Design of experiments (DOE) is defined as a branch of applied statistics that deals with
planning, conducting, analyzing, and interpreting controlled tests to evaluate the factors that
control the value of a parameter or group of parameters. DOE is a powerful data collection and
analysis tool that can be used in a variety of experimental situations.
It allows for multiple input factors to be manipulated, determining their effect on the desired
output (response). By manipulating multiple inputs at the same time, DOE can identify
important interactions that may be missed when experimenting with one factor at a time. All
possible combinations can be investigated (full factorial) or only a portion of the possible
combinations (fractional factorial).
A strategically planned and executed experiment may provide a great deal of information about
the effect on a response variable due to one or more factors. Many experiments involve holding
certain factors constant and altering the levels of another variable. This "one factor at a time"
(OFAT) approach to processing knowledge is, however, inefficient when compared with
changing factor levels simultaneously.
Many of the current statistical approaches to designed experiments originate from the work of
R. A. Fisher in the early part of the 20th century. Fisher demonstrated how taking the time to
seriously consider the design and execution of an experiment before trying it helped avoid
frequently encountered problems in analysis. Key concepts in creating a designed experiment
include blocking, randomization, and replication.
Blocking:
When randomizing a factor is impossible or too costly, blocking lets you restrict
randomization by carrying out all of the trials with one set of the factor and then all the trials
with the other setting.
Randomization:
Refers to the order in which the trials of an experiment are performed. A
randomized sequence helps eliminate the effects of unknown or uncontrolled variables.
Replication:
Repetition of a complete experimental treatment, including the setup.
A well-performed experiment may provide answers to questions such as:
What are the key factors in a process?
At what settings would the process deliver acceptable performance?
What are the key, main, and interaction effects in the process?