'Dig deeper' in analysis
with the latest version
A new release of DOEpack, a program
that supports experimental design and underpins Six Sigma efforts,
facilitates deeper analyses with its panoply of new features. Those
who want to "dig deep" to solve problems will find that DOEpack
EZ 4.0 will help them do just that.
Expanded study analysis, both within and across
studies, can be displayed in multi-chart format for quick analysis
and comparison, and DOEpack EZ can manage multiple responses
simultaneously with scatter plots and desirability analysis as well.
Jeff Aughton, a member of the PQ Systems development
team in its England office, has led the effort to broaden the program’s
usefulness and enhance its ease of use. PQ Systems consultant Gordon
K. Constable, Ph.D., is a principal participant in the program’s
improvement. Aughton points out that a New Experiment Wizard will
guide users step by step through a new experiment, from selecting
a design to running the experiment. Setting up an experiment becomes
“as easy as reading a recipe.” Navigation, too, is easy—hence
the product’s ‘EZ’ designation.
Situations involving the "right" mix of component
parts create special problems for experimental design, since the
factors are constrained in that they must sum to 1 (or 100%). DOEpack
EZ includes popular mixture designs such as Simplex and
Simplex-Centroid to facilitate this analysis. Two- and 3-factor
contour plots complement these designs. The program also offers
regression analysis, scanning all possible regression equations
and selecting the best one for a given experiment, thus saving time
and resources that might be invested in running multiple regression
An advantage of two-level designs lies in the reduction
in runs required to complete a study. A corresponding disadvantage
is that of determining whether the factor has a linear or non-linear
effect. DOEpack EZ uses center and axial points to test
for linearity with a minimal amount of additional experimentation.
Small amounts of data can be tested for linearity to determine the
viability of conducting follow-up experiments—again, saving
resources that would be expended in running several experiements.
PQ Systems is an industry leader in statistical
process control (SPC) and quality management software. The company
also offers training for SPC, measurement systems analysis, and
quality improvement, as well as materials to support this training
and provide statistical and problem-solving tools.
Copyright 2005 PQ Systems.
Please direct questions or problems regarding this web site to the Webmaster.