2k Factorial Designs

By: Stephanie M. Bernas (BSEE 2A)

Outline of Topics:
1. 2k Factorial Designs
2. Single Replicate of the 2k Design
3. Addition of Center Points to a 2k Design
4. Blocking and Confounding in the 2k Design
5. Fractional Replication of the 2k Design
 One-Half Fraction of the 2k Design
 Smaller Fractions: The 2k-p Fractional Factorial
6. Response Surface Methods and Designs

1. 2k Factorial Designs
Factorial designs are frequently used in experiments involving several factors where it is
necessary to study the joint effect of the factors on a response or screening variables. However,
several special cases of the general factorial design are important because they are widely employed
in research work and because they form the basis of other designs of considerable practical value.
The most important of these special cases is that of k factors, each at only two levels. Using
only two levels are enough to determine whether a variable is significant to affect a process or not.
These levels may be quantitative, such as two values of temperature, pressure, or time; or they may
be qualitative, such as two machines, two operators, the “high’’ and “low’’ levels of a factor, or perhaps
the presence and absence of a factor. A complete replicate of such a design requires 2 x 2 x . . . x 2 =
2k observations and is called a 2k factorial design.

Equation 1 - 2k factorial design

If k number of variables/factors are studied to determine/screen the important ones, the total
number of treatment combinations for a k number of factors can be calculated as in Equation 1.
The 2k design is particularly useful in the early stages of experimental work when many
factors are likely to be investigated. It provides the smallest number of runs for which k factors can be
studied in a complete factorial design. Because there are only two levels for each factor, we must
assume that the response is approximately linear over the range of the factor levels chosen. A key
use of such designs is to identify which of many variables is most important and should be considered
for further analysis in more detail.
This is typically done when we have lots of variables for example we have A-D. When we are
interested in many variables what we do is typically we take two levels of these variables just the low
and high. And then we run all of these variables and see the effect on the response Y.

So not all of these variables are really affecting the response maybe one or two are significant and the
rest are not.

So this is a type of screening experiment we do to screen the factors.

Note:
Therefore, this screening technique is known as the 2K design of experiments. More
specifically, this experiment should be named as the completely randomized 2K factorial design of
experiments. Recent popular textbooks on the design of experiment refer this design as the 2K design
(Box et al., 2005; Montgomery, 2019) , while the earlier texts refer the design as 2n design
(Hinkelmann & Kempthorne, 2008; Kempthorne, 1952; Yates, 1978), 2f (Hicks, 1964), 2p, and so on.
However, recently, 2K name has been popular for the factorial design of experiments with multiple
factors with two levels for each factor.
Example:
a. 22 Factorial Design
The simplest type of 2k design is the 22—that is, two factors A and B, each at two levels. We
usually think of these levels as the low and high levels of the factor. The 2 2 design is shown in Fig. 1.

Figure 1 – The 22 Factorial Design

Note:
The design can be represented geometrically as a square with the 2 2 = 4 runs, or treatment
combinations, forming the corners of the square. In the 2 2 design it is customary to denote the low and
high levels of the factors A and B by the signs - and +, respectively. This is sometimes called the
geometric notation for the design.

 a = indicates that factor A is at the high level and factor B is at the low level
 b = indicates that factor A is at the low level and factor B is at the high level
 (1) = indicates that the treatment combination with both factors A and B is at the low level
 ab = indicates that factor A and B is at high level
Let the letters (1), a, b, and ab also represent the totals of all n observations taken at these design
points. The effects of interest in the 2 2 design are the main effects A and B and the two-factor
interaction AB. Let the letters (1), a, b, and ab also represent the totals of all n observations taken at
these design points. It is easy to estimate the effects of these factors. To estimate the main effect of A,
we would average the observations on the right side of the square in Fig. 1 where A is at the high
level, and subtract from this the average of the observations on the left side of the square, where A is
at the low level, or

Equation 2 - Main Effect of Factor A: 22 Design

Similarly, the main effect of B is found by averaging the observations on the top of the square,
where B is at the high level, and subtracting the average of the observations on the bottom of the
square, where B is at the low level:
 Equation 3 - Main Effect of Factor B: 22 Design

Finally, the AB interaction is estimated by taking the difference in the diagonal averages

