This basic Introduction to Design of Experiments (DOE) webinar, which requires no prior knowledge of statistics, covers fundamentals such as factors and levels, hypothesis testing, the need for random samples, and interpretation of results.

This webinar will not go deeply into analysis of experimental results but will illustrate the concepts graphically with box and whisker plots and similar media.

Course participants with no prior knowledge of DOE will understand enough basics to interact effectively with subject matter experts such as industrial statisticians, quality engineers, and Six Sigma practitioners. Managers will understand presentations of experimental results. An understanding of the concepts will also be good preparation if the attendee later takes a course in industrial statistics or an ASQ certification review course.

COURSE OUTLINE

• Understand the reason for DOE: a cost-effective and scientific technique to improve quality and identify defect sources.
• Cost-effective because it minimizes the number of samples that must be used
• Scientific because it quantifies the uncertainty of the reported results
• Understand the foundation of hypothesis testing, which also applies to SPC and acceptance sampling.
• Understand the quantifiable risks of error in any statistical activity. These are specifically Type I vs. Type II, alpha vs. beta, or producer's risk vs. consumer's risk. The first is the chance of concluding that there is a problem or a difference when none exists, and the second is the chance of not detecting a problem or difference that does exist.
• Realize that the only way to reduce both risks simultaneously is to obtain and assess more data. (This is why replication is important.)
• Understand the concepts of factors, levels, and interactions.
• Understand the importance of specimen randomization, blocking, and similar techniques to keep extraneous variation out of the experiment.
• Understand the concept of interactions (the sum of the whole is greater or less than the sum of the parts).
• Interpret experimental results in terms of significance level and P value (chance that any observed differences in results are due to luck or random chance).

WHAT YOU WILL LEARN FROM THIS COURSE

• Recognize situations such as process troubleshooting or process improvement in which DOE could be a valuable tool.
• Understand the concepts of factors, levels, and interactions.
• Know how screening experiments such as factorial designs can save an enormous amount of time and money (awareness only, will not go into detail).
• Know the need to keep extraneous variation sources out of the experiment, so the results will be meaningful. (Concepts of randomization and blocking.)
• Know how to plan the experiment by defining the null and alternate hypothesis. Understand the quantifiable risks (Type I and Type II, alpha and beta, or producer's risk and consumer's risk) of obtaining the wrong conclusion.
• This will equip the attendee to understand all applications of industrial statistics, including statistical process control and acceptance sampling, as well as DOE.
• The cost to minimize both risks simultaneously is to assess a bigger sample; nothing is free! (Concept of replication.)
• Know how to interpret the results of the experiment; does it show a significant difference between the control and experimental treatments, or between materials, methods, or tools?

Quantity: