To view active media links, please use the Training Programs tab.
Experimental Methods provides the participant with the knowledge and skills necessary to effectively and efficiently design and execute statistically designed experiments. Experiment design is most often used to establish a rational set of testing conditions that, when executed, will provide the data necessary to analyze the primary effect of each independent variable, often including the one or more of variable interactions. The applications of designed experiments that are covered in this course range from learning to screen a large group of variables, so as to discover the vital few contributors, understand how to segregate sources of nonrandom error from random error, identify and analyze variable interactions, maximize the mean of a performance variable while concurrently reducing the variance and establish realistic performance specifications and apply tolerances for products and processes. Of course these are just a few of the many applications in which statistically designed experiments can play a central role.
More specifically, this topic will thoroughly cover the design and subsequent analysis of the more common factorial experiments. The participant will learn how to design, analyze, interpret and report the results associated with the common forms of two-level full and fractional factorial experiments. Of great interest, this course represents the foundational knowledge and skills associated with process improvement, therefore providing tremendous insight into the logic and reasoning which underlies Six Sigma and the process of breakthrough improvement. The related tools lie at the core of the DMAIC problem solving system, as well as other recognized systems of quantitative problem resolution. Owing to this, the design and analysis of experiments is a crucial skill for anyone concerned with the improvement or optimization of commercial and industrial products and services.
Reinforcement of major concepts, techniques, and application is realized through exercises, scenarios, and case studies. The following prerequisite topics are listed in sequential learning order: Basic Statistics, Hypothesis Testing, Confidence Intervals and Parametric Methods. Total instructional time for this topic is 10 hours and 32 minutes.
- Design Principles - Understand the principles of experiment design and analysis
- Design Models - Describe the various types of designed experiments and their applications
- Experimental Strategies - Outline a strategy for designing and analyzing a statistical experiment
- Experimental Effects - Define the various types of experimental effects and how they impact decisions
- One-Factor Two Level - Configure and analyze a one-factor two-level statistically based experiment
- One-Factor Multi Level - Configure and analyze a one-factor multi-level statistically based experiment
- Full Factorials - Understand the nature and underlying logic of full factorial experiments
- Two-Factor Two Levels - Configure and analyze a two-factor two-level statistically based experiment
- Two-Factor Multi Level - Configure and analyze a two-factor multi-level statistically based experiment
- Three-Factor Two Level - Configure and analyze a three-factor two-level statistically based experiment
- Planning Experiments - Understand the planning and implementation considerations related to statistical experiments
- Fractional Factorials - Understand the nature and underlying logic of fractional factorial experiments
- Four-Factor Half-Fraction - Configure and analyze a four-factor half-fraction statistically based experiment
- Five-Factor Half-Fraction - Configure and analyze a five-factor half-fraction statistically based experiment
- Screening Designs - Understand how to select, implement, and analyze a screening experiment
- Robust Designs - Explain the purpose of robust design and define several practical usages
- Experiment Simulation - Describe how a DOE can be employed when measurement data is not available