Equation 4 - Interaction Effect AB: 22 Design

2. Single Replicate of the 2k Design

As the number of factors in a factorial experiment grows, the number of effects that can be
estimated also grows.
Example:
a. 23 Experiment
 3 main effects = A, B, C,
 3 two-factor interactions = AB, AC, BC
 1 three-factor interaction = ABC
b. 24 Experiment
 4 main effects = A, B, C, D
 6 two-factor interactions = AB, AC, AD, BC, BD, CD
 4 three-factor interactions = ABC, ABD, BCD, ACD
 1 four-factor interaction = ABCD
c. 26 Experiment
 6 main effects = A, B, C, D, E, F
 15 two-factor interactions
 20 three-factor interactions
 15 four-factor interactions
 6 five-factor interactions
 1 six-factor interaction
Sparsity of effects principle

 The system is usually dominated by the main effects and low-order interactions. The three-
factor and higher order interactions are usually negligible. Therefore, when the number of
factors is moderately large, say, k ≥ 4 or 5, a common practice is to run only a single replicate
of the 2k design and then pool or combine the higher order interactions as an estimate of
error. Sometimes a single replicate of a 2k design is called an unreplicated 2k factorial design.
Note:
When analyzing data from unreplicated factorial designs, occasionally real high-order
interactions occur. The use of an error mean square obtained by pooling high-order interactions is
inappropriate in these cases. A simple method of analysis can be used to overcome this problem.
Construct a plot of the estimates of the effects on a normal probability scale. The effects that are
negligible are normally distributed, with mean zero and variance 2 and will tend to fall along a straight
line on this plot, whereas significant effects will have nonzero means and will not lie along the straight
line.
Example Problem:
Factors affecting the productivity of Engineering students.

Factors A-D

We measure the productivity using the engineering productivity units and the response to it.
First step is to compute the estimates of each of the factor effects as well as the estimates of each of
the interaction effects.

We can compute the factor effects by multiplying each response by the corresponding plus 1 or minus
1 in the column associated with the factor and do that for every row that we have the data for.

Factor A multiplied by the response.

We can do this using the sum product function as follows.

So this gives us the estimates of the factor effects

Second step is to compute the interaction effects.

Let’s begin by computing the effects of factor A and factor B.

So when we finish this we now have a set of factor effects.

We have the individual factor effects and the second-order interaction effects.

We will not be computing higher-order interaction effects that is the third-order interactions which
includes interactions between three factors and etc. because we are assuming that only the second
order effects are significant.

To determine which of these effects are significant, we can create a normal probability plot, and
determine which ones fall significantly away from the line that represents normality.

Most of the effect estimates fall on a straight line which indicates that they’re approximately normal
but we have three that don’t.

From the probability plot we can find that factors B, D, and the interaction of B and D are significant,
and the other effects are not significant.

The third step is to create a linear regression model that relates the significant effects to the
responses.

For this problem, the linear regression model would have the following form.

Beta 0 is just the average of all the experimental responses

Beta 2 which is the coefficient that corresponds to factor B is the estimate effect for factor B divided by
2.

Beta 4 which is the coefficient that corresponds to factor D is the estimate effect for factor D divided
by 2.

Beta 24 is the interaction effect estimate for the BD interaction divided by 2.

One way to check this model provides a good model for the experimental data is to compute the
model residuals and verify that they are normally distributed.

We can compute the residuals as follows.

First we compute the predictive value yhat, then compute the residuals by taking the response value
then subtracting yhat.

Then we create a normal probability plot of the residuals to check if they’re approximately normal.

If they are then we can assume that our linear regression model represents the relationship between
the factors and the response fairly well.

We can see that our residuals fall more or less along a straight line on this normal probability plot,
which means that they are approximately normal. Which means that our model appears to be a fairly
good one that represents the relationship between the factors and the experimental response.

The last thing we need to do is to create an interaction plot. An interaction plot helps us to see how to
choose the factor values to maximize the experimental response value.

In this case, since the significant effects are factors B and D, we’ll create an interaction plot between
B and D.

To do this we’ll create a table and fill it out with entries for values B of -1 and 1 and entries of D of -1
and 1. Then we will average all the responses that have factor B set at -1 and factor D set at -1.

The we’ll plot this table on the interaction plot. Since the lines on this plot are not parallel, we see that
the values of factor B and D that optimize the response cannot be chosen independently of each
other. In other words, if I were to choose a value of B that gives me the highest value of engineer
productivity it would be B is equal to 1 and I would be thinking about this point. But the actual optimum
value depends on the of D as well. And if D is equal to 1, then my value of 1 for B would not be
optimum. In fact if I choose a value of D equals 1 then my optimum value is obtained when B is equal
to -1.

So the idea behind the interaction plot is if these lines are not parallel it meant that the two factors
interact and I have to optimize them jointly

a. Plasma Etch
An article in Solid State Technology [“Orthogonal Design for Process Optimization and Its
Application in Plasma Etching” (May 1987, pp. 127–132)] describes the application of factorial designs
in developing a nitride etch process on a single wafer plasma etcher. The process uses C 2F6 as the
reactant gas. It is possible to vary the gas flow, the power applied to the cathode, the pressure in the
reactor chamber, and the spacing between the anode and the cathode (gap).
We will use a single replicate of a 2 4 design to investigate this process. Since it is unlikely that the
three- and four-factor interactions are significant, we will tentatively plan to combine them as an
estimate of error.
The factor levels used in the design are shown below:
 Table 1 - The 24 Design for the Plasma Etch
Experiment

Table 2 - Contrast Constants for the 24 Design

The signs in the columns of this table can be used to estimate the factor effects.
Estimate effect of factor A:
Estimate effect of all factors:

The normal probability plot of these effects from the plasma etch experiment is shown in Fig.
2. Clearly, the main effects of A and D and the AD interaction are significant because they fall far from
the line passing through the other points.

Figure 2 - Normal probability plot of effects from the plasma etch experiment.

The analysis of variance summarized in Table 3 confirms these findings.

Table 3 - Analysis of Variance for the Plasma Etch Experiment

Practical Interpretation:
Since A = -101.625, the effect of increasing the gap between the cathode and anode is to
decrease the etch rate. However, D = 306.125; thus, applying higher power levels will increase the
etch rate.

Figure 3 - AD (Gap-Power) interaction from the plasma etch experiment.

This plot indicates that the effect of changing the gap width at low power settings is small, but
that increasing the gap at high power settings dramatically reduces the etch rate. High etch rates are
obtained at high power settings and narrow gap widths.

3. Addition of Center Points to a 2k Design

Method of replicating certain points in the 2k factorial that will provide protection against curvature
as well as allow an independent estimate of error to be obtained. The method consists of adding
center points to the 2k design. These consist of nC replicates run at the point xi = 0 (i = 1, 2, . . . , k).
One important reason for adding the replicate runs at the design center is that center points do not
affect the usual effects estimates in a 2k design. We assume that the k factors are quantitative.
Example:
a. 22 Design
Consider a 22 design with one observation at each of the factorial points (-, -), (+, -), (-, +), and (+,
+) and nC observations at the center points (0, 0).

Figure 4 - A 22 design with center points.

 Equation 5 - Curvature Sum of Squares

Equation 6 - Mean Square Error

When points are added to the center of the 2k design, the model we may entertain is:

Test for curvature:

Example Problem:
a. Process Yield
A chemical engineer is studying the percentage of conversion or yield of a process. There are
two variables of interest, reaction time and reaction temperature. Because she is uncertain about the
assumption of linearity over the region of exploration, the engineer decides to conduct a 22 design
(with a single replicate of each factorial run) augmented with five center points. The design and the
yield data are shown in Fig. 5.
 Figure 5 - The 22 design with five center points

Table 4 - Analysis of Variance

The mean square error is calculated from the center points as follows:

The average of the points in the factorial portion of the design is yF = 40.425, and the
average of the points at the center is yC = 40.46. The difference yF - yC = 40.425 - 40.46 = 0.035
appears to be small.
The curvature sum of squares in the analysis of variance table is computed as follows:
Practical Interpretation:
The analysis of variance indicates that both factors exhibit significant main effects, that there
is no interaction, and that there is no evidence of curvature in the response over the region of
exploration. That is, the null hypothesis H cannot be rejected.

