COURSE SYLLABUS

IEE 572 DESIGN OF ENGINEERING EXPERIMENTS

Fall 2008

BYAC 210; 3:00 – 4:15

Instructor: Professor D. C. Montgomery, GWC Room 551, office phone 480.965.3836

Office hours: 1:00pm – 2:30pm TTh; other times by appointment

Course email account:

Textbook: Design and Analysis of Experiments, 7th edition, by D.C. Montgomery, John Wiley & Sons, New York, 2009.

We will use both the student version of Design-Expert V7 software and JMP 7.

The Student Solutions Manual that accompanies the textbook is recommended.

Some of these materials may be ordered as a set from the publisher. The ordering information is as follows: Design Analysis Experiment 7E with Design Expert Software 7.0 (The ISBN for the 7th Edition text + Design Expert Software is:9780470436936). Alternatively, you can purchase only the textbook and the student solutions manual from Wiley and obtain the JMP software from the e-Academy (see e-academy.com).

About the Course

This is a basic course in designing experiments and analyzing the resulting data. It is intended for engineers, physical/chemical scientists and scientists from other fields such as biotechnology and biology. The course deals with the types of experiments that are frequently conducted in industrial settings. The prerequisite background is a basic working knowledge of statistical methods. A formal course in engineering statistics at the level of ECE 380 is the official prerequisite, but this specific course isn’t essential. You will need to know how to compute and interpret the sample mean and standard deviation, have previous exposure to the normal distribution, be familiar with the concepts of testing hypotheses (the t-test, for example), constructing and interpreting a confidence interval, and model-fitting using the method of least squares. Most of these ideas will be reviewed as they are needed.

The course objective is to learn how to plan, design and conduct experiments efficiently and effectively, and analyze the resulting data to obtain objective conclusions. Both design and statistical analysis issues are discussed. Opportunities to use the principles taught in the course arise in all phases of engineering and scientific work, including technology development, new product design and development, process development, and manufacturing process improvement. Applications from various fields of engineering (including chemical, mechanical, electrical, materials science, industrial, etc.) will be illustrated throughout the course. Computer software packages (Design-Expert, JMP) to implement the methods presented will be illustrated extensively, and you will use these packages for homework assignments and the term project.

All experiments conducted by engineers and scientists are designed experiments; some of them are poorly designed, and others are well-designed. Well-designed experiments allow you to obtain reliable, valid results faster, easier, and with fewer resources than with poorly-designed experiments. You will learn how to plan, conduct and analyze experiments efficiently in this course. A well-designed experiment can lead to reduced development lead time for new processes and products, improved manufacturing process performance, and products that have superior function and reliability.

The course schedule and outline contains assigned reading topics from the textbook and suggested homework problems. In addition to the textbook reading assignments you may also want to read some of the supplemental text material for each chapter. This material is found on the World Wide Web page for the book maintained by the publisher, John Wiley & Sons. See the text Preface for more details. The JMP and Design-Expert computer software packages can be used to solve most of the problems in the textbook.

Course Outline and Schedule

Class / Date / Topic / Text Reference / Suggested Exercises
1 / 8/26/08 / Introduction to DOX, begin review of basic statistical concepts / Chapters 1 & Chapter 2 (Sections 2.1 through 2.4) / 1.1, 1.5, 1.6
2 / 8/28 / Continue statistics review; the t-test and confidence intervals / 2.1, 2.6, 2.10, 2.a5, 2.19, 2.22 (work part c by using a normal probability plot)
3 / 9/2 / Introduction to the analysis of variance (ANOVA) / Chapter 3 (Sections 3.1, 3.2, and 3.3) / 3.3, 3.10, 3.12, 3.16, 3.17
4 / 9/4 / Some practical aspects of planning experiments – before this lecture view the video on planning experiments that is on Blackboard / Suggested reading: Coleman, D. E. and Montgomery, D. C. (1993), “Planning for a Designed Industrial Experiment”, Technometrics 35(1), pp. 1-12 (also on Blackboard). Also see the supplemental text material for Chapter 1
5 / 9/9 / More about ANOVA; multiple comparisons, residuals and model adequacy checking / Sections 3.4, 3.5, and 3.6, 3.8 / 3.8
6 / 9/11 / More about ANOVA; checking model assumptions, the Box-Cox method / Chapter 15, Section 15.1.1 / 3.26
7 / 9/16 / Choice of sample size in designed experiments / Section 3.7
8 / 9/18 / The randomized complete block design (RCBD) / Chapter 4 (Section 4.1) / 4.1, 4.2, 4.4, 4.7, 4.8
9 / 9/23 / RCBDs, Latin squares, etc. / Section 4.2
10 / 9/25 / Introduction to factorial designs / Chapter 5 (Sections 5.1, 5.2, and 5.3) / 5.2, 5.7, 5.8
11 / 9/30 / Factorials, continued
First Project Report (Proposal, steps 1-3) Due / Sections 5.4, 5.5, 5.6 / 5.19, 5.23
12 / 10/2 /

