Search

The manuscript introduces a framework for presenting the results of the statistical analysis of experiments with multiple responses and multiple factors. We propose a utilisation of factors scaling to enable a transformation that combines main effects, quadratic effects and interactions into a meaningful summary that allows the scientist/experimenter to immediately recognise the most influential factors for a given response. The framework does not replace the thorough evaluation of the results but provides a clear high‐level summary of the relative importance of findings. The visualisation of such factor importance, using intensity heatmaps, allows the immediate understanding of the results across multiple responses that efficiently guides a following detailed analysis of certain responses and factors and contributes in designing subsequent experiments. The methodology is applied to a real industrial experiment and to a simulated data set with a larger number of responses and factors. [ABSTRACT FROM AUTHOR]

Biochemical mechanism studies often assume statistical models derived from Michaelis–Menten kinetics, which are used to approximate initial reaction rate data given the concentration level of a single substrate. In experiments dealing with industrial applications, however, there are typically a wide range of kinetic profiles where more than one factor is controlled. We focus on optimal design of such experiments requiring the use of multifactor hybrid nonlinear models, which presents a considerable computational challenge. We examine three different candidate models and search for tailor-made D- or weighted-A-optimal designs that can ensure the efficiency of nonlinear least squares estimation. We also study a compound design criterion for discriminating between two candidate models, which we recommend for design of advanced kinetic studies. Supplementary materials accompanying this paper appear on-line [ABSTRACT FROM AUTHOR]

Many optimal experimental designs depend on one or more unknown model parameters. In such cases, it is common to use Bayesian optimal design procedures to seek designs that perform well over an entire prior distribution of the unknown model parameter(s). Generally, Bayesian optimal design procedures are viewed as computationally intensive. This is because they require numerical integration techniques to approximate the Bayesian optimality criterion at hand. The most common numerical integration technique involves pseudo Monte Carlo draws from the prior distribution(s). For a good approximation of the Bayesian optimality criterion, a large number of pseudo Monte Carlo draws is required. This results in long computation times. As an alternative to the pseudo Monte Carlo approach, we propose using computationally efficient Gaussian quadrature techniques. Since, for normal prior distributions, suitable quadrature techniques have already been used in the context of optimal experimental design, we focus on quadrature techniques for nonnormal prior distributions. Such prior distributions are appropriate for variance components, correlation coefficients, and any other parameters that are strictly positive or have upper and lower bounds. In this article, we demonstrate the added value of the quadrature techniques we advocate by means of the Bayesian D-optimality criterion in the context of split-plot experiments, but we want to stress that the techniques can be applied to other optimality criteria and other types of experimental designs as well. Supplementary materials for this article are available online. [ABSTRACT FROM AUTHOR]

In many industrial experiments, complete randomization of the runs is impossible as, often, they involve factors whose levels are hard or costly to change. In such cases, the split-plot design is a cost-efficient alternative that reduces the number of independent settings of the hard-to-change factors. In general, the use of generalized least squares is required for model estimation based on data from split-plot designs. However, the ordinary least squares estimator is equivalent to the generalized least squares estimator for some split-plot designs, including some second-order split-plot response surface designs. These designs are calledequivalent-estimation designs. An important consequence of the equivalence is that basic experimental design software can be used for model estimation. This article introduces two new families of equivalent-estimation split-plot designs, one based on subset designs and another based on supplementary difference set designs. The resulting designs complement existing catalogs of equivalent-estimation designs and allow for a more flexible choice of the number of hard-to-change factors, the number of easy-to-change factors, the number and size of whole plots, and the total sample size. It is shown that many of the newly proposed designs possess good predictive properties when compared to D-optimal split-plot designs. [ABSTRACT FROM AUTHOR]