4. Blocking and Confounding in the 2k Design

Blocking

 It is the design technique that is appropriate for this general situation where it is often
impossible to run all the observations in a 2k factorial design under homogeneous conditions.
Cofounding

 However, in many situations the block size is smaller than the number of runs in the complete
replicate. In these cases, confounding is a useful procedure for running the 2 k design in 2p
blocks where the number of runs in a block is less than the number of treatment combinations
in one complete replicate. The technique causes certain interaction effects to be
indistinguishable from blocks or confounded with blocks. We will illustrate confounding in the
2k factorial design in 2p blocks, where p < k.
Example:
a. 22 Design
Suppose that each of the 22 = 4 treatment combinations requires four hours of laboratory analysis.
Thus, two days are required to perform the experiment. If days are considered as blocks, we must
assign two of the four treatment combinations to each day.

Figure 6 - A 22 design in two blocks.

Block 1 contains the treatment combinations (1) and ab. Block 2 contains a and b.
The contrasts for estimating the main effects of factors A and B are:

Note:
These contrasts are unaffected by blocking since in each contrast there is one plus and one
minus treatment combination from each block. That is, any difference between block 1 and block 2
that increases the readings in one block by an additive constant cancel out.
The contrast for the AB interaction is:
 Since the two treatment combinations with the plus signs, ab and (1), are in block 1 and the
two with the minus signs, a and b, are in block 2, the block effect and the AB interaction are identical.
That is, the AB interaction is confounded with blocks.
The reason for this is apparent from the table of plus and minus signs for the 2 2 design shown
in Table 5.

Table 5 - Signs for Effects in the 22 design

From the table we see that all treatment combinations that have a plus on AB are assigned to
block 1, whereas all treatment combinations that have a minus sign on AB are assigned to block 2.
This scheme can be used to confound any 2k design in two blocks.

b. 23 Design
Consider a 23 design, run in two blocks. From the table of plus and minus signs, shown in Table 6,
we assign the treatment combinations that are minus in the ABC column to block 1 and those that are
plus in the ABC column to block 2.

Table 6 - Algebraic Signs for Calculating Effects in the 2 3 Design

The resulting design is shown in Fig. 7.

 Figure 7 - The 23 design in two blocks with ABC confounded.

Defining contrast

 A more general method of constructing the blocks.

Equation 7 – Defining Contrast

Where:
xi = the level of the ith factor appearing in a treatment combination
αi = the exponent appearing on the ith factor in the effect that is to be confounded with blocks

For the 2k system:

αi = 0 or 1
xi = 0 (low level)
xi = 1 (high level)

Treatment combinations that produce the same value of L (modulus 2) will be placed in the
same block. Since the only possible values of L (mod 2) are 0 and 1, this will assign the 2 k treatment
combinations to exactly two blocks.
Consider the 23 design with ABC confounded with blocks. Here x 1 corresponds to A, x2 to B, x3
to C, and α1 = α2 = α3 = 1. Thus, the defining contrast that would be used to confound ABC with blocks
is:

To assign the treatment combinations to the two blocks, we substitute the treatment
combinations into the defining contrast as follows:
 Thus (1), ab, ac, and bc are run in block 1, and a, b, c, and abc are run in block 2. This same
design is shown in Fig. 7.

5. Fractional Replication of the 2k Design

As the number of factors in a 2 k factorial design increases, the number of runs required increases
rapidly. For example, a 25 requires 32 runs. In this design, only 5 degrees of freedom correspond to
main effects, and 10 degrees of freedom correspond to two-factor interactions. Sixteen of the 31
degrees of freedom are used to estimate high-order interactions— that is, three-factor and higher
order interactions.
Often there is little interest in these high order interactions, particularly when we first begin to
study a process or system. If we can assume that certain high-order interactions are negligible, a
fractional factorial design involving fewer than the complete set of 2 k runs can be used to obtain
information on the main effects and low-order interactions.
This section will introduce fractional replications of the 2 k design. A major use of fractional
factorials is in screening experiments. These are experiments in which many factors are considered
with the purpose of identifying those factors (if any) that have large effects. Screening experiments
are usually performed in the early stages of a project when it is likely that many of the factors initially
considered have little or no effect on the response. The factors that are identified as important are
then investigated more thoroughly in subsequent experiments.

