Value-at-Risk for Government Securities


NSE-VaR system
  

Standard approaches to VaR estimation   

Extreme Value theory and Value-at-Risk 

Issues in Fixed Income VaR 

VaR over multi-day horizon

INTRODUCTION

Value at Risk for Government Securities

1. NSE-VaR system 

Value-at-Risk (VaR) has been widely promoted by regulatory authorities as a way of monitoring and managing market risk and as a basis for setting regulatory minimum capital standards. The revised Basle Accord, implemented in January 1998, makes it mandatory for banks to use VaR as a basis for determining the amount of regulatory capital adequate for covering market risk beyond that required for credit risk. Within the realm of the fixed income portfolios of financial sector players, market related risk has become more relevant and important on account of their trading activities and market positions. For players in the Indian financial sector, the need to develop risk measurement models would prove critical as regulation progressively moves from uniform prudential standards to entity-specific risk coverage requirements. Specifically, the guidelines call for linking of each entity’s market risk capital charge to the riskiness of its assets as measured by the chosen VaR model. Accuracy of measurement would prove critical as regulation would not specify ‘a’ single model for measurement of risk; - the choice of model would be left to market participants who would also be required to furnish details of back-testing for the chosen VaR model. While a conservative estimate of risk would lead to very large capital holdings, a liberal estimate would result in inadequate coverage of loss and excessive number of model failures historically, which would in turn attract penalties from the regulator. It would therefore be in the interest of market participants to develop models that accurately measure the riskiness of their portfolios and furnish estimates of capital charge that would provide adequate cover. An important consideration in this context is that setting up of risk measurement systems by each individual participant for estimating portfolio risk under alternative models and scenarios would involve significant costs.

In line with its endeavour to develop market infrastructure, NSE has taken initiative in developing a VaR system for measuring the market risk inherent in Government of India (GoI) securities. The NSE-VaR system builds on the NSE database of daily yield curves - the NSE-ZCYC is now well accepted in terms of its conceptual soundness and empirical performance, and is increasingly being used by market participants as a basis for valuation of fixed income instruments. The NSE-VaR system provides measures of VaR using 5 alternative methods - variance-covariance (normal) and historical simulation methods, together with weighted normal, weighted historical simulation and the recently developed extreme value method [a technical paper explaining these methods is available here]. While the first set of methods are easier to implement and therefore more popular, they may not provide accurate assessment of risk in volatile market conditions. To this end, we provide estimates based on the latter set of methods that are specifically suited for this purpose. Together, the 5 methods would provide a range of options for market participants to choose from. 
[Top]

2. Standard approaches to VaR estimation 

VaR is the measure of the maximum (worst case) trading loss for a given portfolio over a certain holding period and for a given confidence interval. The VaR number is thus essentially determined by two parameters, - (holding) time period and a confidence level, and is a measure of the loss (expressed in say Rupees crore) on the portfolio that will not be exceeded by the end of the time period with the specified confidence level. 

The most difficult part in VaR estimations is the derivation of the portfolio returns distribution. Two popular approaches in the literature for the calculation of VaR are variance-covariance analysis and historical simulation. Variance-covariance analysis relies on the assumption that financial returns are normally distributed. This method is easy to implement because the VaR can be computed from a simple linear formula with variances and co-variances of the returns as the only inputs. Its major drawback is the assumption that financial market returns are normally distributed, an assumption that has been shown to be invalid in thousands of empirical studies on asset returns. Financial returns are typically characterized by fat-tails and volatility clustering. Fat-tail property of asset returns implies that losses are much more frequent than predicted by the variance-covariance analysis. The variance-covariance analysis is particularly weak where the demands from a VaR model for regulatory purposes and risk control are strong, i.e. in the prediction of extreme quantiles or large losses. 

Another variant of variance-covariance analysis is the Exponential weighting approach. This approach applies exponentially declining weights to past returns to calculate conditional volatilities. This technique is justified by the presence of conditional heteroskedasticity or volatility clustering in the data, meaning that a volatile day is typically followed by volatile days. The exponential approach also has the drawback that a conditional normality assumption needs to be made to calculate the VaR of a portfolio from its conditional volatility, an assumption that, more often than not, is not satisfied by financial data. Although the exponential smoothing approach addresses the issue of non-normality in the (unconditional) distribution of returns, it may not be applicable for regulatory VaR purposes on three grounds. First, while daily returns reflect strong volatility clustering, they can hardly be detected in bi-weekly returns such as the regulatory 10-day holding period. Second, the volatility clustering observed in the data largely emanates from medium and small range volatility periods. Extreme events, such as losses at or beyond 99% confidence interval scatter rather independently over time. Finally, as has been established by the theoretical and empirical literature, interest rate and bond return processes typically display a complicated dependence structure in both mean and variance, thereby making simple exponential weighting schemes - so often used in computing the equity VaR - inapplicable. 

The historical simulation (HS) method, by using empirical percentiles from the historical return distribution, gets around the problem of making distributional assumptions. By applying the full empirical market return distribution to all the items in the current trading portfolio, the outcome exactly reflects the historical frequency of the large losses over specific data window. A second advantage of this approach compared to variance-covariance analysis is that it can incorporate non-linear positions, such as derivative positions, in a natural way, a property that is also useful in the context of fixed income portfolios. The problem with the HS method is that it is very sensitive to the particular data window, which the Basle committee has chosen to be at least one year of past returns. In other words, whether returns from a highly volatile or a crash period is included or not makes a huge difference for the value-at-risk predicted. Hence VaR predictions based on HS exhibit high variability. 

