![]() |
Dakota Reference Manual
Version 6.16
Explore and Predict with Confidence
|
Specify how the trial samples are generated
Alias: none
Argument(s): none
Default: random
Child Keywords:
| Required/Optional | Description of Group | Dakota Keyword | Dakota Keyword Description | |
|---|---|---|---|---|
| Required (Choose One) | Trial Type (Group 1) | grid | Samples on a regular grid | |
| halton | Generate samples from a Halton sequence | |||
| random | Uses purely random Monte Carlo sampling to sample variables |
The user has the option to specify the method by which the trials are created to adjust the centroids. The trial_type can be one of three types:
random, where points are generated randomly halton, where points are generated according to the Halton sequence grid, where points are placed on a regular grid over the hyperspace.