One-Half Fraction of the 2k Design

A one-half fraction of the 2k design contains 2k-1 runs and is often called a 2k-1 fractional
factorial design.
Example:
a. 23-1 design
This design has only four runs, in contrast to the full factorial that would require eight runs. The
table of plus and minus signs for the 23 design is shown in Table 9. Suppose we select the four
treatment combinations a, b, c, and abc, as our one-half fraction. These treatment combinations are
shown in the top half of Table 9 and in Fig. 10(a).
 Table 9 – Plus and Minus Signs for the 2 3 Factorial Design

Figure 10 – The one-half fractions of the 2 3 design.

Notice that the 23-1 design is formed by selecting only those treatment combinations that yield
a plus on the ABC effect. Thus, ABC is called the generator of this particular fraction. Furthermore,
the identity element I is also plus for the four runs, so we call this formula as the defining relation for
the design.

The treatment combinations in the 23-1 design yields three degrees of freedom associated with
the main effects. From the upper half of Table 9, we obtain the estimates of the main effects as linear
combinations of the observations, say,

It is also easy to verify that the estimates of the two-factor interactions should be the following
linear combinations of the observations:
 Thus, the linear combination of observations in column A, ℓA estimates both the main effect of
A and the BC interaction. That is, the linear combination ℓA estimates the sum of these two effects A +
BC. Similarly, ℓB estimates B + AC, and estimates C + AB. Two or more effects that have this property
are called aliases. In our 231 design, A and BC are aliases, B and AC are aliases, and C and AB are
aliases. Aliasing is the direct result of fractional replication. In many practical situations, it will be
possible to select the fraction so that the main effects and low-order interactions that are of interest
will be aliased only with high-order interactions (which are probably negligible).
The alias structure for this design is found by using the defining relation I = ABC. Multiplying
any effect by the defining relation yields the aliases for that effect. In our example, the alias of A is:

since A . I = A and A2 = I. The aliases of B and C are:

Now suppose that we had chosen the other one-half fraction, that is, the treatment
combinations in Table 9 associated with minus on ABC. These four runs are shown in the lower half of
Table 9 and in Fig. 10(b). The defining relation for this design is I = -ABC. The aliases are A = -BC, B =
-AC, and C = -AB. Thus, estimates of A, B, and C that result from this fraction really estimate A - BC,
B - AC, and C - AB. In practice, it usually does not matter which one-half fraction we select. The
fraction with the plus sign in the defining relation is usually called the principal fraction, and the other
fraction is usually called the alternate fraction.
Note that if we had chosen AB as the generator for the fractional factorial and the two main
effects of A and B would be aliased. This typically loses important information.

Sometimes we use sequences of fractional factorial designs to estimate effects.

Example:
a. 23-1 Design
Suppose we had run the principal fraction of the 2 3-1 design with generator ABC. From this design
we have the following effect estimates:

Suppose that we are willing to assume at this point that the two-factor interactions are
negligible. If they are, the 2 3-1 design has produced estimates of the three main effects A, B, and C.
However, if after running the principal fraction we are uncertain about the interactions, it is possible to
estimate them by running the alternate fraction. The alternate fraction produces the following effect
estimates:
 We may now obtain de-aliased estimates of the main effects and two-factor interactions by
adding and subtracting the linear combinations of effects estimated in the two individual fractions. For
example, suppose we want to de-alias A from the two-factor interaction BC. Since ℓA = A + BC and ℓ’A
= A - BC, we can combine these effect estimates as follows:

For all three pairs of effect estimates, we would obtain the following results:

Thus, by combining a sequence of two fractional factorial designs, we can isolate both the
main effects and the two-factor interactions. This property makes the fractional factorial design highly
useful in experimental problems since we can run sequences of small, efficient experiments, combine
information across several experiments, and take advantage of learning about the process we are
experimenting with as we go along. This is an illustration of the concept of sequential experimentation.
A 2k-1 design may be constructed by writing down the treatment combinations for a full
factorial with k-1 factors, called the basic design, and then adding the kth factor by identifying its plus
and minus levels with the plus and minus signs of the highest order interaction. Therefore, a 2 3-1
fractional factorial is constructed by writing down the basic design as a full 2 2 factorial and then
equating factor C with the ±AB interaction. Thus, to construct the principal fraction, we would use C =
±AB as follows:

