Dakota Reference Manual
Version 6.12
Explore and Predict with Confidence

How to scale each objective function
Alias: objective_function_scale_types
Argument(s): STRINGLIST
Default: no scaling
Each string in primary_scale_types
indicates the scaling type for each objective function. They only have effect when the associated method specifies scaling
.
The options are:
'value'
 characteristic value by which response functions will be divided. If this is chosen, then primary_scales must also be specified; 'value' is assumed if scales are given without scale_types
'log'
 logarithmic scaling (can be used together with primary_scales, which can be helpfully used to negate values prior to log transformation)(Automatic scaling is disallowed due to lack of bounds or targets for primary responses.)
If a single string is specified it will apply to all objective_functions. Otherwise the length of primary_scale_types
must have length equal to objective_functions. Thus, when scalar and/or field responses are specified, the number of primary_scale_types
must equal the number of scalars plus the number of fields, not the total elements in the fields.
Usage Tips:
When scaling is active, it is applied to objective functions prior to any weights and multiobjective sum formation.
See the scaling information under specific methods, e.g., method*scaling
for details on how to use this keyword.