Topics in the body text of this DOE FAQ Alert are headlined below (the expert ones, if any, delve into statistical details):

PS. Quote for the month: Not promising to tell nothing but the truth.

1: Newsletter alert: September issue of the Stat-Teaser details how “Statistics Point the Way to Save Time Commuting,” discusses the pitfalls for “Regressing the Rupee’s Plunge” and features the Stat-Ease IT Team

Many of you have received, or soon will, an e-mailed link to the latest Stat-Teaser, but if you have not seen this yet, go here. It features a report by me on my experimentation on alternative routes to work, which may be well worth trying for yourself.  This Stat-Teaser also provides a fun and enlightening study by Stat-Ease Consultant Brooks Henderson as to why the Indian currency plummeted this year.  Also, check out the picture of our IT Team, which includes my son Hank.  They are doing great work! : )

2: FAQ: Using tolerance intervals (TI) to size a Quality by Design (QbD) experiment

Original Question from an R&D Specialist:

“We use Design-Expert software in our pharmaceutical company.  Your June webinar “Quality by Design for Pharma and Beyond,”* which demonstrated the application of a tolerance interval (TI) for sizing an experimental design, really drew my attention.  Please clarify these primary elements for me so I can achieve quality by design (QbD) via DOE:

1. Where does the half-width (d) come from?
2. How do I estimate the experimental error(s)?
3. What should I do with multiple responses?”

Answer from Stat-Ease Consultant Wayne Adams:

“The “d” for a tolerance interval is the absolute value of the difference between the closest specification and what you believe the response value will be.  That’s the easy one.

Estimated standard deviation(s) can come from a number of sources.  Best is a value computed from data gathered from actual production.  Better yet is if you successfully completed a designed experiment—then simply read off the standard deviation found below the analysis of variance (ANOVA).  Next best is to use the standard deviation from the same response measures on a similar product.  If neither of these is available, then a small pilot study could be conducted to calculate a standard deviation.  The last option, if you have no data and time is of the essence, is to simply make an educated guess on “s”.  Prior data is NOT required.

Calculate the d/s ratio for all critical-to-quality response.  Then use the smallest ratio to size the design.  Following these steps will greatly improve your chances of achieving QbD via DOE.”

3: FAQ: Can Design-Expert compute analysis of variance (ANOVA) on happenstance data that did not come from a designed experiment?

Original Question from a Coatings Chemist:

“I have a question which may be unusual.  If we have a set of process data already, can Design-Expert perform ANOVA on it, even though it was not generated by design.”

Answer from Stat-Ease Consultant Wayne Adams:

“Yes it can.  The easiest method is to use a historical design found under the response surface tab.  Enter the minimum and maximum factor limits, the number of rows in the data set and response name(s).  Then paste the actual data into the blank spreadsheet (design layout).  See this tutorial for more details.

Watch out for factors being overly correlated—this makes modeling difficult.  Also, if the space is poorly covered, then be wary of predictions in the open areas.”

(Learn more about modeling by attending the two-day computer-intensive workshop Response Surface Methods for Process Optimization.  Click on the title for a complete description.  Link from this page to the course outline and schedule.  Then, if you like, enroll online.)





4: Info alert: DOE improves yield of active pharmaceutical ingredient (API); mixture design catalyzes development of a rubber-based product

The digital home of Pharmaceutical Manufacturing magazine details here how “DOE Improves Throughput in Manufacturing of Key Intermediate” for a pharmaceutical producer.  Check it out!

Elastomer chemists seeking details on the application of DOE to optimizing their formulations should pay close attention to “Development of a Rubber-Based Product Using a Mixture Experiment: A Challenging Case Study” published by Progress in Rubber, Plastics and Recycling Technology in Volume 29, Number 3, 2013.  Read the introduction here.  Purchase the article (free for PRPRT subscribers) at this site or contact co-author Greg Piepel at [email protected].

5: Webinar alert: How many runs do I need? How to use Power and Precision to Size Factorial and Mixture Designs

On Tuesday, October 15th, at 8 PM CDT* Stat-Ease Consultant Brooks Henderson will provide the first of three repeated briefings on “How many runs do I need?  How to use Power and Precision to Size Factorial and Mixture Designs.”  This free webinar, presented at an intermediate level statistically, will begin with a review of power calculations to determine if a factorial design provides enough runs to detect important effects.  Power, however, is not the appropriate tool to evaluate mixture and response surface method (RSM) designs.  To properly size these experiments for the optimization of products and processes, we advise using fraction of design space (FDS) as a tool.  To learn about power, FDS and how to apply these measures appropriately for sizing experiment designs—including how to determine a design space that meets specifications for Quality by Design (QbD), sign up for this webinar by Brooks.

