Scribd
Upload
91 views3 pages

5.3.3.3.3. Blocking of Full Factorial Designs

This document discusses blocking in full factorial designs. Blocking is used to eliminate the influence of extraneous factors, such as changes in raw materials, by dividing the experiment into blocks. For a 2^3 factorial design, blocks can be created by assigning runs to alternating corners of the design space. Formally, this works by assigning the estimation of the unwanted blocking effect to a higher-order interaction term, confounding the block effect with the higher-order interaction. Software can perform blocking automatically but it is important to understand that block effects become confounded with higher-order interactions as a result.

Uploaded by

haniff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
91 views3 pages

5.3.3.3.3. Blocking of Full Factorial Designs

This document discusses blocking in full factorial designs. Blocking is used to eliminate the influence of extraneous factors, such as changes in raw materials, by dividing the experiment into blocks. For a 2^3 factorial design, blocks can be created by assigning runs to alternating corners of the design space. Formally, this works by assigning the estimation of the unwanted blocking effect to a higher-order interaction term, confounding the block effect with the higher-order interaction. Software can perform blocking automatically but it is important to understand that block effects become confounded with higher-order interactions as a result.

Uploaded by

haniff
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

8/12/2018 5.3.3.3.3.

Blocking of full factorial designs

5. Process Improvement
5.3. Choosing an experimental design
5.3.3. How do you select an experimental design?
5.3.3.3. Full factorial designs

5.3.3.3.3. Blocking of full factorial designs

Eliminate the We often need to eliminate the influence of extraneous


influence of factors when running an experiment. We do this by
extraneous "blocking".
factors by
"blocking" Previously, blocking was introduced when randomized
block designs were discussed. There we were concerned
with one factor in the presence of one of more nuisance
factors. In this section we look at a general approach that
enables us to divide 2-level factorial experiments into
blocks.

For example, assume we anticipate predictable shifts will


occur while an experiment is being run. This might happen
when one has to change to a new batch of raw materials
halfway through the experiment. The effect of the change in
raw materials is well known, and we want to eliminate its
influence on the subsequent data analysis.

Blocking in a In this case, we need to divide our experiment into two


23 factorial halves (2 blocks), one with the first raw material batch and
design the other with the new batch. The division has to balance out
the effect of the materials change in such a way as to
eliminate its influence on the analysis, and we do this by
blocking.

Example Example: An eight-run 23 full factorial has to be blocked


into two groups of four runs each. Consider the design `box'
for the 23 full factorial. Blocking can be achieved by
assigning the first block to the dark-shaded corners and the
second block to the open circle corners.

Graphical FIGURE 3.3 Blocking Scheme for a 23 Using Alternate


representation Corners
of blocking
scheme

https://www.itl.nist.gov/div898/handbook/pri/section3/pri3333.htm 1/3
8/12/2018 5.3.3.3.3. Blocking of full factorial designs

Three-factor This works because we are in fact assigning the `estimation'


interaction of the (unwanted) blocking effect to the three-factor
confounded interaction, and because of the special property of two-level
with the block designs called orthogonality. That is, the three-factor
effect interaction is "confounded" with the block effect as will be
seen shortly.

Orthogonality Orthogonality guarantees that we can always estimate the


effect of one factor or interaction clear of any influence due
to any other factor or interaction. Orthogonality is a very
desirable property in DOE and this is a major reason why
two-level factorials are so popular and successful.

Table showing Formally, consider the 23 design table with the three-factor
blocking interaction column added.
scheme
TABLE 3.10 Two Blocks for a 23 Design
SPEED FEED DEPTH BLOCK
X1 X2 X3 X1*X2*X3
-1 -1 -1 -1 I
+1 -1 -1 +1 II
-1 +1 -1 +1 II
+1 +1 -1 -1 I
-1 -1 +1 +1 II
+1 -1 +1 -1 I
-1 +1 +1 -1 I
+1 +1 +1 +1 II

Block by Rows that have a `-1' in the three-factor interaction column


assigning the are assigned to `Block I' (rows 1, 4, 6, 7), while the other
"Block effect" rows are assigned to `Block II' (rows 2, 3, 5, 8). Note that
https://www.itl.nist.gov/div898/handbook/pri/section3/pri3333.htm 2/3
8/12/2018 5.3.3.3.3. Blocking of full factorial designs

to a high- the Block I rows are the open circle corners of the design
order `box' above; Block II are dark-shaded corners.
interaction

Most DOE The general rule for blocking is: use one or a combination of
software will high-order interaction columns to construct blocks. This
do blocking gives us a formal way of blocking complex designs. Apart
for you from simple cases in which you can design your own blocks,
your statistical/DOE software will do the blocking if asked,
but you do need to understand the principle behind it.

Block effects The price you pay for blocking by using high-order
are interaction columns is that you can no longer distinguish the
confounded high-order interaction(s) from the blocking effect - they
with higher- have been `confounded,' or `aliased.' In fact, the blocking
order effect is now the sum of the blocking effect and the high-
interactions order interaction effect. This is fine as long as our
assumption about negligible high-order interactions holds
true, which it usually does.

Center points Within a block, center point runs are assigned as if the block
within a block were a separate experiment - which in a sense it is.
Randomization takes place within a block as it would for
any non-blocked DOE.

https://www.itl.nist.gov/div898/handbook/pri/section3/pri3333.htm 3/3

You might also like