Screening Strategies in the Presence of Interactions

“…Here the definition of supersaturated has been widened to include designs that have fewer runs than the total number of factorial effects to be investigated. In particular, Bayesian Doptimal designs have been shown to be effective in identifying active interactions [34]. Note that under this expanded definition of supersaturated designs, all fractional factorial designs are supersaturated under model (1) when p < n.…”

Section: Supersaturated Designs For Main Effects Screeningmentioning

confidence: 99%

Design of Experiments for Screening

Woods

Lewis

2015

Handbook of Uncertainty Quantification

Self Cite

View full text Add to dashboard Cite

The aim of this paper is to review methods of designing screening experiments, ranging from designs originally developed for physical experiments to those especially tailored to experiments on numerical models. The strengths and weaknesses of the various designs for screening variables in numerical models are discussed. First, classes of factorial designs for experiments to estimate main effects and interactions through a linear statistical model are described, specifically regular and nonregular fractional factorial designs, supersaturated designs and systematic fractional replicate designs. Generic issues of aliasing, bias and cancellation of factorial effects are discussed. Second, group screening experiments are considered including factorial group screening and sequential bifurcation. Third, random sampling plans are discussed including Latin hypercube sampling and sampling plans to estimate elementary effects. Fourth, a variety of modelling methods commonly employed with screening designs are briefly described. Finally, a novel study demonstrates six screening methods on two frequently-used exemplars, and their performances are compared. arXiv:1510.05248v1 [stat.ME]

show abstract

“…Main‐effect (ME) focused budget allocation strategy: She may be most interested in the main effect of each individual factor (ie, the μ ( j ) ‘s), while being less concerned about the interaction effects of the factors; Interaction‐effect (IE) focused budget allocation strategy: She may be more interested in the interaction (or nonlinear) effect of each individual factor (ie, the

σ_{d^{(j)}}^{2}

‘s), while being less concerned about the main effects of the factors. Despite that the main effects of various input variables on a system response are typically of primary focus in practice, interaction effects have been recognized to play significant roles both in theory and practice (Draguljić, Woods, Dean, Lewis, & Vine, ; Vine, Lewis, Dean, & Brunson, ). Ignoring interaction effects may lead to an invalid statistical inference, such as some factors may be wrongly identified as important due to spurious significant main effects whereas truly important ones may be considered unimportant. Main‐and‐interaction‐effect focused budget allocation strategy: She may be equally interested in both effects of each individual factor. …”

Section: Efficient Simulation Budget Allocation Strategies For MMmentioning

confidence: 99%

Efficient budget allocation strategies for elementary effects method in stochastic simulation

Shi¹,

Chen

2018

Naval Research Logistics

View full text Add to dashboard Cite

This paper focuses on extending the Morris' elementary effects method (MM) for sensitivity analysis/factor screening originated in the context of deterministic computer experiments to the stochastic simulation setting. Given a fixed simulation budget to expend, the main objective is to provide efficient and accurate estimates of main and interaction (or nonlinear) effects coined by the standard MM for characterizing the importance of each factor, despite the impact of simulation errors. Taking into account both the factor/input sampling uncertainty rooted in MM and the random errors inherent in a stochastic simulation, we develop efficient budget allocation strategies for implementing MM in this new context. Under each strategy proposed, we derive its corresponding optimal budget partition and optimal budget allocation rules. Numerical results corroborate the practical effectiveness of the proposed budget allocation strategies.

show abstract

Screening Strategies in the Presence of Interactions

Cited by 32 publications

References 82 publications

A Note on Foldover of 2^{k − p} Designs With Column Permutations

A Note on Foldover of 2^{k − p} Designs With Column Permutations

Design of Experiments for Screening

Efficient budget allocation strategies for elementary effects method in stochastic simulation

Contact Info

Product

Resources

About

Screening Strategies in the Presence of Interactions

Cited by 32 publications

References 82 publications

A Note on Foldover of 2k − p Designs With Column Permutations

A Note on Foldover of 2k − p Designs With Column Permutations

Design of Experiments for Screening

Efficient budget allocation strategies for elementary effects method in stochastic simulation

Contact Info

Product

Resources

About

A Note on Foldover of 2^{k − p} Designs With Column Permutations

A Note on Foldover of 2^{k − p} Designs With Column Permutations