To obtain the alternate fraction we would equate the last column to C = -AB.
Sample Problem:
a. Plasma Etch
An article in Solid State Technology [“Orthogonal Design for Process Optimization and Its
Application in Plasma Etching” (May 1987, pp. 127–132)] describes the application of factorial designs
in developing a nitride etch process on a single wafer plasma etcher. The process uses C 2F6 as the
reactant gas. It is possible to vary the gas flow, the power applied to the cathode, the pressure in the
reactor chamber, and the spacing between the anode and the cathode (gap). Several response
variables would usually be of interest in this process, but in this example, we will concentrate on etch
rate for silicon nitride.
Suppose that we decide to use a 2 4-1 design with I = ABCD to investigate the four factors gap
(A), pressure (B), C2F6 flow rate (C), and power setting (D). This design would be constructed by
writing down as the basic design a 23 in the factors A, B, and C and then setting the levels of the
fourth factor D = ABC. The design and the resulting etch rates are shown in Table 10. The design is
shown graphically in Fig. 11.
In this design, the main effects are aliased with the three-factor interactions; note that the
alias of A is:

and similarly B = ACD, C = ABD, and D = ABC. The two-factor interactions are aliased with each
other. For example, the alias of AB is CD:

Table 10 – The 24-1 Design with Defining Relation I = ABCD

Figure 11 – The 24-1 Design for the experiment

The other aliases are AC = BD and AD = BC. The estimates of the main effects and their aliases are
found using the four columns of signs in Table 10. For example, from column A we obtain the
estimated effect:
The other columns produce:

Clearly, ℓA and ℓB are large, and if we believe that the three-factor interactions are negligible,
the main effects A (gap) and D (power setting) significantly affect etch rate.
The interactions are estimated by forming the AB, AC, and AD columns and adding them to
the table. For example, the signs in the AB column are +, -, -, +, +, -, -, + and this column produces
the estimate:

The ℓAD estimate is large; the most straightforward interpretation of the results is that since A
and D are large, this is the AD interaction. Thus, the results obtained from the 2 4-1 design agree with
the full factorial results in the example.
Practical Interpretation:
Often a fraction of a 2k design is satisfactory when an experiment uses four or more factors.
Computer Solution
Fractional factorial designs are usually analyzed with a software package. Table 10 shows the
effect estimates obtained from Minitab for the example. They are in agreement with the hand
calculation reported earlier.
Normal Probability Plot of Effects
The normal probability plot is very useful in assessing the significance of effects from a
fractional factorial design, particularly when many effects are to be estimated. We strongly
recommend examining this plot. Figure 12 presents the normal probability plot of the effects from the
example. This plot was obtained from Minitab. Notice that the A, D, and AD interaction effects stand
out clearly in this graph.

Figure 12 - Normal probability plot of the effects from Minitab

Residual Analysis
The residuals can be obtained from a fractional factorial by the regression model method
shown previously. Note that the Minitab output for the example in Table 11 shows the regression
coefficients. The residuals should be graphically analyzed as we have discussed before, both to
assess the validity of the underlying model assumptions and to gain additional insight into the
experimental situation.

Table 11 – Effect Estimates from Minitab

Projection of the 2k-1 Design

If one or more factors from a one-half fraction of a 2 k can be dropped, the design will project
into a full factorial design. For example, Fig. 13 presents a 2 3-1 design. Notice that this design will
project into a full factorial in any two of the three original factors. Thus, if we think that at most two of
the three factors are important, the 2 3-1 design is an excellent design for identifying the significant
factors. This projection property is highly useful in factor screening, because it allows negligible
factors to be eliminated, resulting in a stronger experiment in the active factors that remain.

Figure 13 - Projection of a 23-1 design into three 22 designs.

In the 24-1 design used in the plasma etch experiment, we found that two of the four factors (B
and C) could be dropped. If we eliminate these two factors, the remaining columns in Table 8 form a
22 design in the factors A and D, with two replicates. This design is shown in Fig. 14. The main effects
of A and D and the strong two-factor AD interaction are clearly evident from this graph.
 Table 8 – Analysis of Variance

Figure 14 - The 22 design obtained by dropping factors B and C

from the plasma etch experiment.

