Design of Experiments (DOE)
Full factorial design, ANOVA, ANCOVA
Regression
Mixture design
The gold standard of Analytics, where factor affects are well understood, but not quantified to the specific range and performance requirements of your production process. This treatment is essential to the development of high quality internal standards for production and quality and supports negotiations with suppliers, regulating bodies and customers to generate meaningful and mutually beneficial quality and performance
Taguchi multifactorial screening experiments
Applied to complex development problems where a large number of factors may have unknown impacts of properties. Where experimentation is expensive and time consuming, Screening experiments rapidly filter out trivial factor affects and bring narrow focus to optimization, without missing anything.
Linear, non-linear and planar regression, including Arrhenius regression are most suitable to refining performance criteria and optimization of multiple functions. Applications range from demonstration of service life and performance to calibration and reliability for multiple properties at once.
Where concentrations of one component in a formulation are constrained by the concentration of others, ,mixture design techniques permit a broad and thorough examination of formulation effects, both in reactive processes and interactive performance impacts. Iterative development of formulation models assures that all experimentation is directly relevant to final outcomes and assures truely optimized formulations