Space is limited.  Reserve your Webinar seat now at by clicking one of the links below:

1. Tuesday, October 15, 2013 at 8:00 pm USA-CDT (for Asia and Australia)
2. Thursday, October 17, 2013 at 11:00 am USA-CDT
3. Friday, October 18, 2013 at 6:30 am USA-CDT (for Europe and India)

If this is your first Stat-Ease webinar, see these suggestions on how to be prepared.

Stat-Ease webinars vary somewhat in length depending on the presenter and the particular session: Plan for 45 minutes to 1.5 hours, with 1 hour being the target median.  When developing these one-hour educational sessions, our presenters often draw valuable material from Stat-Ease DOE workshops.

Again, attendance may be limited, so sign up soon via the link above.  Direct any questions you may have to our Communications Specialist, Karen Dulski, via [email protected].  However, if this relates to audiovisual issues, please first research help provided online by GotoWebinar.

If you cannot schedule any of these webinars, take advantage of the recording to be posted after the series of live events.

*(To determine the time in your zone of the world, try using this link.  We are based in Minneapolis, which appears on the city list that you must manipulate to calculate the time correctly.)

6: Events alert: “Practical DOE ‘Tricks of the Trade’”

Stat-Ease Consultant Pat Whitcomb with present “Practical DOE ‘Tricks of the Trade’” at two conferences in the coming months:

• Annual Conference of the European Network for Business and Industrial Statistics (ENBIS) in Ankara, Turkey on September 16-18—see meeting site here
• Annual Fall Technical Conference (FTC) in San Antonio, Texas, on October 17-18, co-sponsored by the American Society for Quality (ASQ) Chemical & Process Industry Division (CPID) and Statistics Division; and American Statistical Association (ASA) Section on Physical and Engineering Sciences (SPES) and Section on Quality & Productivity (Q&P)

Pat will lay out a series of real-life case studies that illustrate a few useful “tricks of the trade” for successful design of experiments:

• Using standard error to constrain optimization
• Employing Cpk (or Ppk) to optimize your DOE
• Combining categoric factors to avoid improbable combinations
• Applying mean bias correction to a transformed response

This practical advice on DOE will enhance the application of this powerful statistical tool for experimenters.

Click here for a list of upcoming appearances by Stat-Ease professionals.  We hope to see you sometime in the near future!

7: Workshop alert: See when and where to learn about DOE

All classes listed below will be held at the Stat-Ease training center in Minneapolis unless otherwise noted.  If possible, enroll at least 4 weeks prior to the date so your place can be assured.  Also, take advantage of a $395 discount when you take two complementary workshops that are offered on consecutive days.

• Experiment Design Made Easy (EDME)
• October 22-23
• December 10-11*
  
  
• Response Surface Methods for Process Optimization (RSM)
  • December 12-13*

*Take both EDME and RSM in the same week to earn $395 off the combined tuition!

• Mixture Design for Optimal Formulations (MIX)
  • November 5-6**
    
    
• Advanced Formulations: Combining Mixture & Process Variables (MIX2)
  • November 7-8**

**Take both MIX and MIX2 in the same week to earn $395 off the combined tuition!

See this web page for complete schedule and site information on all Stat-Ease workshops open to the public.  To enroll, click the "register online" link on our web site or call Shari at 1-612-746-2035.  If spots remain available, bring along several colleagues and take advantage of quantity discounts in tuition.  Or, consider bringing in an expert from Stat-Ease to teach a private class at your site.  Once you achieve a critical mass of about 6 students, it becomes very economical to sponsor a private workshop, which is most convenient and effective for your staff.  For a quote, e-mail [email protected].

I hope you learned something from this issue. Address your general questions and comments to me at: [email protected].

Please do not send me requests to subscribe or unsubscribe—follow the instructions at the end of this message. Sincerely,

Mark

Mark J. Anderson, PE, CQE
Principal, Stat-Ease, Inc.
2021 East Hennepin Avenue, Suite 480
Minneapolis, Minnesota 55413 USA

PS. Quote for the month—not promising to tell nothing but the truth:

"Statistics is about reasonable ways of dealing with uncertainty.  We value reasonableness, not truth.”

—Kaiser Fung, author of Numbers Rule Your World and Numbersense.

Trademarks: Stat-Ease, Design-Ease, Design-Expert and Statistics Made Easy are registered trademarks of Stat-Ease, Inc.

Acknowledgements to contributors:
—Students of Stat-Ease training and users of Stat-Ease software
—Stat-Ease consultants Pat Whitcomb, Shari Kraber, Wayne Adams and Brooks Henderson
—Statistical advisor to Stat-Ease: Dr. Gary Oehlert
—Stat-Ease programmers led by Neal Vaughn
—Heidi Hansel Wolfe, Stat-Ease sales and marketing director, Karen Dulski, and all the remaining staff that provide such supreme support!

For breaking news from Stat-Ease go to this Twitter site.

DOE FAQ Alert ©2013 Stat-Ease, Inc.
Circulation: Over 6300 worldwide
All rights reserved.