Nested Maximin Designs

Nested designs consist of two (or more) separate designs, one being a subset of the other, and are useful when dealing with linking parameters or sequential evaluations, see Van Dam et al. (2010), Husslage et al (2005), and Rennen et al. (2010).

Linking parameters occur, for example, when black boxes have one or more input parameters in common. Using nested designs helps to determine what settings to use for these parameters such that as much information as possible is obtained about the black box functions (and their relations).

When we need to evaluate an extra set of design points, after having evaluated an initial set, we speak of sequential evaluations. Nested designs help to determine the best sequence of sets of design points to evaluate.

All nested designs provided on this webpage can be downloaded and used in your specific simulation environment.

Dam, E.R. van, B.G.M. Husslage, and D. den Hertog (2010). One-dimensional nested maximin designs, Journal of Global Optimization 46, 287-306.
Husslage, B.G.M., E.R. van Dam, and D. den Hertog (2005). Nested maximin Latin hypercube designs in two dimensions, CentER Discussion Paper 2005-79, 11pp.
Rennen, G., B.G.M. Husslage, E.R. van Dam, and D. den Hertog (2010). Nested maximin Latin hypercube designs, Structural and Multidisciplinary Optimization 41, 371-395.