2kfactorial designs, introduction

/ Chapter 6 / 6.1, 6.5
13 / 10/7 / 2k factorial designs, continued / 6.6
14 / 10/9 / 2kfactorial designs, continued / 6.18, 6.19, 6.26, 6.27
15 / 10/14 / Blocking and confounding in two-level factorial designs / Chapter 7 (Sections 7.1 through 7.6) / 7.1, 7.4, 7.7, 7.9
16 / 10/16 / Quiz 1
17 / 10/21 /

Blocking and confounding in the 2k, continued

18 / 10/23 / 2k-pfractional factorial designs, introduction / Chapter 8 / 8.3, 8.4, 8.6
19 / 10/28 / 2k-pfractional factorial designs, continued / 8.24
20 / 10/30 / 2k-pfractional factorial designs, continued / 8.27, 8.28
21 / 11/4 / 2k-pfractional factorial designs, continued; Second Project Report Due / 8.31
22 / 11/6 / 2k-pfractional factorial designs, continued / 8.5, 8.33
23 / 11/13 / Response surface methods and designs (an overview) / Chapter 11 (Sections 11.1 through 11.5) / 11.8
24 / 11/18 / Quiz 2
25 / 11/20 / Random factors in experiments / Chapter 13, Section 13.1 / 13.1, 13.4
26 / 11/25 / Random factors in factorial experiments, mixed models / Section 13.2, 13.3, 13.5, 13.6 / 13.9,
13.10, 13.11, 13.14
27 / 12/2 / Nested & split-plot designs / Chapter 14, Sections 14.1, 14.2 and 14.3 / 14.1, 14.3
28 / 12/4 / Nested and split-plot designs / Chapter 14, Sections 14.4 and 14.5 / 14.19
29 / 12/9 / Nested and split-plot designs
Term Projects Due
Final exam: 12/11 from 12:10-2:00

Grading

Your grade in the course will be determined by the two quiz scores (25% each), the final exam (25%) and the term project (25%).

Term Project

The term project is performed in teams of up to three people. The project consists of planning, designing, conducting and analyzing an experiment, using appropriate DOX principles. Two written interim project reports are required, along with a final written project report. The dates these items are due is on the course outline above.

The context of the term project experiment is limited only by your imagination. In previous classes, students have conducted experiments directly connected to their own research projects. The project is a nice way to get extra-mileage from this course; it can help you finish your research sooner. For industrial participants or those with an internship in industry, a project that they are involved with at work is a good possibility. If all else fails, you could conduct a “household” experiment (such as how does varying factors such as type of cooking oil, amount of oil, cooking temperature, pan type, brand of popcorn, etc. affect the yield and taste of popcorn). However, I’ve seen just about all the possible popcorn(and catapult and paper airplane) experiments than can be run, and I’m looking for a little variety in my life, so let’s be creative.

The major requirement is that the experiment must involve at least three design factors. Each of the interim reports requires information about the problem, the factors, the responses that will be observed, and the specific details of the design that will be used. You will be given feedback on these reports that should help you in completing the final experiment and the analysis, and preparing the final report. Some of these projects may be selected for class discussion/presentation, if time permits.

The textbook web site has several examples of term projects from previous classes. These will give you a good idea about the types of experiments that have been conducted by previous groups of students, and how their reports were prepared. I would like to include some of your projects on the website, so if you are willing to donate your project, please ensure that I receive an electronic copy of the final report.