08APR2014
Note: The links below are no longer current, however I will leave them in place to show the great selection of free webinars that Stat-Ease offers. An up-to-date list of Stat-Ease webinars and training materials may be found here: http://www.statease.com/training/webinar.html.
Stat-Ease products and training are great resources for those who work with DOE. Whether or not someone uses Stat-Ease software, these webinars provide a good overview of the applied DOE theory.
"An Introduction to Design-Expert Software for Design of Experiments (DOE)" (If you missed this webinar, just click on the link above to view a recording of it at your convenience.) For a PDF of the slides only, click here.)
Presented on Thursday, November 3, 2011 Time: 12:30 PM - 2:00 PM CDT.
Pat Whitcomb and Shari Kraber introduce tools for multifactor process improvement, product development and optimization. Three case studies are presented, illustrating the use of factorial design, response surface design, and mixture design. These designed experiments are shown, along with their ties to AAO software for Beckman Coulter Biomek FX equipment.
"Basics of Response Surface Methodology (RSM) for Process Optimization, Part 1" (If you missed this webinar, just click on the link above to view a recording of it at your convenience. For a PDF of the slides only, click here.) Intermediate Level
Encore presentation was presented on Tuesday, October 18th at 10:30 am. Was 1st presented on Thursday, September 8th, 2011 at 2 pm CDT.
Response Surface Methods (RSM) can lead you to the peak of process performance. In this webinar, Shari Kraber introduces the fundamental concepts of response surface methods (RSM). You will look at the central composite design and learn about multiple response optimization while working through an actual case study application.
"Practical Aspects of Algorithmic Design of Physical Experiments" (Click on the title at left to download, 6.83 MB) Intermediate Level
Was presented on Wednesday, October 12th, 2011 at 1 pm CDT to the ASQ Stat Division.
"How to Get Started with DOE" (Click on the title at left to download, 843 KB) Beginner Level
Was presented on Thursday, April 28th, 2011 at 2 pm, Thursday, June 9th at 10:30 am, Wednesday, June 15th at 5:00 pm, and Wednesday, June 22nd at 6 am CDT.
Stat-Ease Consultant Brooks Henderson incorporated his Whirley-Pop DOE and some tips from the past webinars into this presentation. If you are new to DOE, this webinar is for you!
"DOE Made Easy and More Powerful via Version 8 of Design-Expert® Software" (Click on the title at left to download, 2.13 MB) Intermediate Level
Wednesday, March 24, Thursday, March 25, & April 28, 2010
Through a series of three webinars, Stat-Ease introduces an array of statistical methods for design of experiments (DOE) made easy and more powerful via version 8 of Design-Expert software. This first webinar highlights key features from simple to sublime, culminating in the design and analysis of a high-level factorial case-study.
"DOE Made Easy and More Powerful via Version 8 of Design-Expert® Software, Part 2—Response Surface Methods (RSM) for Process Optimization" (Click on the title at left to download, 1.13 MB) Advanced Level
Wednesday, July 14, Thursday, July 15 and Tuesday, September 21, 2010
Through a series of three webinars, Stat-Ease introduces an array of statistical methods for design of experiments (DOE) made easy and more powerful via version 8 of Design-Expert software. This second webinar looks at response surface methods (RSM) for process optimization through a series of case studies.
"DOE Made Easy and More Powerful via Design-Expert® Software, Part 3—Multicomponent Mixture Design for Optimal Formulation" (Click on the title at left to download, 1.50 MB) Advanced Level
Presented on Wednesday, December 15, Thursday, December 16, and Wednesday, January 27.
Through a series of three webinars, Stat-Ease introduces an array of statistical methods for design of experiments (DOE) made easy and more powerful via version 8 of Design-Expert software. In this third webinar Mark Anderson works through mixture case studies.
"Problems Analyzing Historical Data" (Click on the title at left to download, 659 KB) Intermediate Level
Tuesday, September 15 & Wednesday, September 16, 2009.
Explore the pitfalls and treacherous territory of analyzing historical data. See the damage that collinearity, nonsense correlations, feedback loops, and other data problems can do to your analysis. This is why we recommend that you do well-designed experiments!
"DOE—What's In It for Me" (Click on the title at left to download, 476 KB) Managerial Level
Wednesday, May 27 & Thursday, May 28, 2009.
This webinar is aimed at those who are unclear or need convincing on how design of experiments (DOE) harnesses the power of matrix-based multifactor testing. Wayne will discuss and demonstrate the clear advantages of DOE over the old-fashioned one-factor-at-a-time (OFAT) method. Learn how the interactions that DOE reveals are the key to big success!
"An Introduction to Mixture Design for Optimal Formulations" (Click on the title at left to download, 760 KB) Beginner Level
Wednesday, January 21 & Thursday, January 22, 2009.
This webinar is aimed at product formulators who at best may be using standard factorial designs, or worse yet, the one-variable-at-a-time method. Keeping it simple and making it fun, Mark introduces tools of multicomponent mixture design, modeling and statistical analysis. The goal is to generate interest in these powerful DOE methods for quickly converging on the sweet spot—where all desired product attributes are achieved.
"How to Plan and Analyze a Verification DOE" (Click on the title at left to download, 310 KB) Intermediate Level
Wednesday, October 29, 2008
Applications of DOE during Verification Stage
Companies are gradually learning that design of experiments (DOE) can be a useful tool during the final verification stage of a product or process. Rather than just testing the extremes one factor at a time, a DOE can cover the expected range of production variation and confirm that the final production conditions will make product within specification. The underlying difficulty in this application is that the desired DOE result is to have NO significant effects. This talk demonstrates how to confirm that the DOE chosen has the correct power to detect effects IF they exist. The design must be capable of doing the job. After collecting data a variety of potential results to estimate power are presented on half-normal plots. The interpretation of each plot will be discussed.