A hybrid approach proposed by Boudokh, Richardson and Whitelaw (Risk, 1998) draws on the strengths of the exponential and the HS approaches to estimate the percentiles of returns directly using declining weights on past observations. Ordering returns over the historical simulation period, the hybrid approach attributes exponentially diminishing weights to each observation in building the conditional empirical distribution. Although this method combines the strengths of above mentioned methods, it still suffers from the tail-discreteness problem that we discussed earlier and it may not be very effective particularly in predicting the extremely large losses. 
[Top]

3. Extreme Value theory and Value-at-Risk 

As pointed out above, financial risk management, either for regulatory purposes or for internal control, is intimately concerned with tail quantiles. Traditional parametric models, such as variance-covariance method and exponential weighting method, implicitly strive to produce a good fit in regions where most of the data fall, potentially at the expense of a good fit in the tails, where, by definition, few observations fall. It is common, moreover, to require estimates of quantiles and probabilities not only near the boundary of the range of observed data, but also beyond the boundary. That is, one would like to allow for the possibility that the expected loss on any future date to be greater than that observed in the past. 

A key idea in Extreme Value theory is that one can estimate extreme quantiles and probabilities by fitting a “model” to the empirical survival function (or one minus the cumulative distribution function (CDF)) of a set of data using only the extreme event data rather than all the data, thereby fitting the tail and only the tail. EVT uses statistical techniques that focus only on that part of a sample of returns data that carry information about extreme behavior. Typically, the sample is divided into N blocks of non-overlapping returns with say ‘n’ returns in each block. From each block the largest rise and biggest fall in returns are extracted to create a series of maxima and minima respectively. An extreme value model (more specifically a Generalised Extreme Value (GEV) or Generalised Pareto (GP) distributions) is fitted to either of these series, via Maximum likelihood or method of moments, to estimate the ‘tail index’ parameter that characterizes the way the extreme events in the data can occur. Once an estimate of the ‘tail index’ is available, one can compute the probability of occurrence of a large event from the CDF, or VaR value for a given probability . 
[Top]

4. Issues in Fixed Income VaR 

The computation of VaR for a fixed income portfolio differs in important ways from that of an equity portfolio. First, unlike in the case of an equity portfolio where observed prices can be directly used for the computation of VaR, the price of each fixed income instrument in a portfolio is an outcome of many security-specific attributes, in addition to the fundamental factor, the underlying term structure. This rules out the use of prices directly for the computation of VaR if the objective is to measure the interest rate risk that the portfolio is subject to . Use of a zero coupon yield curve (ZCYC) is central to the exercise, as yield-to-maturity (YTM) based approaches are also subject to the same problem as with use of observed prices. Movements of the ZCYC, inasmuch as they depict the changes in the interest rate structure, are reflective of changes in the value of the portfolio occurring on account of interest rate changes alone. 

Estimation of VaR for a portfolio of fixed income securities is complicated by two reasons: one, the changes in market values of the securities are non-linearly related to changes in spot interest rates leading to difficulties in making simple assumptions about the distribution of the portfolio returns. A related point is that since one needs to know the entire term structure of interest rates to value a fixed income security (up to the relevant maturity), to study the VaR of the security we need to model the distribution of a great number of interest rates. The popular practice of cash-flow mapping considers a selected set of interest rates and maps the cash flow timings to that of the tenor of the selected interest rates through linear interpolations. Underling in this strategy is interest rates are distributed as normal or conditional normal, an assumption not typically supported by the data. In addition, the cash-flow interpolations may also lead to significant approximation errors. A better strategy would be to generate ‘returns’ on (a portfolio of) fixed income instruments at the first stage by valuing the said portfolio on observed yield curves, and estimate the VaR directly from the returns on the bond portfolio. A major advantage of this approach is that it does not require an assumption about the interest rates. Since the VaR is estimated based on bond portfolio returns, this approach has the disadvantage of being portfolio specific thereby necessitating the model parametrization, and estimation to be done for each portfolio separately. The NSE-VaR system follows the latter approach of generating returns via historical simulation and fitting a model of VaR to the return series. 
[Top]

5. VaR over multi-day horizon 

A first important observation is that VaR applies to the extreme lower tail of the return distribution, i.e. large losses far way from the mean. Bank regulators have recognized this and typically chosen a (the confidence level) equal to 99%. This number obviously reflects regulators’ natural tendency for conservativeness in their prudential supervision of banks. The same tendency also comes out in Basle regulators’ choice of holding period, the second important model parameter. A 10-day horizon is prescribed on the assumption that positions cannot be liquidated quicker than within 10 business days. To compute the 10-day VaR, the application of a simple square-root-of-time rule is permitted, ie. 10-day VaR is derived as the product of Ö10 and the 1-day VaR. For the purpose of setting adequate capital, the Basle accord provides, in addition, a multiplicative factor of 3 by which the computed VaR for the 10-day period should be multiplied. It is important to mention here that the square-root-of-time rule is the appropriate scaling factor for deriving multi-day VaR figures from 1-day figures only under the assumption of normality. Once we take into consideration the fat-tail property of underlying risk factors, the scale factor would be a-root-of-time, where a is the tail index . A point of interest in this context is that while simple models, such as Normal, under-estimate the 1-day VaR when the return series have ‘fat’ tails, they over estimate the multi-day VaR because the square-root rule turns out to be too conservative for fat tailed series. For more detailed discussion on this and an empirical illustration see the technical document available.
[Top]

Resource Persons:
Dr.Gangadhar Darbha
Dr.(Ms.)Vardhana Pawaskar
Consultants,
National Stock Exchange, 
Bandra-Kurla Complex, 
Bandra (E), Mumbai. 
Phone: 659-8291, 
Fax: 659-8288 
E-mail: gdarbha@nse.co.in
            vpawaskar@nse.co.in

Back To Top