pg_0166
5.
Process Improvement
5.4.
Analysis of DOE data
5.4.7.
Examples of DOE's
Software
packages do
the
calculations
and plot the
graphs for a
DOE
analysis: the
analyst has
to know
what to
request and
how to
interpret the
results
Most DOE analyses of industrial experiments will be performed by
statistical software packages. Good statistical software enables the
analyst to view graphical displays and to build models and test
assumptions. Occasionally the goals of the experiment can be achieved
by simply examining appropriate graphical displays of the experimental
responses. In other cases, a satisfactory model has to be fit in order to
determine the most significant factors or the optimal contours of the
response surface. In any case, the software will perform the appropriate
calculations as long as the analyst knows what to request and how to
interpret the program outputs.
Three
detailed
DOE
analyses
will be given
using JMP
software
Perhaps one of the best ways to learn how to use DOE analysis software
to analyze the results of an experiment is to go through several detailed
examples, explaining each step in the analysis. This section will
illustrate the use of JMP 3.2.6 software to analyze three real
experiments. Analysis using other software packages would generally
proceed along similar paths.
The examples cover three basic types of DOE's:
A full factorial experiment
1.
A fractional factorial experiment
2.
A response surface experiment
3.
5.4.7. Examples of DOE's
http://www.itl.nist.gov/div898/handbook/pri/section4/pri47.htm [5/7/2002 4:02:07 PM]
Hosted free by FREE WEBSITES - Free Hosting with Online Website Builder!
