![]() |
Dakota Reference Manual
Version 6.15
Explore and Predict with Confidence
|
Shape (alpha) of the inverse gamma hyper-parameter prior
Alias: none
Argument(s): REALLIST
Child Keywords:
Required/Optional | Description of Group | Dakota Keyword | Dakota Keyword Description | |
---|---|---|---|---|
Required | hyperprior_betas | Scale (beta) of the inverse gamma hyper-parameter prior |
Shape of the prior distribution for calibrated error multipliers. Either a single value or number of hyper-parameters values may be specified.
Default: 102.0 (with beta = 103.0) so mean and mode are approximately 1.0 and standard deviation is about 0.1.