Borderline: judging the adequacy of return distribution estimation techniques in initial margin models

The advent of mandatory central clearing for certain types of over-the-counter derivatives and margin requirements for others means that margin is the most important mitigation mechanism for many counterparty credit risks. Initial margin requirements are typically calculated using risk-based margin models, and these models must be tested to ensure that they are prudent. However, two different margin models can calculate substantially different levels of margin yet both pass the usual tests. This paper presents a new approach to parameter selection based on the statistical properties of the worst loss over a margin period of risk estimated by the margin model under test. This measure is related to risk estimated at a fixed confidence interval yet leads to a more powerful test which is better able to justify the choice of parameters used in margin models. The test proposed is used on a variety of volatility estimation techniques applied to a long history of returns of the S&P 500 index. Well known techniques, including exponentially weighted moving average volatility estimation and generalised autoregressive conditional heteroskedasticity approaches are considered, and novel approaches derived from signal processing are also analysed. In each case a range of model parameters which give rise to acceptable risk estimates is identified.