16/1/10
Introduction and Simple
Comparative Experiments
IE-533 Spring 2016
Industrial Application of Statistics
1
.
Syllabus
Some Useful Tools, Scientific Context, Comparing Two Treatments
Blocking and Randomization
Empirical Models and Regression Analysi
16/2/23
Factorial Experiments
Chapter 5-6
One-Factor at a Time Approach to
Experiments with Multiple Factors
Vary only one factor at a time, hold everything else
constant
Replicate the points to get an estimate of noise
1
16/2/23
The Effects of Each Fac
Design of Engineering Experiments
The Blocking Principle
Text Reference, Chapter 4
Blocking and nuisance factors
The randomized complete block design or
the RCBD
Extension of the ANOVA to the RCBD
Other blocking scenariosLatin square
designs
Chapter
IE 533 Midterm, Spring 2013
Instructor: Hong Wan
Name of Student_
Instructions
1.
2.
3.
4.
Close book and close notes, except one-page (double-sided) script sheet.
Calculator is allowed
75 minutes
Write intermediate steps when appropriate for partial cred
Lab Name:
Group member names and date
1. Experimental designs and conduction: in this section, describe your
experiments including factors, parameters and response; give the designresponse table, briefly describe how you decide the sampling sequence and
r
iPad ’u:
130
3.12 Problems
9:29 PM
Design and Analysis of Experiments, Eighth Edition
Chapter 3 I Experiments with a Single Factor: The Analysis of Variance
3.11.2
The procedure used in the previous section of replacing the observations by their ranks i
iPad ".3
9:29 PM
@ 95% 1:}:
Design and Analysis of Experiments, Eighth Edition
2.7 Problems 59
The 100(1 — a) conﬁdence interval for the ratio of the population variances (If/0% is
I
Fl—a/2Jl3—IJII-l — 2 —
0,2 s2
01 < Fa/2.n_~-l.n.-l
2 2
To illustrate
IE 533: Industrial Applications of Statistics
School of Industrial Engineering, Purdue University
Lab 2: One factor experiment and analysis
Lab report due: Feb 18th, 2016.
Remember the paper helicopter experiments we have discussed at the beginning of
the
IE 533: welcome on board
Hong Wan
Spring, 2016.
1
What this course is
Simple Comparative Experiments
ANOVA analysis
Randomized Blocks, Latin Squares, and Related
Designs.
Factorial designs and Fractional factorial
designs(main emphasis)
Nested and spl
Models and Modeling
A model gives an interpretation to a pattern.
A model can be used to:
Predict what will happen in the future
Understand how a process works
Control or improve a process through a prediction and feedback loop
A model should be mad
IE 533: Industrial Applications of Statistics
School of Industrial Engineering, Purdue University
Lab 3: One factor experiment and analysis
Lab report due: April 21st, 2016.
In Lab 3, you will use an unreplicated fractional factorial design to study the
h