Sie sind auf Seite 1von 50

Whats New in

Design-Expert version 7
Factorial and RSM Design

Pat Whitcomb
November, 2006

Design-Expert vers 1
ion 7
Whats New

General improvements
Design evaluation
Diagnostics
Updated graphics
Better help
Miscellaneous Cool New Stuff
Factorial design and analysis
Response surface design
Mixture design and analysis
Combined design and analysis
Design-Expert vers 2
ion 7
Two-Level Factorial Designs

2k-p factorials for up to 512 runs (256 in v6) and 21 factors


(15 in v6).
Design screen now shows resolution and updates with
blocking choices.
Generators are hidden by default.
User can specify base factors for generators.
Block names are entered during build.
Minimum run equireplicated resolution V designs for
6 to 31 factors.
Minimum run equireplicated resolution IV designs for
5 to 50 factors.

Design-Expert vers 3
ion 7
2k-p Factorial Designs
More Choices

Need to check box to see factor generators

Design-Expert version 4
7
2k-p Factorial Designs
Specify Base Factors for Generators

Design-Expert vers 5
ion 7
MR5 Designs
Motivation

Regular fractions (2k-p fractional factorials) of 2k designs


often contain considerably more runs than necessary to
estimate the [1+k+k(k-1)/2] effects in the 2FI model.
For example, the smallest regular resolution V design
for k=7 uses 64 runs (27-1) to estimate 29 coefficients.
Our balanced minimum run resolution V design for k=7
has 30 runs, a savings of 34 runs.

Small, Efficient, Equireplicated Resolution V Fractions of 2k designs and their


Application to Central Composite Designs, Gary Oehlert and Pat Whitcomb, 46th
Annual Fall Technical Conference, Friday, October 18, 2002.
Available as PDF at: http://www.statease.com/pubs/small5.pdf

Design-Expert vers 6
ion 7
MR5 Designs
Construction

Designs have equireplication, so each column contains


the same number of +1s and 1s.
Used the columnwise-pairwise of Li and Wu (1997) with
the D-optimality criterion to find designs.
Overall our CP-type designs have better properties than
the algebraically derived irregular fractions.
Efficiencies tend to be higher.
Correlations among the effects tend be lower.

Design-Expert vers 7
ion 7
MR5 Designs
Provide Considerable Savings

k 2k-p MR5 k 2k-p MR5


6 32 22 15 256 122
7 64 30 16 256 138
8 64 38 17 256 154
9 128 46 18 512 172
10 128 56 19 512 192
11 128 68 20 512 212
12 256 80 21 512 232
13 256 92 25 1024 326
14 256 106 30 1024 466

Design-Expert vers 8
ion 7
MR4 Designs
Mitigate the use of Resolution III Designs

The minimum number of runs for resolution IV designs is


only two times the number of factors (runs = 2k). This can
offer quite a savings when compared to a regular resolution
IV 2k-p fraction.
32 runs are required for 9 through 16 factors to obtain
a resolution IV regular fraction.
The minimum-run resolution IV designs require 18 to
32 runs, depending on the number of factors.
A savings of (32 18) 14 runs for 9 factors.
No savings for 16 factors.
Screening Process Factors In The Presence of Interactions, Mark Anderson and
Pat Whitcomb, presented at AQC 2004 Toronto. May 2004. Available as PDF at:
http://www.statease.com/pubs/aqc2004.pdf.

Design-Expert vers 9
ion 7
MR4 Designs
Suggest using MR4+2 Designs

Problems:
If even 1 run lost, design becomes resolution III
main effects become badly aliased.
Reduction in runs causes power loss may miss
significant effects.
Evaluate power before doing experiment.

Solution:
To reduce chance of resolution loss and increase power,
consider adding some padding:
New Whitcomb & Oehlert MR4+2 designs

Design-Expert vers 10
ion 7
MR4 Designs
Provide Considerable Savings

k 2k-p MR4+2 k 2k-p MR4+


2
6 16 14 16 32 34*
7 16 16* 17 64 36
8 16 18* 18 64 38
9 32 20 19 64 40
10 32 22 20 64 42
11 32 24 21 64 44
12 32 26 22 64 46
13 32 28 23 64 48
14 32 30 24 64 50
* No savings
15 32 32* 25 64 52
Design-Expert vers 11
ion 7
Two-Level Factorial Analysis

Effects Tool bar for model section tools.


