Go Duke... !!

DOOK !!!

When you say !!! GO DUKE !!! today, guess most folks are thinking basketball, the Final Four, or Krysrhu.... Khachf.... Kzyreski.... or whatever the coach's name is....


But the cognoscenti of robusterian quantalytics know that Duke is as good off the court as it is on the court when it comes to statistics.  

Thought you might like to see a brief primer  on forecasting from Dr. Robert Nau from the Duke Fuqua Schoool of Business.  Any professor who leads with the following quote must be taken seriously:

"I have seen the future and it is very much like the present, only longer."

- Kehlog Aldbran

In case you haven't got time before the game, here are the key plays:

  Forecasting can take many forms - staring into crystal balls or bowls of tea leaves, combining the opinion of experts,...

  "If you live by the crystal ball, you end up eating broken glass."

*  "Intrinsic risk - This doesn't necessarily mean the original model was "wrong", but merely that it was too simplistic or under-informed."

* "Parameter risk - No pattern really stays the same forever, which is known as the "blur of history" problem."

*  "Model risk - Is the risk of choosing the wrong model, i.e., making the wrong assumptions about whether or how the future will resemble the past.  This is usually the most serious of forecast error... because every model assumes itself to be correct."

"There is no magic formula."

           ... the DEVILS* are in the details !!!

* ( Y'know the "K-factors" - judgment, execution, 
and practical, "on-court" experience!!!)

!!! GO DUKE !!!