Virtual Library of Simulation Experiments:

Screening Test Problems

---

Morris et al. (2006) Function

Description:

Dimensions: 30

This is a function with 30 input variables, of which only the first k₁ variables have an effect, for 1 ≤ k₁ ≤ 10.

Morris et al. (2006) did analyses for k₁ = 2, 3, …, 10. Here, α and β are chosen so as to result in θ_i = 1 and Θ_i = 1.1, for 1 ≤ i ≤ k₁, where θ_i is a measure of the output variation attributable only to x_i, and Θ_i is a measure of the output variation attributable to x_i and any interactions involving x_i.

Input Domain:

This function is evaluated on the hypercube x_i ∈ [0, 1], for all i = 1, …, 30.

Code:

Reference:

Morris, M. D., Moore, L. M., & McKay, M. D. (2006). Sampling plans based on balanced incomplete block designs for evaluating the importance of computer model inputs. Journal of statistical planning and inference, 136(9), 3203-3220.

---

For questions or comments, please email Derek Bingham at: dbingham@stat.sfu.ca.