Ultimate access to all questions.
In the context provided, where a bank’s derivative trading desk currently employs a Value at Risk (VaR) model that utilizes historical simulation with a 3-year look-back period and applies equal weighting to past returns, a new VaR model has been developed. This new model employs the delta-normal method, where volatilities and correlations are estimated using the RiskMetrics Exponentially Weighted Moving Average (EWMA) method over the past 4 years. During a 6-week parallel run, the new model reported no exceedances and consistently estimated lower VaR values compared to the old model. Following this, the model evaluation team, after a brief assessment led by a junior analyst, quickly decided to adopt the new model. Given this scenario, what is the correct conclusion to draw regarding the model replacement?
A
Delta-normal VaR is more appropriate than historical simulation VaR for assets with non-linear payoffs.
B
Changing the look-back period and weighting scheme from 3 years, equally weighted, to 4 years, exponentially weighted, will understate the risk in the portfolio.
C
Overnight examination by the junior analyst increased the desk's exposure to model risk due to the potential for incorrect calibration and programming errors.
D
A 99% VaR model that generates no exceedances in 6 weeks is necessarily conservative.