Colored positive and negative effects and Shapiro-Wilk
test statistic add to probability plots.
Select model terms by boxing them.
Pareto chart of t-effects.
Select aliased terms for model with right click.
Better initial estimates of effects in irregular factions by
using Design Model.
Recalculate and clear buttons.

Design-Expert vers 12
ion 7
Two-Level Factorial Analysis
Effects Tool Bar

New Effects Tool on the factorial


effects screen makes all the options
obvious.
New Pareto Chart
New Clear Selection button
New Recalculate button (discuss
later in respect to irregular fractions)

Design-Expert vers 13
ion 7
Two-Level Factorial Analysis
Colored Positive and Negative Effects
D e si g n-E xpe rt S oftw are
Fi l tra ti on Rate

S h ap i ro -W il k tes t
W -va l u e = 0.9 74
p - val u e = 0 .9 2 7
A : Te mp e r atu re
B : Pre ss u r e
C : Co n ce n tra ti on
D : Sti r Ra te
Po s i ti v e E f ec ts
Ne g ati v e Ef fec ts

Half-Normal Plot

99

Half-Normal % Probability
95

90 AC

80
AD
D
70 C

50

30
20
10
0

0.00 5.41 10.81 16.22 21.63

|Standardized Effect|

Design-Expert vers 14
ion 7
Two-Level Factorial Analysis
Select Model Terms by Boxing Them.

Half-Normal Plot Half-Normal Plot


Warning! No terms are selected.
99 99

A
Half-Normal % Probability

Half-Normal % Probability
95 95

90 90 AC

80 80
AD
D
70 70 C

50 50

30 30
20 20
10 10
0 0

0.00 5.41 10.81 16.22 21.63 0.00 5.41 10.81 16.22 21.63

|Standardized Effect| |Standardized Effect|

Design-Expert version 15
7
Two-Level Factorial Analysis
Pareto Chart to Select Effects

The Pareto chart is useful for showing the relative size of


effects, especially to non-statisticians.
Problem: If the 2k-p factorial design is not orthogonal and
balanced the effects have differing standard errors, so the
size of an effect may not reflect its statistical significance.
Solution: Plotting the t-values of the effects addresses
the standard error problems for non-orthogonal and/or
unbalanced designs.
Problem: The largest effects always look large, but what
is statistically significant?
Solution: Put the t-value and the Bonferroni corrected
t-value on the Pareto chart as guidelines.

Design-Expert vers 16
ion 7
Two-Level Factorial Analysis
Pareto Chart to Select Effects

Pareto Chart
C
11.27

8.45 AC
t-Value of |Effect|

5.63 A

Bonferroni Limit 5.06751

2.82
t-Value Limit 2.77645

0.00

1 2 3 4 5 6 7

Rank

Design-Expert vers 17
ion 7
Two-Level Factorial Analysis
Select Aliased terms via Right Click

Design-Expert version 18
7
Two-Level Factorial Analysis
Better Effect Estimates in Irregular Factions

Design-Expert version 6 De sig n


cle an
- E xper t S oft wa re

Sh api ro- Wi lk te s
W- value = 0. 876
p-v alu e= 0 .171
A: wat er t em p
B: cycle t im e
C: soap
D: sof tene r
Po sit i v
t

e E f fect s
Ne gat ive E f ect s

Design-Expert version 7
Ha lf N o r m a l p lo t Half-Normal Plot

99 99
H a lf N o rm a l % p ro b a b ility

97

Half-Normal % Probability
95 A 95 AC

90 90

85 C C
80 80
AC A
70 70
B
60
50
40
30
20 20
10
0 0

0 .0 0 1 4 .8 3 2 9 .6 7 4 4 .5 0 5 9 .3 3 0.00 17.81 35.62 53.44 71.25

|E ffe c t| |Standardized Effect|

Design-Expert version 19
7
Two-Level Factorial Analysis
Better Effect Estimates in Irregular Factions

ANOVA for Selected Factorial Model


Analysis of variance table [Partial sum of squares]
Sum of Mean F
Source Squares DF Square Value Prob > F
Model 38135.17 4 9533.79 130.22 < 0.0001
A 10561.33 1 10561.33 144.25 < 0.0001
B 8.17 1 8.17 0.11 0.7482
C 11285.33 1 11285.33 154.14 < 0.0001
AC 14701.50 1 14701.50 200.80 < 0.0001
Residual 512.50 7 73.21
Cor Total 38647.67 11

Design-Expert vers 20
ion 7
Two-Level Factorial Analysis
Better Effect Estimates in Irregular Factions

Main effects only model:


[Intercept] = Intercept - 0.333*CD - 0.333*ABC - 0.333*ABD
[A] = A - 0.333*BC - 0.333*BD - 0.333*ACD
[B] = B - 0.333*AC - 0.333*AD - 0.333*BCD
[C] = C - 0.5*AB
[D] = D - 0.5*AB
Main effects & 2fi model:
[Intercept] = Intercept - 0.5*ABC - 0.5*ABD
[A] = A - ACD
[B] = B - BCD
[C] = C
[D] = D
[AB] = AB
[AC] = AC - BCD
[AD] = AD - BCD
[BC] = BC - ACD
[BD] = BD - ACD
[CD] = CD - 0.5*ABC - 0.5*ABD

Design-Expert vers 21
ion 7
Two-Level Factorial Analysis
Better Effect Estimates in Irregular Factions

Design-Expert version 6 calculates the


initial effects using sequential SS via
hierarchy.
Design-Expert version 7 calculates the
initial effects using partial SS for the
Base model for the design.
The recalculate button (next slide)
calculates the chosen (model) effects
using partial SS and then remaining
effects using sequential SS via
hierarchy.

Design-Expert vers 22
ion 7
Two-Level Factorial Analysis
Better Effect Estimates in Irregular Fractions

Irregular fractions Use the Recalculate key when


selecting effects.

Design-Expert vers 23
ion 7
General Factorials

Design:
Bigger designs than possible in v6.
D-optimal now can force categoric balance (or
impose a balance penalty).
Choice of nominal or ordinal factor coding.

Analysis:
Backward stepwise model reduction.
Select factor levels for interaction plot.
3D response plot.

Design-Expert vers 24
ion 7
General Factorial Design
D-optimal Categoric Balance

Design-Expert vers 25
ion 7
General Factorial Design
Choice of Nominal or Ordinal Factor Coding

Design-Expert vers 26
ion 7
Categoric Factors
Nominal versus Ordinal

The choice of nominal or ordinal for coding categoric factors


has no effect on the ANOVA or the model graphs. It only
affects the coefficients and their interpretation:
1. Nominal coefficients compare each factor level
mean to the overall mean.
2. Ordinal uses orthogonal polynomials to give
coefficients for linear, quadratic, cubic, ,
contributions.

Design-Expert vers 27
ion 7
Battery Life
Interpreting the coefficients

Nominal contrasts coefficients compare each factor level mean


to the overall mean.
Name A[1] A[2]
A1 1 0
A2 0 1
A3 -1 -1
The first coefficient is the difference between the overall
mean and the mean for the first level of the treatment.
The second coefficient is the difference between the overall
mean and the mean for the second level of the treatment.
The negative sum of all the coefficients is the difference
between the overall mean and the mean for the last level of
the treatment.

