Design of Experiments (DoE)

Overview

Course Content

Process Model Overview

• Black and white box modeling
• Preview on all working steps (design & data analysis)

Basic Statistics

• Distributions (normal, Weibull, binomial)
• Confidence intervals

Building Blocks of Experimental Design

• Functional approach for process behavior
• Statistical models for measuring errors, noise variables, and unknown factors
• Design space and design space coverage

Setting Up Experimental Designs

• Working steps for good designs
• Impact of model assumption
• Sample Size calculation
• Special situations (constraints, inclusions, candidates)

Analyzing DoE Data (Regression)

• Working steps for data analysis (checklist) and background
• Background for the working steps
• Model visualization and optimization for conflicting response
• Practical exercises

Objective

Target Groups & Background Knowledge

System Requirements

• The focus is on understanding the methods; underlying mathematics and statistics is explained by simulations and not by formula. 
• The basics of the various methods are examined, extensively. 
• The most important methods are not only explained but through the discussion of the application examples and their processing, you should become familiar with these methods. 
• The focus is on the current state of the art which allows to treat almost any situation. 
• The impact of DoE on Machine Learning (ML) projects will be explained. 

This course is designed for: 

• Engineers, technicians, analysts, and scientists in R&D departments who want to effectively achieve results 

Background knowledge:  

• Quantitative way of thinking 
• Affinity to model building