Stress Test Model Update – CCAR Stress Tests: Modeling What Cannot Be Modeled – Nom de Plumber’s Thought of the Day

ndp  Nom de Plumber is a Nom de Plume.

The Fed knows best? This is a follow up to a previous post:

Federal Reserve Stress-Testing Model Error–Nom de Plumber’s Thought of the Day


There seems a fundamental conundrum about regulatory expectations for
the management validation of CCAR stress models, market inputs, and
loss projections.

Stress scenarios inherently mean unexpectedly anomalous model breakdowns,
market behaviors, and asset losses, far surpassing historical experience or
plausible projections.  

This implies that those ex-ante validations conferred an overwhelmingly false sense of security—thereby questioning the very robustness of stress-testing infrastructures.

How can one model what cannot be modeled, and prove so in advance?
Nonetheless, new regulatory directives still require that to be done:

Yes, we have no bananas.

Thank you. 


Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s