Design-Expert vers 28
ion 7
Battery Life
Interpreting the coefficients

Ordinal contrasts using orthogonal polynomials the first


coefficient gives the linear contribution and the second the
quadratic:
Name B[1] B[2]
15 -1 1
70 0 -2
125 1 1

B[1] = linear
B[2] = quadratic

Design-Expert vers 29
ion 7
General Factorial Analysis
Backward Stepwise Model Reduction

Design-Expert vers 30
ion 7
Select Factor Levels for Interaction Plot

Design-Expert vers 31
ion 7
General Factorial Analysis
3D Response Plot
De s i g n-Ex p e rt S o ftwa re

wo o d fa i lu re
X1 = A: W o o d
X2 = B: A d h e si ve

Ac tu a l Fa c to rs
C: A p pl i c a to r = b r u s h
D: C l a mp = p ne u m a tic
E: P re ss u re = fi rm

96

81.5
wood failure

67

52.5

38
LV-EPI-RT pine
EPI-RT maple
RF-RT poplar
PRF-RT red oak
B: Adhesive PRF-ET chestnut A: Wood

Design-Expert vers 32
ion 7
Factorial Design Augmentation

Semifold: Use to augment 2k-p resolution IV; usually


as many additional two-factor interactions can be
estimated with half the runs as required for a full
foldover.
Add Center Points.
Replicate Design.
Add Blocks.

Design-Expert vers 33
ion 7
Whats New

General improvements
Design evaluation
Diagnostics
Updated graphics
Better help
Miscellaneous Cool New Stuff
Factorial design and analysis
Response surface design
Mixture design and analysis
Combined design and analysis
Design-Expert vers 34
ion 7
Response Surface Designs

More canned designs; more factors and choices.


CCDs for 30 factors (v6 10 factors)
New CCD designs based on MR5 factorials.
New choices for alpha practical, orthogonal
quadratic and spherical.
Box-Behnken for 330 factors (v6 3, 4, 5, 6, 7, 9 & 10)
Odd designs moved to Miscellaneous.
Improved D-optimal design.
for 30 factors (v6 10 factors)
Coordinate exchange

Design-Expert vers 35
ion 7
MR-5 CCDs
Response Surface Design

Minimum run resolution V (MR-5) CCDs:


Add six center points to the MR-5 factorial design.
Add 2(k) axial points.
For k=10 the quadratic model has 66 coefficients. The
number of runs for various CCDs:
Regular (210-3) = 158
MR-5 = 82
Small (Draper-Lin) = 71

Design-Expert vers 36
ion 7
MR-5 CCDs (k = 6 to 30)
Number of runs closer to small CCD

Design-Expert vers 37
ion 7
MR-5 CCDs (k=10, = 1.778)
Regular, MR-5 and Small CCDs

210-3 CCD MR-5 Small


158 runs CCD CCD
82 runs 71 runs

Model 65 65 65

Residuals 92 16 5

Lack of Fit 83 11 1

Pure Error 9 5 4

Corr Total 157 81 70

Design-Expert vers 38
ion 7
MR-5 CCDs (k=10, = 1.778)
Properties of Regular, MR-5 and Small CCDs

210-3 CCD MR-5 CCD Small CCD


158 runs 82 runs 71 runs
Max coefficient SE 0.214 0.227 16.514

Max VIF 1.543 2.892 12,529

Max leverage 0.498 0.991 1.000

Ave leverage 0.418 0.805 0.930

Scaled D-optimality 1.568 2.076 3.824

Design-Expert vers 39
ion 7
MR-5 CCDs (k=10, = 1.778)
Properties closer to regular CCD

A-B slice

4 4 16
14
3 3 12
StdErr of Design

StdErr of Design

StdErr of Design
10
2 2 8
6
1 1 4
2
0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
B: B -0.50 0.00 B: B -0.50 0.00 B: B -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

210-3 CCD MR-5 CCD Small CCD


158 runs 82 runs 71 runs
different y-axis scale

Design-Expert vers 40
ion 7
MR-5 CCDs (k=10, = 1.778)
Properties closer to regular CCD

A-C slice

4 4 4

3 3 3
StdErr of Design

StdErr of Design

StdErr of Design
2 2 2

1 1 1

0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
C: C -0.50 0.00 C: C -0.50 0.00 C: C -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

210-3 CCD MR-5 CCD Small CCD


158 runs 82 runs 71 runs
all on the same y-axis scale

Design-Expert version 41
7
MR-5 CCDs
Conclusion

Best of both worlds:


The number of runs are closer to the number in the
small than in the regular CCDs.
Properties of the MR-5 designs are closer to those of
the regular than the small CCDs.
The standard errors of prediction are higher than
regular CCDs, but not extremely so.
Blocking options are limited to 1 or 2 blocks.

Design-Expert vers 42
ion 7
Practical alpha
Choosing an alpha value for your CCD

Problems arise as the number of factors increase:


The standard error of prediction for the face centered
CCD (alpha = 1) increases rapidly. We feel that an
alpha > 1 should be used when k > 5.
The rotatable and spherical alpha values become too
large to be practical.
Solution:
Use an in between value for alpha, i.e. use a practical
alpha value.
practical alpha = (k)

Design-Expert vers 43
ion 7
Standard Error Plots 26-1 CCD
Slice with the other four factors = 0

1 1 1

0.8 0.8 0.8


StdErr of Design

StdErr of Design
StdErr of Design
0.6 0.6 0.6

0.4 0.4 0.4

0.2 0.2 0.2

0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
B: B -0.50 0.00 B: B -0.50 0.00 B: B -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

Face Centered Practical Spherical


= 1.000 = 1.565 = 2.449

Design-Expert version 44
7
Standard Error Plots 26-1 CCD
Slice with two factors = +1 and two = 0

1 1 1

0.8 0.8 0.8


StdErr of Design

StdErr of Design
StdErr of Design
0.6 0.6 0.6

0.4 0.4 0.4

0.2 0.2 0.2

0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
B: B -0.50 0.00 B: B -0.50 0.00 B: B -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

Face Centered Practical Spherical


= 1.000 = 1.565 = 2.449

Design-Expert version 45
7
Standard Error Plots MR-5 CCD (k=30)
Slice with the other 28 factors = 0

1 1 1

0.8 0.8 0.8


StdErr of Design

StdErr of Design
StdErr of Design
0.6 0.6 0.6

0.4 0.4 0.4

0.2 0.2 0.2

0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
B: B -0.50 0.00 B: B -0.50 0.00 B: B -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

Face Centered Practical Spherical


= 1.000 = 2.340 = 5.477

Design-Expert version 46
7
Standard Error Plots MR-5 CCD (k=30)
Slice with 14 factors = +1 and 14 = 0

2.4 2.4 2.4

2 2 2
StdErr of Design

StdErr of Design
StdErr of Design
1.6 1.6 1.6

1.2 1.2 1.2

0.8 0.8 0.8

0.4 0.4 0.4

0 0 0

1.00 1.00 1.00

0.50 0.50 0.50


1.00 1.00 1.00
0.00 0.50 0.00 0.50 0.00 0.50
B: B -0.50 0.00 B: B -0.50 0.00 B: B -0.50 0.00
-0.50 -0.50 -0.50
-1.00 -1.00 -1.00 -1.00 -1.00 -1.00
A: A A: A A: A

Face Centered Practical Spherical


= 1.000 = 2.340 = 5.477

Design-Expert version 47
7
Choosing an alpha value for your CCD

Design-Expert vers 48
ion 7
D-optimal Design
Coordinate versus Point Exchange

There are two algorithms to select optimal points for


estimating model coefficients:
Point exchange
Coordinate exchange

Design-Expert vers 49
ion 7
D-optimal Coordinate Exchange*

Cyclic Coordinate Exchange Algorithm


1. Start with a nonsingular set of model points.
2. Step through the coordinates of each design point
determining if replacing the current value increases the
optimality criterion. If the criterion is improved, the new
coordinate replaces the old. (The default number of steps
is twelve. Therefore 13 levels are tested between the low and
high factor constraints; usually 1.)
3. The exchanges continue and cycle through the model
points until there is no further improvement in the
optimality criterion.
* R.K. Meyer, C.J. Nachtsheim (1995), The Coordinate-Exchange Algorithm for
Constructing Exact Optimal Experimental Designs, Technometrics, 37, 60-69.
Design-Expert vers 50
ion 7

Das könnte Ihnen auch gefallen