Stat-Ease
If you are having trouble viewing this email view it online.
 
Vol: 15 | No: 2 | Mar/Apr '15
Stat-Ease
The DOE FAQ Alert
     
 

Stat-Ease Statistical Group

Dear Experimenter,
Here’s another set of frequently asked questions (FAQs) about doing design of experiments (DOE), plus alerts to timely information and free software updates. If you missed the previous DOE FAQ Alert click here.

To open another avenue of communications with fellow DOE and Stat-Ease fans, sign up for The Stat-Ease Professional Network on Linked in. A recent posting features an answer to the question: “Does DX use parallel programming and/or GPUs in its designs and analyses of experiments?”.

 
Stats Made Easy Blog

 

 

 

 

 

 

 

 

 

 

-

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

1:  Newsletter alert: New issue of Stat-Teaser features a fun split-plot exercise plus a primer on aliasing
2:  Statistical Tool Alert: Stat-Ease, Inc. announces a strategic partnership with CAMO Software
3:  FAQ: Why does the ANOVA report not provide an F-test or p-value for blocks?
4:  Info alert: Case study for pharma, primer on DOE
5: Events alert: World Conference on Quality and Improvement (Nashville), Spring Research Conference (Cincinnati), 1st Asian DOE User Meeting (Goa)
6:  Workshop alert: California here we come!
 
 

PS. Quote for the month: Ronald Fisher’s advice on how to most quickly decipher the nature of things


- Back to top -


1: Newsletter alert: New issue of Stat-Teaser features a fun split-plot exercise plus a primer on aliasing

Check out the latest issue of our Stat-Teaser newsletter via this link. It leads with a detailing by me of a great way via an in-class exercise on paper helicopters to teach design and analysis of split plots using Design-Expert® software.  Next up in this double-feature edition is an informative article by Consultant Wayne Adams on how to interpret aliasing of effects.  This is tricky, but Wayne makes the statistics easy for experimenters who prefer not to get into too much math but really need to understand what they are getting into with a run-saving design.

Thank you for reading our newsletter.  We appreciate you passing along the link to the posting of the Stat-Teaser to your colleagues.


- Back to top -


2: Statistical Tool Alert: Stat-Ease, Inc. announces a strategic partnership with CAMO Software

I am very pleased to announce that we’ve partnered with CAMO Software for them to bundle Design-Expert with their Unscrambler® software for multivariate analysis (MVA). This makes it easy for those needing both MVA and DOE to get it all in one world-class toolset.

Stat-Ease Founder Pat Whitcomb and I will join CAMO at their User Meeting in Prague April 16-17 where I will give a briefing on our company and Pat will provide technical details on “Managing Uncertainty in a Design Space”.


- Back to top -


3: FAQ: Why does the ANOVA report not provide an F-test or p-value for blocks?

Original question from an Asian user:

“I want to assess the block's F and p-value but it does not appear in the ANOVA report.  Please advise.”

Answer from Stat-Ease Consultant Wayne Adams:
“Our software does not provide an F-statistic or a p-value for blocks because there is no statistically-valid test for them.*  Here are my suggested alternatives:

  • Imitate an F-statistic by dividing the mean square of the block by the mean square residual.  As a general rule, if this computation exceeds 4, then the blocks would probably have tested as significant if they had been set up as a factor in the randomized design.
  • Go to the block coefficients in your analysis of variance (ANOVA) report by clicking the Coefficients bookmark as shown below.

Coefficients Bookmark
Compute the range between the minimum and the maximum block coefficient.  This amount is the block effect.  If your client feels it is substantial, then they can conclude that the variable they blocked, such as raw material lots or equipment lines, probably affected their process.

It is assumed that experimenters have no interest in the effect of blocked variables, that is, they need to be blocked out.  However, if the real reason is that blocking simply accommodated a hard-to-change (HTC) variable, then a split-plot design should be used.  Split-plot designs, now available in version 9 of Stat-Ease software, conveniently restrict the randomization of the HTC factors, so long as there is some replication of the hard-to-change variable.  Then, presuming you do not over-ride the program’s recommend replication of the HTC(s), these factors that otherwise would be blocked can now undergo the F test in ANOVA, thus providing the desired p-value(s).”

* As to why, refer to the #1 answer to "why a p-value is not provided for variance from blocks" in the March 2006 DOE FAQ Alert.

(Learn more about blocking by attending the two-day computer-intensive workshop Experiment Design Made Easy.  Click on the title for a description of this class and link from this page to the course outline and schedule.  Then, if you like, enroll online.)


- Back to top -


4: Info alert: Case study for pharma, primer on DOE

The Jan/Feb issue of Pharmaceutical Manufacturing features a case study by VerGo Pharma Research Laboratories detailing how, with the aid of Design-Expert software, they ran an optimal three-factor experiment that led to a substantial reduction in their drug-development time.  See it here.

If you need a good icebreaker for experimenters balking at trying multifactor testing, I recommend “Understanding Design of Experiments, Common Questions and Misconceptions” by Matt Treglia published by Quality Digest and posted here.


- Back to top -


5: Events alert: World Conference on Quality and Improvement (Nashville), Spring Research Conference (Cincinnati), 1st Asian DOE User Meeting (Goa)

If you make it to the American Society of Quality (ASQ) World Conference on Quality and Improvement (WCQI) in Nashville, TN on May 4-6, please come to my detailing of how to respond when an experimenter says “I Really Would rather Not Randomize My Experiment!!!”.  While there, stop by booth 615 for a visit with me and/or my colleague Heidi.  Details on WCQI can be found here.

Our newest technical team-member Martin Bezener, along with Consultant Shari Kraber, will represent Stat-Ease at the Spring Research Conference (SRC) in Cincinnati, OH on May 20-22.  See the meeting details via this link. Martin will be giving a talk on "Practical Model Confirmation".

Stat-Ease and our reseller Systech are hosting our 1st Asian DOE User Meeting in Goa, India on May 27-29.  This extraordinary event is detailed here.  If you reside in that region do not miss this chance to get together with the Stat-Ease team and fellow users of our DOE software.

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


- Back to top -


6: Workshop alert: California here we come!

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 $400 discount when you take two complementary 2-day workshops that are offered on consecutive days.

*Take both EDME and RSM to earn $400 off the combined tuition!

** Take both MIX and MIX2 to earn $400 off the combined tuition!

See this web page for complete schedule and site information on all Stat-Ease workshops open to the public throughout 2015 (newly posted).  To enroll, scroll down to the workshop of your choice and click on it, or call Rachel Pollack at 612-746-2038.  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].


- Back to top -


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—Ronald Fisher’s advice on how to most quickly decipher the nature of things:

 
"No aphorism is more frequently repeated in connection with field trials, than that we must ask Nature few questions, or, ideally, one question at a time.  The writer is convinced that this view is wholly mistaken. Nature, he suggests, will best respond to a logical and carefully thought out questionnaire; indeed, if we ask her a single question, she will often refuse to answer until some other topic has been discussed.”

—R. A. Fisher

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, Brooks Henderson, and Martin Bezener
—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!

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

DOE FAQ Alert ©2015 Stat-Ease, Inc.
Circulation: Over 8900 worldwide
All rights reserved.


 
  Subscribe