Design Resolution
The concept of design resolution is a useful way to catalog fractional factorial designs
according to the alias patterns they produce. Designs of resolution III, IV, and V are particularly
important. The definitions of these terms and an example of each follow.
1. Resolution III Designs. These are designs in which no main effects are aliased with any other main
effect, but main effects are aliased with two-factor interactions and some two-factor interactions may
be aliased with each other. The 23-1 design with I = ABC is a resolution III design. We usually employ a
3−1
Roman numeral subscript to indicate design resolution; thus, this one-half fraction is a 2 III design.

2. Resolution IV Designs. These are designs in which no main effect is aliased with any other main
effect or two-factor interactions, but two-factor interactions are aliased with each other. The 24-1 design
4 −1
with I = ABCD used in the plasma etch example is a resolution IV design (2 IV ).

3. Resolution V Designs. These are designs in which no main effect or two-factor interaction is aliased
with any other main effect or two-factor interaction, but two-factor interactions are aliased with three-
5−1
factor interactions. The 25-1 design with I = ABCDE is a resolution V design (2V ).

Resolution III and IV designs are particularly useful in factor screening experiments. A resolution IV
design provides good information about main effects and will provide some information about all two-
factor interactions.

Smaller Fractions: The 2k-p Fractional Factorial

 Although the 2k-1 design is valuable in reducing the number of runs required for an
experiment, we frequently find that smaller fractions will provide almost as much useful information at
even greater economy. In general, a 2 k design may be run in a 1/2p fraction called a 2 k-p fractional
factorial design. Thus, a 1/4 fraction is called a 2 k-2 design, a 1/8 fraction is called a 2 k-3 design, a 1/16
fraction a 2k-4 design, and so on.
Example:
a. ¼ fraction; 2k-2 design
To illustrate the 1/4 fraction, consider an experiment with six factors and suppose that the
engineer is primarily interested in main effects but would also like to get some information about the
two-factor interactions. A 26-1 design would require 32 runs and would have 31 degrees of freedom for
estimating effects. Since there are only six main effects and 15 two factor interactions, the one-half
fraction is inefficient—it requires too many runs.
Suppose we consider a 1/4 fraction, or a 2 6-2 design. This design contains 16 runs and, with 15
degrees of freedom, will allow all six main effects to be estimated, with some capability for examining
the two-factor interactions.
To generate this design, we would write down a 2 4 design in the factors A, B, C, and D as the
basic design and then add two columns for E and F. To find the new columns we could select the two
design generators I = ABCE and I = BCDF. Thus, column E would be found from E = ABC, and
column F would be F = BCD. That is, columns ABCE and BCDF are equal to the identity column.
However, we know that the product of any two columns in the table of plus and minus signs for a 2 k
design is just another column in the table; therefore, the product of ABCE and BCDF or ABCE(BCDF)
= AB2C2DEF = ADEF is also an identity column.
Consequently, the complete defining relation for the 26-2 design is:

We refer to each term in a defining relation (such as ABCE above) as a word. To find the alias of
any effect, simply multiply the effect by each word in the foregoing defining relation. For example, the
alias of A is:

The complete alias relationships for this design are shown in Table 12. In general, the resolution
of a 2k-p design is equal to the number of letters in the shortest word in the complete defining relation.
Therefore, this is a resolution IV design; main effects are aliased with three-factor and higher
interactions, and two-factor interactions are aliased with each other. This design would provide good
information on the main effects and would give some idea about the strength of the two-factor
interactions. The construction and analysis of the design are illustrated in Example 14-9.

6−2
Table 12 – Alias Structure for the 2 IV Design with I = ABCE = BCDF = ADEF
6. Response Surface Methods and Designs
Response surface methodology, or RSM, is a collection of mathematical and statistical techniques
that are useful for modeling and analysis in applications where a response of interest is influenced by
several variables and the objective is to optimize this response. For example, suppose that a
chemical engineer wishes to find the levels of temperature (x 1) and feed concentration (x2) that
maximize the yield (y) of a process. The process yield is a function of the levels of temperature and
feed concentration, say,

where ϵ represents the noise or error observed in the response Y. If we denote the expected
response by E(Y) = f(x1, x2) = ղ, then the surface represented by the formula below is called a
response surface.