"Pat-Tricks on Model Diagnostics "What are They? Why Use Them? What Good Do They Do?” (Click on the title at left to download, 300 KB) Intermediate Level
Tuesday, August 12 & Wednesday, August 13, 2008
In this webinar Pat Whitcomb (Consultant) will offer up his "Best Pat-Tricks on Model Diagnostics (What are they? Why use them? What good do they do?)." These questions were answered while examining the diagnostics for a series of DOE case studies. Download a ZIP file of the Design-Expert data files mentioned in the webinar here (pat_tricks_data.exe, 126 KB). For your reference, also take a look at the "Diagnostics Report—Formulas & Definitions" (click here to download, 48 KB) and the "Residual Analysis and Diagnostics Plots Guide" (click here to download,122 KB).
“Dual Response Surface Methods (RSM) to Make Processes More Robust” (Click on the title at left to download, 2.18 MB) Intermediate Level
Tuesday, July 1st & Wednesday, July 2nd, 2008
Response surface methods (RSM) provide statistically-validated predictive models, sometimes referred to as "transfer functions," that can then be manipulated for finding optimal process configurations. The dual response approach to RSM captures both the average and standard deviation of the output(s) and simultaneously optimizes for the desired level at minimal variation, thus achieving an on-target, robust process. With inspiration provided by a case study on a semiconductor etching process, the positive repercussions of these methods will be readily apparent, especially for those involved in design for six sigma (DFSS) quality programs.
“The Difference Between Repeats and Replicates in DOE” Basic to Intermediate Level
Tuesday, May 13 & Wednesday, May 14, 2008
In this presentation examples are used to illustrate the differences between replicates, duplicates, and repeats, as well as the reasons for using each. Cost-based decision selection of one versus another are discussed. This is a practical presentation with a dash of technical spice thrown in for flavor.
For a heads-up on this tricky issue, consider this advice from consultant Pat Whitcomb for FAQ #1 in the November, 2004 DOE FAQ Alert: "Another question might be can I repeat the measurement rather than replicate the DOE run? The answer is yes, but in this case you enter the average of the repeated measures, not the individual results. Independent measurements will reduce the measurement system component of the total process variation... Only with knowledge of the variance components and the costs of replicating the DOE run and/or repeating the measure can one decide which is the best option." (See http://www.statease.com/news/faqalert4-11.html for Pat's complete answer, including a sample calculation on variance components. Wayne's webinar addresses this and much more.)
Data files and PowerPoint presentation can be downloaded as the WinZip archive: 08-May-Webinar.zip
"Multiple Response Optimization with Design-Expert" (4.91 MB) Intermediate Level
Tuesday, April 1 & Wednesday, April 2, 2008
The optimization module in Design-Expert searches for combinations of factor levels that simultaneously satisfy the requirements placed on each of the responses and factors. Discover how to get the most out of the optimization module in order to find the "sweet spot" for your product or an operating window for your process. Learn how to fine-tune your search by adding weights and importance settings to your basic criteria. A case study will be used to illustrate all of the features of Design-Expert's optimization module.
"10 Ways to Mess Up an Experiment & 8 Ways to Clean It Up" (1.04 MB) Basic Level
Tuesday, February 5 & Wednesday, February 6, 2008
This basic presentation is intended for actual experimenters and applied statisticians who are looking for practical advice. It's all about design of experiments itself and how to do it more effectively.
Mark says, "Here's how this presentation came about. After decades in the trenches, primarily working on injection-molding process improvement, Stat-Ease's client, Jeff Hybarger, established his consultancy and wrote "'The Ten Most Common Designed Experiment Mistakes" as a white paper that documented his DOE 'chops.' Stat-Ease published the article in its Stat-Teaser newsletter. Design Product News picked it up in their June/July 2007 issue. The Fall Technical Conference of applied statisticians invited Jeff to talk about it. He bowed out due to scheduling conflicts so I edited and presented "The Ten Most Common Designed Experiment Mistakes."
For this webinar I summarized these 10 ways to mess up an experiment and recapped 8 ways to clean them up. This latter part stems from a talk developed by Consultant Shari Kraber with my collaboration. It was originally presented under the title of the "8 keys to DOE."
"Sizing Mixture (RSM) Designs for Adequate Precision via Fraction of Design Space (FDS)" (1.04 MB) Advanced Level
Wednesday, November 28 & Thursday, November 29, 2007
We begin with a review of power calculations to determine if a factorial design has enough runs to detect effects. Power, however, is not the appropriate tool to evaluate mixture and response surface designs. This presentation shows how to use the fraction of design space (FDS) tool (only in DX7.1+) to properly size these more powerful designs. The use of FDS is also dependent on the experimenter’s design objectives—precision, prediction, or detecting a change. All three objectives are discussed.
"A Factorial Design Planning Process" (261 KB) Intermediate Level
Wednesday, September 19, 2007
This talk outlines a four-step process for planning a factorial design. A substantial part of this process is to evaluate the power of the design, which is based on detecting a specific change in the response versus the process variation present in the system. Via a case study, this talk addresses the issue of replicating runs versus repeating the measurement to increase the power of the design.