this new ongoing webinar, or register to get the recording of this one. |
|
WEBINAR ALERT 2
“How to Detect and Overcome Bad Data”
This talk by me on October 21 at 10 AM CDT will provide ways to handle results that fit badly. I will show how Design-Expert, via graphical tools, makes it easy to diagnose what went wrong—damaging outliers and/or a need for transformation. Attend my webinar to lessen your chances for incorrectly interpreting your experimental results. Register via this link and/or please pass it along to your colleagues. If you cannot accommodate the scheduling, register to get the recording. |
|
EVENT ALERT
MN ASQ Quality Conference: Talk and Half-Day Workshop
The 2020 Minnesota Quality Conference, presented via virtual venue, features two presentations by Stat-Ease Consultants:
- Deploying DOE to Predict and Improve Process Performance talk by Shari Kraber on Wednesday, November 4th from 12:45 pm to 1:45 pm CDT
- Design of Experiments Leading to Verification / Validation workshop by Shari and me on Thursday , November 4th from 1:00 pm to 4:30 pm CDT
To register for the Stat-Ease and other Quality Conference presentations, click here.
PS Do you need a speaker on DOE for a learning session within your company or technical society at regional, national, or even international levels? If so, contact me. It may not cost you anything if Stat-Ease has a consultant close by, or if a web conference will be suitable. However, for presentations involving travel, we appreciate reimbursement for travel expenses. In any case, it never hurts to ask Stat-Ease for a speaker on this topic.
|
|
WORKSHOP ALERT
Sharpen up on DOE—Sign up now before fall 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 distance-learning courses. To enroll in the workshop that suits you best, click Register, or email our Lead Client Specialist Rachel Poleke at [email protected].
PS If you lead a group of 6 or more colleagues, save money and customize content via a private workshop. For a quote, email [email protected]. |
|
|
“Lucky is he who has been able to understand
the cause of things.”
—Virgil.
|
|
|
Stat-Ease, Design-Expert and Statistics Made Easy are registered trademarks of Stat-Ease, Inc.
Circulation: Over 7500 worldwide
|
|
|
|
