I would suggest incorporating implied vols into risk models.....

>What about historical testing/backtesting? Well just cause the model was successful in predicting the past does not mean it will perform as well predicting the future. Certain events may not have occured which would have caused the model to fall apart. Models backtested before the asian crisis all did well up to that event. You would still have model risk with backtesting>I would suggest incorporating implied vols into risk models..... Assuming that the market for the instrument was deep, liquid and reasonably priced that implied vols would be great - but not all instruments are readily traded. In which case your implied vol may be too high or low.

Agreed KL, but ultimately its how your model stands up to reality, (not how it stand up to other models) which counts.There is huge scope for pulling info from options markets into buy side risk management modeling.

QuoteWell just cause the model was successful in predicting the past does not mean it will perform as well predicting the future. Certain events may not have occured which would have caused the model to fall apart. Models backtested before the asian crisis all did well up to that event. You would still have model risk with backtestingwell i suppose the interests of stress-testing (in complement to to the backtesting) are in fact to test the sensitiveness of the model ?