“How To Design

Your Model”
 DOE Software
This EASY TO USE software has all the major
experimental designs (general ANOVA, two-level full
Design of Experiment
and fractional factorials, three-level factorials, several
www.statease.com
RSM designs, mixture designs, and much more).

More and more features are added with each new

version of the software.

 It has powerful graphical tools and it has been

featured in several well-known texts on DOE.
Apparently it has been WIDELY USED IN
INDUSTRY.

The web site provides excellent DOE resources and

one can download a 30-day full version from
the web site.
 DOE Wisdom
www.launsby.co This software also claims that it offers PRACTICALITY
and EASE-OF-USE that is IDEAL FOR
BEGINNERS but with the computing power demanded
by advanced users.
It basically offers VERY SIMILAR FEATURES TO
DESIGN-EXPERT with the addition of the Pareto chart
and a few other minor differences.
One can DOWNLOAD A 15-DAY FULL
VERSION of the
software for the web site.

DOEpack
www.pqsystems.com This standalone software available also
FEATURES THE USUAL CLASSICAL AND
TAGUCHI DESIGNS with a wide selection of
SCREENING DESIGNS, PROCESS
OPTIMIZATION DESIGN AND ANALYSIS
TOOLS.

 It has good graphical tools and an intuitive user

www.jmp.com This standalone DOE software is developed by the
well-known SAS Institute, developers of the SAS
program.

This is also powerful software and provides design

choices for almost every situation. Perhaps the
additional feature that is not available in the other
software is that the user can perform custom designs
which give the experimenter the most flexibility.

Obviously, this feature is ONLY USEFUL FOR

THE EXPERT USER. Limited time free download
of the software is also available from the JMP web site.
n Expert Version 7.1.5 or LATEST Version 8
 Doe Vocabulary
Factor One of the independent variables under investigation that
can be set to desire value
K Number of factors or variables the effect of which are to be
estimated in an experimental
Level The numerical value or qualitative feature of a factor

Run The act of operating the process with a factors at certain

setting
Response The numerical result of a run
Factor Experiment Design to determine the effect of all possible combinations
across all level of the factor under study
Factorial Factorial Designed to examine k factors with the fraction of the runs
required for a full factorial
Blocking A strategy for designing experiment to provide the ability to
eliminate from the experimental error a contributor of
variability that is known but not under investigation
 Why Goes For
Experimental Design?
1 2
EFFICIENCY Get FOCUSING Collect
more info from fewer only info that really
experiments needed

is a useful complement to multivariate data analysis.

with designed experiments there is a better possibility of

testing the significance of the effects and the relevance

of the whole model .
 DOE Flowchart?
1 4 7
Set your Select your Fit & Diagnose
objective design Model

5 8
2
Develop your Interpret
Select Input
strategy Model
Factors
Will be
explain
6 9 next
3
Confirm semester
Run
Select Output Model
Experiment
Response
 Building a
Experimental Design
! Project Titles
Your Final Year
Example:
Studies Of Potential Parts Of Streblus
asper (Kesinai) For Protease
Production
1

DEFINE THE OBJECTIVE To screen and identify the

of the investigation: e.g. “sort POTENTIAL PLANT
out important variables” or PARTS of PROTEASE
“find the optimum conditions PRODUCTION from
Streblus asper by using Design
of Experiment (DOE).
 Building a
Experimental Design
! 3
2 Weight of your SELECT
sample (g) OUTPUT
SELECT INPUT RESPONSE
FACTORS
that will be Ratio (mol) that will be
controlled during measured to Enzyme
(Buffer : Sample)
the experiment describe the Activity
(design variables), outcome of the (unit/mL)
and their levels or experimental
ranges of variation. Time of Extraction runs (response
(minutes) variables), and
examine their
precision
 Experimental Design
!
4

SELECT YOUR DESIGN

CHOOSE among the available

standard designs the one that is
compatible with the objective,
number of design variables and
precision of measurements, and
has a reasonable cost
Screening
Design
The Screening designer supplies a
list of popular screening designs for
2 or more factors.

Screening factors can be

continuous or categorical with two
or three levels.

The list of screening designs also

includes designs that group the
experimental runs into blocks of
equal sizes where the size is a
power of two.
WELCOME! 1
2 START YOUR DESIGN!!
Choose
The
Experimenta
l
Design

4
 The choices appear in color on your screen.
White squares symbolize full factorials
requiring 2k runs for k (the number
of factors) from 2 to 9.

This design builder The other choices are

offers full and colored like a stoplight:
fractional two‐level GREEN FOR GO,
factorials for 2 to 21 YELLOW FOR
factors PROCEED WITH
in powers of two (4, 8, CAUTION, and RED
16…) for up to 512 FOR STOP, which
runs. represent varying
degrees of resolution: ≥
V, IV, and III,
respectively.
For a quick overview of these color codes, press the
screen tips button (or select Tips, Screen Tips) and
click
topic 1: “What type of information do you want?”
 Insert your range here!
Make sure the range is not
8 too small or too big

7 Insert your factors and unit

9
 Choose number of response in your
10 study

11 Insert your response here!

12
 Actual
Values!!!!

14

Insert your
experimental
data here

13 List of experiment that you design before will be

shown here

5 6

Develop your Run

strategy Experiment
15 You might choose process factors in coded or actual
You’ve put in some work at this point so it is a good time to save it. The quickest way of
doing this is to press the standard save icon. But you can also go to the File menu and
select Save As. Type in the name of your choice for your
data file. Then click Save.
For Plackett Burman Design
minimum factor is 11.

If your factors is less than 11, you

add dummies factors to complete
it.

Next step is the same as previous.

 Response Surface Design

Response Surface Methodology (RSM) is an

experimental technique invented to find the optimal
response within the specified ranges of the factors.

These designs are capable of fitting a second order

prediction equation for the response.

The quadratic terms in these equations model the

curvature in the true response function. If a maximum or
minimum exists inside the factor region, RSM can find it.

In industrial applications, RSM designs involve a small

number of factors. This is because the required number
of runs increases dramatically with the number of factors.
The Response Surface designer in JMP lists well-known
RSM designs for two to eight continuous factors. Some
of these designs also allow blocking
 CENTRAL COMPOSITE design, combines a two-level fractional factorial and two
other kinds of points:
Fractional
factorial
point

Axial (or star) points, for which all but one factor set at zero
Axial (midrange) and one factor set at outer (axial) values.
Point

Centre Center points, for which all the factor values are at the zero
Point (or midrange) value.

The BOX-BEHNKEN design, is an alternative to central composite designs.

One distinguishing feature of the Box-Behnken design is that there are ONLY
THREE LEVELS PER FACTOR.

Another important difference between the two design types is that the BOX-
BEHNKEN DESIGN HAS NO POINTS AT THE VERTICES OF
THE CUBE defined by the ranges of the factors.

This is sometimes useful when it is desirable to avoid these points due to engineering
considerations. The price of this characteristic is the higher uncertainty of prediction near
the vertices compared to the Central Composite design.
 1
Insert your optimize factor and your
range here

Number of run

2
Insert list of response involved in your optimization here

3
 Actual Values!!!!

Insert your
experimental
data here

4 List of experiment that you design before will be

shown here

5 6

Develop your Run

strategy Experiment
Thank you…..