Scribd
Upload
93 views9 pages

DOE Course Essentials

This document provides information about experiments and design of experiments (DOE) for a course. It recommends textbooks on DOE and software for simulations and analysis. It discusses background in DOE and experimental strategies like changing one factor at a time versus full factorial designs, which are more effective. It concludes with an announcement of an upcoming quiz on statistics concepts.

Uploaded by

Stephen Hassler
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
93 views9 pages

DOE Course Essentials

This document provides information about experiments and design of experiments (DOE) for a course. It recommends textbooks on DOE and software for simulations and analysis. It discusses background in DOE and experimental strategies like changing one factor at a time versus full factorial designs, which are more effective. It concludes with an announcement of an upcoming quiz on statistics concepts.

Uploaded by

Stephen Hassler
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

DESIGN ENGINEERING EXPERIMENTS

(DOE)
This Semester…
2

 DOE Simplified, third edition, Mark Anderson & Patrick Whitcomb


 Recommended
 Design and Analysis of Experiments, eighth edition, Douglas Montgomery
 Suggested

 SimWarePro
 Obligatory, $20 for access to their computer simulations
 You will need purchase this from Air Academy Associates starting next week

 Software Package
 Minitab, $30 (6 mo), $50 (12 mo) www.minitab.com
 DOE Pro, $375 (lifetime) www.airacad.com
 Design-Ease, Design-Expert, $575 (lifetime) www.statease.com
Design Of Experiments
3

 My background

H2 = 194 – 713 OSO – 208 ISO + 749 PMG + 280 ISO2


Lecture #1
EXPERIMENTING
Relevance
5

 The scientific (or engineering) method is a body of execution


for investigating beliefs, acquiring new knowledge, or
correcting previous assumptions.
 Scientific method requires
 Formulating a question
 Determining your hypothesis
 Testing
 Evaluation
 Experimentation is a vital part of the scientific method
 Properly designed experiments are the most efficient and
effective approach to experimenting
 A basic understanding of statistical hypothesis testing is
essential
Experimentation
6

Experiment: purposefully changing the inputs of a


process to observe the changes in the output or
response variable.
Controllable Factors
X1 X2 . . . Xn

Output
INPUTS Noise* Process Y or
Response Variable

Z1 Z2 . . . Zi
Controllable* & Uncontrollable* Factors
*Nuisance Factors
Experimentation
7

Important Definitions
 Factors—the main effects/inputs being changed
 Factor levels—The values the factors are set during experimentation
 Response variable—the output under study

Summary When Using Statistical Techniques in Experimentation


1. Use all non-statistical knowledge of the problem first
2. Keep the design and analysis as simple as possible—KISS
3. Recognize the difference between practical and statistical significance
4. Experiments are typically iterative
Experimental Strategies
8

 One Factor at a Time (O-FAT)


 Most people take their best guess to begin and then change one variable
at a time.
 Changing one variable at a time lets you see the effect of that one
variable but can result in additional time and cost.

 Keep the Winner (Change many factors at the same time)


 Teams often do this when they brainstorm and prioritize a list of possible
ways to improve the process.
 Hard to fully analyze & separate effects and interactions

 Factorial Designs
 Most effective and efficient process of experimenting
Quiz on Statistics
9

 Your own work


 You’ll need a pencil and calculator
 Maximum time is 45 minutes

 Will NOT affect your grade

You might also like