Basic information for latin hypercube samples

Share:

Description

Basic information for latin hypercube samples

Brief statistical background

Latin hypercube designs try to fill the multidimensional space spanned by several quantitative response variables. Space filling is attempted by different methods (the simplest and least effective of which is a random sample. For more information, look at the help file for function lhs.design from package DoE.wrapper.

Inputs on Tab Base Settings

radio buttons

allow to choose among different design types. The default choice (optimum) is reasonable, if it is feasible. random should only be used for a quick random look, of course no space-filling optimality can be expected by a random selection. For the other variants and the optimality criterion, see the help of the underlying function.

name of design

must be a valid name. The design itself is created under this name in the R workspace.

number of runs

must be provided and can be any positive integer.

number of factors

must always be specified. Although not very reasonable, it is possible to choose the number of factors larger than the number of runs.
The number of factors must match the number of entries on the Factor Details tab.

number of decimal places

can be provided for rounding (as in function round).

seed

can be provided for reproducing an existing design.

Author(s)

Ulrike Groemping

See Also

See Also lhs.design for the function that does the calculations and lhs-package for the package used in that function.

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.