Statistical Test Designs for Experiments

DOES, Inc. has developed new innovative test designs  which allow you to get more information from statistically designed tests. We provide a service of developing test designs for clients.
 

We offer test designs for many purposes:

  • measuring the effects of variables
  • optimization of products and processes
  • product screening
  • formulation of mixtures (blends)
  • quality assessment
  • determination of optimum conditions
  • process capability

Types of effects measured:

  • 1st Order- Linear
  • 2nd Order – Quadratic
  • 3rd Order – Cubic
  • 4th Order – Quartic
  • Interactions

 

Higher Order Test Designs

DOES has developed tests designs which are of a higher order than those found in available software and literature.

Specifically, we ‘have developed 3rd and 4th order test designs whereas the available literature and software have only 1st and 2nd order test designs. Higher order test designs allow the experimenter to develop higher order models that reduce the lack-of-fit. Thus using higher order models generally improves the ability to predict.

NASA is currently using DOES higher order test designs and models to test the orbital shuttle.

In many cases the use of higher order test designs does not materially increase the sample size.

DOES has also developed proprietary statistical software to analyze test data gathered from experiment test designs. We provide a service of analyzing client's test data.

Back to top

DOES Inc. Clients Experience Staff References DOE Knowledge Services Contact

DOES, Inc. · 2531 Woodbine Road. · Winston-Salem, NC 27104 · Phone:(336) 624-2294
Fax
(336)-721-2441 email: Bill@Doesinc.com