We may represent the response surface graphically as shown in Fig. 15, where is plotted
versus the levels of x1 and x2. Notice that the response is represented as a surface plot in a three-
dimensional space. To help visualize the shape of a response surface, we often plot the contours of
the response surface as shown in Fig. 16. In the contour plot, lines of constant response are drawn in
the x1, x2 plane. Each contour corresponds to a particular height of the response surface. The contour
plot is helpful in studying the levels of x 1 and x2 that result in changes in the shape or height of the
response surface.

Figure 15 - A three-dimensional response surface

showing the expected yield as a function of
temperature and feed concentration.

Figure 16 - A contour plot of the yield

response surface in Figure 15.

In most RSM problems, the form of the relationship between the response and the
independent variables is unknown. Thus, the first step in RSM is to find a suitable approximation for
the true relationship between Y and the independent variables. Usually, a low-order polynomial in
some region of the independent variables is employed. If the response is well modeled by a linear
function of the independent variables, the approximating function is the first-order model.
 If there is curvature in the system, then a polynomial of higher degree must be used, such as
the second-order model.

Many RSM problems use one or both of these approximating polynomials. Of course, it is
unlikely that a polynomial model will be a reasonable approximation of the true functional relationship
over the entire space of the independent variables, but for a relatively small region they usually work
quite well.
The method of least squares is used to estimate the parameters in the approximating
polynomials. The response surface analysis is then done in terms of the fitted surface. If the fitted
surface is an adequate approximation of the true response function, analysis of the fitted surface will
be approximately equivalent to analysis of the actual system.
RSM is a sequential procedure. Often, when we are at a point on the response surface that
is remote from the optimum, such as the current operating conditions in Fig. 16, there is little
curvature in the system and the first-order model will be appropriate. Our objective here is to lead the
experimenter rapidly and efficiently to the general vicinity of the optimum. Once the region of the
optimum has been found, a more elaborate model such as the second-order model may be employed,
and an analysis may be performed to locate the optimum. From Fig. 16, we see that the analysis of a
response surface can be thought of as “climbing a hill,” where the top of the hill represents the point of
maximum response. If the true optimum is a point of minimum response, we may think of “descending
into a valley.”
The eventual objective of RSM is to determine the optimum operating conditions for the
system or to determine a region of the factor space in which operating specifications are satisfied.
Also, note that the word “optimum” in RSM is used in a special sense. The “hill climbing” procedures
of RSM guarantee convergence to a local optimum only.

Method of Steepest Ascent

Frequently, the initial estimate of the optimum operating conditions for the system will be far
from the actual optimum. In such circumstances, the objective of the experimenter is to move rapidly
to the general vicinity of the optimum. We wish to use a simple and economically efficient
experimental procedure. When we are remote from the optimum, we usually assume that a first-order
model is an adequate approximation to the true surface in a small region of the x’s.
The method of steepest ascent is a procedure for moving sequentially along the path of
steepest ascent, that is, in the direction of the maximum increase in the response. Of course, if
minimization is desired, we are talking about the method of steepest descent. The fitted first-order
model is:

and the first-order response surface, that is, the contours of , is a series of parallel lines such as that
shown in Fig. 17.
 Figure 17 – First-order response surface and path of steepest ascent.

The direction of steepest ascent is the direction in which increases most rapidly. This direction
is normal to the fitted response surface contours. We usually take as the path of steepest ascent the
line through the center of the region of interest and normal to the fitted surface contours. Thus, the
steps along the path are proportional to the regression coefficients. The experimenter determines the
actual step size based on process knowledge or other practical considerations.
Experiments are conducted along the path of steepest ascent until no further increase in
response is observed. Then a new first-order model may be fit, a new direction of steepest ascent
determined, and further experiments conducted in that direction until the experimenter feels that the
process is near the optimum.
References:
Ahmed, S. (2020). The open educator – 1. What is 2K design. Retrieved April 11, 2023, from
https://www.theopeneducator.com/doe/2K-Factorial-Design-of-Experiments/What-is-2K-
Factorial-Design-of-Experiments
Charles. (2017). @k Factorial Design Basic Concepts. Real Statistics Using Excel. Retrieved April 11,
2023, from https://real-statistics.com/design-of-experiments/2k-factorial-design/2k-factorial-
design-basic-concepts/
Montgomery, D. C., & Runger, G. C. (2011). Chapter 14 Design of Experiments with Several Factors.
In Applied Statistics and Probability for Engineers (5th ed., pp. 571-618). Essay, Don Fowley.