Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement EEE and/or MVA sensitivity analysis #172

Open
richardarsenault opened this issue Sep 21, 2019 · 1 comment
Open

Implement EEE and/or MVA sensitivity analysis #172

richardarsenault opened this issue Sep 21, 2019 · 1 comment
Assignees
Labels

Comments

@richardarsenault
Copy link
Contributor

Two new sensitivity analysis methods have been developed and we would want to add them to the platform. EEE and MVA are developed already and should be implemented in the platform and tested.

@julemai
Copy link
Collaborator

julemai commented Sep 23, 2019

  • EEE is a sensitivity method to identify informative parameters with a minimal number of model runs (might be helpful pre-calibration)
  • MVA is a method to estimate the uncertainty of sensitivity estimates (so far Sobol' and PAWN implemented) without the necessity of additional model runs or bootstrapping

We might want to implement the Morris method (easy since EEE is based on that), Sobol' and PAWN (both easy since part of the MVA package) method as well as such that users have a selection of methods they could perform. All these methods (except EEE and MVA) are computationally really expensive.

The plan is to implement them in OSTRICH such that we don't have to maintain the interfacing with raven but can build everything based on the current OSTRICH interface.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants