Experimental Design

Design of experiments (DoE) is one of the most useful statistical tools in product design and testing. DoE provides an efficient and cost-effective method for understanding and optimising products and processes. DoE has been successfully adopted by many industries, including chemical, automotive, and production of medical devices. Designed experiments can be as useful in management and the service sector as they are in manufacturing industries. Different designs are used for different purposes.

We have particular expertise in:

  • factorial and fractional factorial design. This article gives a new and improved method of determining variable importance for Random Forest models based on using fractional factorial experiments.
  • response surface methodology (RSM). See Ewa's Ph.D thesis.
  • design of computer experiments
  • design of experiments for web optimisation

Some of our publications

  • Chambers, J.D., Bethwaite, B., Diamond, N.T., Peachey, T.C., Ambramson, D., Petrou, S. and Thomas, E.A. 2012 Parametric computation predicts a multiplicative interaction between synaptic strength parameters controls properties of gamma oscillations, Frontiers in Computational Neuroscience, Volume 6, Article 53 doi:103389/fncom.2012.00053
  • Diamond, N.T. 1995. Some properties of a foldover design, Austral. J. Statist, 37, 345-352.
  • Peachey, T. C., Diamond, N. T., Abramson, D. A., Sudholt, W., Michailova, A. and Amirriazi, S. 2008. Fractional factorial design for parameter sweep experiments using Nimrod/E, Sci. Program. 16(2-3), 217-230.
  • Sahama, T. and Diamond, N.T. 2001. Sample size considerations and augmentation of computer experiments, The Journal of Statistical Computation and Simulation, 68, 307-319.
  • Sztendur, E.M. and Diamond, N.T. 2002. Extension to confidence region calculations for the path of steepest ascent, Journal of Quality Technology, 34, 288-295.
  • Van Matre, J. and Diamond, N.T. 1996. Team work and design of experiments, Quality Engineering, 9, 343-348.

Some recommended resources

  • Fang, K-T., Runze, L. and Sudjianto, A. 2006. Design and Modeling for Computer Experiments, Chapman and Hall/CRC, Boca raton, FL.
  • McFarland, C. 2013. Experiment! Website conversion rate optimization with A/B and multivariate testing, New Riders, CA.
  • Santner, T.J., Williams, B.J. and Notz, W.I. 2003. The Design and Analysis of Computer Experiments, Springer, New York.