AIMs: Explain the model-building approach to calculating VaR. Describe the Hull and White (HW) and the BRW approaches and their advantages and disadvantages.
Questions:
402.1. Each of the following is true about the reading's so-called "model building approach" identified by Hull and White EXCEPT which is false?
a. Hull's linear (non-quadratic) model-building approach is the classic parametric approach (aka, analytical approach); in contrast with this reading's three studied approaches (i.e., HS, BRW, and HW) which are each essentially non-parametric approaches
b. The parametric linear normal value at risk (VaR) model-building approach can assume a portfolio value with a normal probability distribution if the daily change in the portfolio value is linearly dependent on daily changes in market variables that are normally distributed
c. A disadvantage of the parametric linear normal VaR approach is that market variables are assumed to be conditionally multivariate normal, such that this approach takes no account of skewness or kurtosis in the distributions of market variables and no account of nonlinear correlations between market variables
d. A disadvantage of the parametric linear normal VaR approach is that the underlying variance-covariance matrix cannot be updated using an exponentially weighted moving average (EWMA) or GARCH model
402.2. Each of the following is true about the reading's so-called Boudoukh, Richardson and Whitelaw (BRW) approach except which is false?
a. BRW is an essentially non-parametric approach, also know as age-weighted historical simulation (Dowd), which is a hybrid between simple historical simulation (HS) and exponentially weighted moving average (EWMA)
b. An attractive feature of the BRW approach is that it greatly reduces the measurement challenge created by "bunching;" i.e., the reality that tail events tend to occur in close succession rather randomly throughout the observation window
c. BRW attempts to incorporate stochastic volatility into the VaR approach, but by effectively shortening the sampling period to indeed capture the behavior of stochastic volatility (an advantage), it unfortunately captures the stochastic behavior of all other sample moments of the distribution (a disadvantage)
d. BRW solves the problem of a ghosting effect in the resultant value at risk (VaR) measure
402.3. Assume the worst return over the previous 100 days (K = 100), which is the data window, happened to occur just yesterday (the most recent daily period) and it was -6.40%. Under the BRW approach (aka, hybrid approach) the lambda parameter is set to 0.980. Which is the 99.0% BRW value at risk (VaR)?
a. 3.20%
b. 6.40%
c. 12.80%
d. Need more information
Answers:
https://forum.bionicturtle.com/thre...odel-building-and-brw-approaches-to-var.7503/
Questions:
402.1. Each of the following is true about the reading's so-called "model building approach" identified by Hull and White EXCEPT which is false?
a. Hull's linear (non-quadratic) model-building approach is the classic parametric approach (aka, analytical approach); in contrast with this reading's three studied approaches (i.e., HS, BRW, and HW) which are each essentially non-parametric approaches
b. The parametric linear normal value at risk (VaR) model-building approach can assume a portfolio value with a normal probability distribution if the daily change in the portfolio value is linearly dependent on daily changes in market variables that are normally distributed
c. A disadvantage of the parametric linear normal VaR approach is that market variables are assumed to be conditionally multivariate normal, such that this approach takes no account of skewness or kurtosis in the distributions of market variables and no account of nonlinear correlations between market variables
d. A disadvantage of the parametric linear normal VaR approach is that the underlying variance-covariance matrix cannot be updated using an exponentially weighted moving average (EWMA) or GARCH model
402.2. Each of the following is true about the reading's so-called Boudoukh, Richardson and Whitelaw (BRW) approach except which is false?
a. BRW is an essentially non-parametric approach, also know as age-weighted historical simulation (Dowd), which is a hybrid between simple historical simulation (HS) and exponentially weighted moving average (EWMA)
b. An attractive feature of the BRW approach is that it greatly reduces the measurement challenge created by "bunching;" i.e., the reality that tail events tend to occur in close succession rather randomly throughout the observation window
c. BRW attempts to incorporate stochastic volatility into the VaR approach, but by effectively shortening the sampling period to indeed capture the behavior of stochastic volatility (an advantage), it unfortunately captures the stochastic behavior of all other sample moments of the distribution (a disadvantage)
d. BRW solves the problem of a ghosting effect in the resultant value at risk (VaR) measure
402.3. Assume the worst return over the previous 100 days (K = 100), which is the data window, happened to occur just yesterday (the most recent daily period) and it was -6.40%. Under the BRW approach (aka, hybrid approach) the lambda parameter is set to 0.980. Which is the 99.0% BRW value at risk (VaR)?
a. 3.20%
b. 6.40%
c. 12.80%
d. Need more information
Answers:
https://forum.bionicturtle.com/thre...odel-building-and-brw-approaches-to-var.7503/
Last edited:
