Anda di halaman 1dari 10

Article

Value-at-Risk Estimation of Foreign Asia-Pacific Journal of Management


Research and Innovation

Exchange Rate Risk in India


12(1) 1–10
© 2016 Asia-Pacific
Institute of Management
SAGE Publications
sagepub.in/home.nav
DOI: 10.1177/2319510X16650057
Onkar Shivraj Swami1 http://apjmri.sagepub.com

Santosh Kumar Pandey1


Puneet Pancholy1

Abstract
Banks are required to maintain an appropriate level of capital which must commensurate with the riskiness of their portfolio. Recently,
the Reserve Bank of India (RBI) issued a circular on Prudential Guidelines on Capital Adequacy—Implementation of Internal Models Approach
(IMA) for Market Risk to select a suitable method for the banks to determine the regulatory capital requirement under the market
risk exposure. Banks which adopt this approach are required to quantify market risk through their own Value-at-Risk (VaR) model.
Therefore, it is a challenging task for risk managers of the bank to select an appropriate risk model which reasonably covers the risk
of the bank’s portfolio. Use of wrongly calibrated risk models may lead to undercapitalised banking system. This article aims at
exploring the suitable risk model for measuring foreign exchange risk in banks’ portfolio. The objective of present study is to empirically
test the appropriate VaR model for foreign exchange rate risk. Value-at-Risk has been estimated for foreign exchange rate risk by
using parametric variance–covariance method and non-parametric historical simulation (HS) method. Under parametric method, VaR
is estimated by assuming that returns follow normal and Student’s t-distribution. Backtesting results for various VaR models have been
done based on Kupiec’s proportion of failures (KPOF) test and regulatory ‘traffic light’ test. This article concludes that when returns
are non-normal, VaR model based on the assumption of normality significantly underestimates the risk. Our empirical results based on
backtesting show that most accurate VaR estimates are obtained from Student’s t VaR model.

Keywords
Foreign exchange rate risk, internal models approach, Value-at-Risk, historical simulation, variance–covariance, VaR backtesting

Introduction economic (operational, competitive or cash flow) and trans-


lation (accounting) (Abor, 2005). Transaction risk arises
According to the Basel Committee on Banking Supervision when the value of existing obligations is deteriorated
(BCBS), market risk is defined as ‘the risk of losses in on by movements in foreign exchange rates (Abor, 2005).
and off-balance-sheet positions arising from movements in Economic risk occurs due to impact of high unexpected
market prices’ (BIS, 2005). Market risk is the risk of losses volatility in the exchange rate on equity/income for both
to the bank arising from movements in market prices as a domestic and foreign operations. Translation risk is associ-
result of changes in interest rates, foreign exchange rates ated with the assets or income derived from offshore
and equity and commodity prices. activities (Abor, 2005).
Foreign exchange rate risk is the risk that the value of BCBS has adopted VaR as a primary measure of market
the bank’s assets or liabilities changes due to currency ex- risk for determining the bank capital adequacy (BCBS,
change rate fluctuations. By buying and selling the foreign 2006). Subsequently, VaR has become the standard measure
exchange on behalf of their customers, banks are exposed to for estimating the market risk in financial sector industries.
exchange rate risk. Generally, banks are vulnerable to three Value-at-Risk is defined as ‘the worst loss over a target
types of foreign exchange risk: transaction (commitment), horizon with a given level of confidence’ (Jorion, 2007).

Disclaimer: The views expressed in this study are of the authors and not of the institution to which they belong.

1  Banking Policy Division, Department of Banking Regulation, Central Office, Reserve Bank of India, Shahid Bhagat Singh Marg, Fort, Mumbai, Maharashtra,

India.

Corresponding author:
Onkar Shivraj Swami, Banking Policy Division, Department of Banking Regulation, Reserve Bank of India, Shahid Bhagat Singh Marg, Fort, Mumbai
400001, India.
E-mail: oswami@rbi.org.in
2 Asia-Pacific Journal of Management Research and Innovation 12(1)

The portfolio VaR estimates the maximum loss with the trading portfolios such as foreign exchange rates (Sirr,
given probability an investor may suffer over a given time Garvey & Gallagher, 2011).
period (Abad, Benito & López, 2014).
The objective of the present study is to empirically test
the foreign exchange rate risk for the management of VaR Models
market risk with the use of VaR methodology. Value-at- The non-parametric HS method and parametric method
Risk has been estimated for foreign exchange rate risk by for estimating the VaR, that is, variance–covariance
using (i) parametric method called as variance–covariance approach, are described below:
approach and (ii) non-parametric HS method.
The article is organised as follows. In the next section, Historical Simulation Method
we review HS and parametric approach to estimate the The historical VaR model assumes that all possible future
VaR. The third section provides the regulatory framework variations have been experienced in the past, and that
for market risk in India. The fourth section delineates the historically simulated distribution is identical to the
topics related to data and methodology. Empirical findings returns distribution over the forward-looking risk horizon
are given in the fifth section. The last section concludes the (Alexander, 2008a, 2008b). Thus, non-parametric HS has
findings of the study. some advantages over the parametric method, as it makes
no assumption about the shape of the distribution of returns.
Further, HS method is very easy to implement. However,
Theoretical Background, more recent studies (Abad et al., 2014; Angelidis, Benos
Concept and Definitions & Degiannakis, 2007; Ashley & Randal, 2009; Trenca,
2009) have mentioned that the HS method gives poor VaR
Definition and Concept of VaR estimates. Filtered HS and conditional extreme value
Value-at-Risk is a statistical measure that summarises provide more adequate VaR estimates than HS VaR (Abad
all the risks of a portfolio into a single number suitable et al., 2014). Nevertheless, by far HS approach is most
for use in the boardroom, for reporting to regulators or for widely implemented by the banks for estimating the daily
disclosure in an annual report. More precisely, according VaR (Pérignon & Daniel, 2010).
to Elliott and Miao (2009), ‘VaR is a statistical estimate of Parametric Method
a portfolio loss with the property that, with a small pro-
Wang, Wu, Chen and Zhou (2010) mentioned that the
bability α, the owner of the portfolio stands to incur that
variance–covariance method is a parametric method to
loss or moreover a given (typically short) holding period.’
calculate VaR. This parametric method needs the estimation
In general, a may be fixed at 1, 2.5 and 5 per cent and the
of standard deviation of the portfolio by means of sample
holding period may be taken as 1, 2 and 10 business days
estimation of variance (Rossignolo, Duygun & Mohamed,
or 1 month.
2012). The 100a per cent h-day normal linear VaR for
According to Jorion (2007), ‘VaR is the worst loss over
single exchange rate is given by
a target horizon such that there is a low, prespecified
probability that the actual loss will be larger.’ This definition VaR h, a = U -1 (1 – a) v h
consists of two parameters: the risk horizon and the
confidence level. Let a be the confidence level and L be where vh is the standard deviation of the sample returns
the loss, measured as a positive number. Value-at-Risk is and U –1 (1 – a) is the inverse of the cumulative density
also reported as a positive number (Jorion, 2007). Again function of the standard normal distribution.
as mentioned by Jorion (2007), a general definition of Similarly, 100a per cent h-day normal linear VaR for
VaR is that it is the smallest loss, in absolute value, such portfolio of foreign exchange rates is given by
that
VaR h, a = U –1 (1 – a) wl Vh w – wl E (X h)
P [L > VaR] # 1 – a
where risk factor returns are multivariate normal and
Take, for example, a 99 per cent confidence level independent and identically distributed (iid), w denotes the
(i.e., a = 0.99). Value-at-Risk then is the cut-off loss such current vector of portfolio weights, E(Xh) is the n × 1
that the probability of experiencing a greater loss is less vector of the expected/mean excess h-day returns and Vh is
than 1 per cent. Jorion (2007) also has suggested that the the h-day covariance matrix of foreign exchange rates
length of time required to hedge the market risk should be return.
in alignment with the risk horizon. It is convenient to use To estimate the VaR with high peaks and heavy tails
short risk horizons than the longer one for the frequently of exchange rate returns, it is ideal to assume that U(·)
Swami et al. 3

follows Student’s t-distribution (Wang et al., 2010). When 1. Value-at-Risk must be computed on a daily basis.
h is small, an approximate formula for the 100a per cent 2. In calculating VaR, a 99th percentile, one-tailed
h-day Student’s t VaR is given by confidence interval is to be used.
3. In calculating VaR, an instantaneous price shock
Student t VaR h, a, y = y -1 (y - 2) ht y-1 (1 – a) v – hn equivalent to a 10-movement in prices is to be
used, that is, the minimum ‘holding period’ will
where y denotes degrees of freedom for Student’s t- be 10 trading days. Banks may use VaR numbers
distribution. calculated according to shorter holding periods
Similarly, 100a per cent h-day Student’s t VaR for scaled up to 10 days in an appropriate manner. Banks
foreign exchange rates portfolio is given by should use the ‘square root of time rule’ only for
linear portfolios with identically and independently
Student t VaR h, a, = y -1 (y - 2) ht -y 1 # normally distributed returns. A bank using this
 approach, for portfolios other than linear portfolios
(1 – a) il X h i – il n h)
with identically and independently normally distri-
where Xh denotes the m × m covariance matrix of the risk buted returns, must periodically justify the reasona-
factor and nh denotes the m × 1 vector of expected/mean bleness of its approach to the satisfaction of the RBI.
excess returns over the h-day risk horizon.
For calculating VaR, it is essential to have a minimum,
past 1 year daily returns data (i.e., 250 trading days). Banks
Regulatory Framework in India are permitted to use any VaR model subject to
To allocate adequate regulatory capital under the market the condition that it is satisfies the above requirements, that
risk, Basel II framework on capital adequacy provides is, variance–covariance matrices, HSs, etc., for calculating
two methods, namely, standardised measurement method the VaR under the market risk exposure.
(SMM) and Internal Models Approach (IMA). Since 31
March 2005, banks in India have been measuring market
risk under Basel II accord by using the SMM. Compared to Regulatory Backtesting
the SMM, the IMA is considered to be more risk sensitive Rossignolo et al. (2012) mentioned that ‘backtesting
and aligns the capital charge for market risk more closely constitutes a statistical technique to assess the quality of
to the actual losses likely to be incurred by banks due to the risk measurement specifications which involves the
movements in the market risk factors. Therefore, the comparison between the daily VaR forecast with the actual
Reserve Bank of India (RBI) issued circular on Prudential losses’. Backtesting involves comparing the number of
Guidelines on Capital Adequacy—Implementation of times actual losses exceed VaR estimates in approximately
Internal Models (IMA) Approach for Market Risk on 7 250 trading days (Rossignolo et al., 2012). In accordance
April 2010 to provide a wider choice to banks in select- with Basel II requirements, the RBI under IMA guide-
ing a method for determining the regulatory capital require- line (2010) has stated that ‘backtesting will be based on
ment for their market risk exposure (RBI, 2010). As of 1 percent daily VaR estimate i.e. holding period is assumed
now, none of the banks in India are determining the regula- as one day and it will cover a period of 250 days’. For
tory capital requirement for their market risk exposure by backtesting, most recent 12 months of data (i.e., 250 daily
using IMA.
observations) are used. Apart from backtesting VaR model
based on 1 per cent VaR, banks can validate model
assumptions at 2, 5 and 10 per cent VaR. In general, to have
VaR one exception in a month (1 in 20 trading days) for
As per the RBI’s circular on Prudential Guidelines on backtesting, 95 per cent confidence level is considered to
Capital Adequacy—Implementation of Internal Models be more appropriate.
(IMA) Approach for Market Risk issued on 7 April 2010, As per RBI’s circular on IMA dated 7 April 2010,
the capital requirement is a function of three components: backtesting outcomes can be classified into three zones
‘(1) Normal VaR Measure (for general market risk and depending on the number of exceptions coming out of
specific risk) (2) Stressed VaR Measure (for general market the backtesting, often called the ‘traffic light’ approach.
risk and specific risk) and (3) Incremental Risk Charge Based on the number of exceptions, backtesting outcomes
(IRC) (for positions subject to interest rate specific-risk will fall in either green zone, yellow zone or red zone
capital charge)’. Further, according to the same circular on and the corresponding zone-wise increase in the multi-
IMA dated 7 April 2010, mandatory parameters for VaR plication factors for both VaR and stressed VaR are given
models are given below: in Table 1.
4 Asia-Pacific Journal of Management Research and Innovation 12(1)

Table 1. Zone-wise Classification Backtesting Outcomes this study calculates VaR with 99 per cent confidence
level for 1-day horizon. First, we estimate 1-day VaR for
Number of Increase in
3 January 2000, that is, 251st day by using the entire returns
Zone Exception Multiplication Factor
of the year 1999 (i.e., around 250 days observations).
Green zone 0 0.00 Second, we calculate VaR for 4 January 2000, that is,
1 0.00 252nd day using returns from 5 January 1999 to 3 January
2 0.00 2000. In a similar way, VaR is estimated up to the last data
3 0.00 point of the present study (i.e., 31 December 2013). We
have used 1-year data, that is, about 250 days data rolling
4 0.00
window, for our VaR analysis and backtesting.
Yellow zone 5 0.40 Although it is computationally convenient to assume
6 0.50 normal distribution of the returns when calculating the
7 0.65 VaR, it always does not hold true. Estimation based on
8 0.75 normal distribution produces significant errors when
dealing with skewed data. We have used Q–Q plots and
9 0.85
Jarque–Berra test for detecting the non-normality.
Red zone 10 or more 1.00 Value-at-Risk violation occurs when returns exceed the
Source: Reserve Bank of India. estimated VaR. Backtesting is a statistical procedure in
which actual returns are systematically compared to corres-
ponding VaR estimates. The backtesting of estimated VaR
Methodology is carried out for each year from 2000 to 2013 by using the
The main data contain univariate price series of three latest preceding 1-year data (i.e., about 250 days). In addi-
foreign exchange currencies, that is, Indian rupee (INR)/ tion to regulatory backtesting, we have also performed
US Dollar (USD), INR/POUND and INR/EUR. We have backtesting using KPOF test (Kupiec, 1995). Kupiec’s test
taken a hypothetical portfolio of 200 million INR. Of these, measures whether the number of exceptions is consistent
100 million INR foreign exchange business of a bank is in with the confidence level (Nieppola, 2009).
USD, 50 million INR business is in pound sterling and
euro each (i.e., INR/USD has 50 per cent weight of total
portfolio, and INR/POUND and INR/EUR each have Results
25 per cent weight in total portfolio). The data are retrieved
from RBI’s database on Indian economy for the period Descriptive Statistics
from 4 January 1999 to 31 December 2013. The descriptive statistics of daily logarithmic returns of the
The daily logarithmic return Rt is defined as three series and portfolio are given in Table 2. For all the
Pt
Rt = ln d n . For each exchange rate, we have 3,400 three series, skewnesses of daily logarithmic returns are
Pt–1 not equal to zero and kurtosises are greater than three.
daily logarithmic returns. As per regulatory requirements, Further, portfolio reruns series also has skewness greater

Table 2. Descriptive Statistics of Daily Logarithmic Return from Three Exchange Rates of INR

Parameters INR/USD INR/POUND INR/EUR Portfolio


Mean 0.00010 0.00010 0.00014 0.00011
Median 0.00000 0.00020 0.00020 0.00010
Minimum –0.03010 –0.05700 –0.03890 –0.03180
Maximum 0.04020 0.03680 0.04150 0.03970
Standard deviation 0.00432 0.00632 0.00680 0.00429
Skewness 0.26790 –0.41229 –0.02087 0.22510
Kurtosis 11.39130 7.86258 5.09643 9.50848
Jarque–Bera 10,723 3,689 667 6,455
Probability 0.00000 0.00000 0.00000 0.00000
N (sample size) 3,640 3,640 3,640 3,640
Source: Authors’ calculation.
Swami et al. 5

than zero and kurtosises greater than three (Table 2). This for three exchange rates of INR and portfolio returns. From
suggests that these exchange rate series and portfolio these histograms, it appears that all three series and portfo-
returns do not follow the normal distribution. These find- lio returns have high peak than normal distribution. In
ings are also supported by the Jarque–Bera statistics for general, Q–Q plot is used to identify the distribution of
daily logarithmic returns of the three series and portfolio. sample in the study. Figure 2 represents the Q–Q plot
Figure 1 depicts the histogram of daily logarithmic return of daily logarithmic return for three exchange rates of

Figure 1. Histogram of Daily Logarithmic Return from Three Exchange Rates of INR and Portfolio Returns
Source: Authors’ calculation.
6 Asia-Pacific Journal of Management Research and Innovation 12(1)

Figure 2. Q–Q Plot of Daily Logarithmic Return from Three Exchange Rates of INR and Portfolio Returns
Source: Authors’ calculation.

INR and portfolio returns. The Q–Q plot compares the dis- VaR
tribution for each exchange rate returns including portfolio
returns with the normal distribution and indicates that all Figure 3 shows the time series of portfolio of foreign
three exchange rates of INR and portfolio returns deviate exchange rate returns. The logarithmic returns and VaR
from the normal distribution. based on HS and normal and Student’s t-distribution are
Swami et al. 7

Figure 3. Graph of Daily Portfolio Returns and VaR Estimated by Using Various Models
Source: Authors’ calculation.

estimated on a daily basis. The time series begins on 3 and Normal_VaR. During the GFC onset and the later
January 2000 as the previous 1-year data (i.e., year 1999) period, the Student’s t VaR has performed better than
are needed to estimate the initial parameters. The chart Normal_VaR.
shows the significant increase in volatility of foreign
exchange rate portfolio returns from the second half of
Backtesting of VaR Models
2008 and as a result, VaR estimates also worsen.
Daily estimated HS_VaR has been highest between the Value-at-Risk violation occurs when actual portfolio loss
period December 2008 and November 2009. In fact, HS_ exceeds the estimated VaR. Tables 3–5 represent the
VaR estimates are higher than VaR estimates based on backtesting results for various VaR models based on KPOF
normal and Student’s t-distribution for the same period. test and regulatory ‘traffic light’ test. We have observed 59
This is the period when the Global Financial Crisis (GFC) exceptions/violations for HS_VaR model over the study
began. As the foreign exchange rate returns are non- period, that is, from 2000 to 2013. For HS_VaR model, the
normal, Normal_VaR estimates underestimate the risk maximum number of violations occurred in the year 2008
throughout the study period. Moreover, as GFC progressed followed by the year 2007 and 2013. Backtesting based
further, Normal_VaR has performed even more poorly. on KPOF test for HS_VaR model is accepted for 11 years
This confirms the belief that as return distributions do not (p ≤ 0.05) and is rejected for the years 2007, 2008 and 2013
follow normal distribution, risk estimates based on assump- (Table 3). Backtesting based on Regulatory test for HS_
tion of normality will not provide robust risk assessments. VaR model has indicated a result in the red zone for the
It is therefore prudent for banks and bank supervisors to year 2008 and yellow zone for the year 2003, 2007, 2012
look into the assumptions of return distribution while and 2013.
computing regulatory capital based on their internal risk For Normal_VaR model, we have observed 68 excep-
models. When significant positive excess kurtosis is found tions/violations over the study period. For Normal_VaR
in empirical return distribution, the Student’s t-distribution model, the maximum number of violations occurred dur-
is likely to produce VaR estimates that are more close to ing the years 2007 and 2008. Form Figure 3, it is clear
historical behaviour than normal distribution (Elliott & that throughout the study period, VaR number based on
Miao, 2009; Lin & Shen, 2006). The Student’s t-distribution Normal_VaR model is underestimated. Backtesting based
is more adequate to deal with the fat-tailed and leptokurtic on KPOF test for Normal_VaR model is accepted for 11
features. As our foreign exchange rate returns are having years (p ≤ 0.05) and is rejected for the years 2004, 2007and
leptokurtic feature, the VaR estimates based on Student’s 2008. Backtesting based on regulatory test for Normal_
t-distribution appear to be more appropriate. From Figure 3, VaR model has indicated a result in the red zone for the
in general, it seems that VaR estimates based on Student’s years 2007 and 2008 and yellow zone for the years 2000,
t-distribution lie between the estimates based on HS_VaR 2004 and 2013.
8 Asia-Pacific Journal of Management Research and Innovation 12(1)

Table 3. Backtesting of HS_VaR Model

No. of Percentage of Kupiec’s Proportion of Failures Test


Year Exceptions No. of Exceptions Likelihood Ratio Accept/Reject Regulatory Test
2000 4 1.6 0.77 Accept Green zone
2001 2 0.8 0.11 Accept Green zone
2002 1 0.4 1.18 Accept Green zone
2003 5 2 1.96 Accept Yellow zone
2004 4 1.6 0.77 Accept Green zone
2005 2 0.8 0.11 Accept Green zone
2006 2 0.8 0.11 Accept Green zone
2007 9 3.6 10.23 Reject Yellow zone
2008 10 4.0 12.96 Reject Red zone
2009 1 0.4 1.18 Accept Green zone
2010 3 1.2 0.09 Accept Green zone
2011 4 1.6 0.77 Accept Green zone
2012 5 2 1.96 Accept Yellow zone
2013 7 2.8 5.50 Reject Yellow zone
Source: Authors’ calculation.

Table 4. Backtesting of Normal VaR Model

No. of Percentage of Kupiec’s Proportion of Failures Test


Year Exceptions No. of Exceptions Likelihood Ratio Accept/Reject Regulatory Test
2000 5 2.0 1.96 Accept Yellow zone
2001 1 0.4 1.18 Accept Green zone
2002 1 0.4 1.18 Accept Green zone
2003 3 1.2 0.09 Accept Green zone
2004 8 3.2 7.73 Reject Yellow zone
2005 2 0.8 0.11 Accept Green zone
2006 2 0.8 0.11 Accept Green zone
2007 14 5.6 25.78 Reject Red zone
2008 14 5.6 25.78 Reject Red zone
2009 1 0.4 1.18 Accept Green zone
2010 3 1.2 0.09 Accept Green zone
2011 4 1.6 0.77 Accept Green zone
2012 4 1.6 0.77 Accept Green zone
2013 6 2.4 3.56 Accept Yellow zone
Source: Authors’ calculation.

We have observed 43 exceptions/violations for t_VaR indicated a result in the red zone for the year 2007 and
model over the study period. For t_VaR model, the maxi- yellow zone for the years 2004 and 2008.
mum number of violations occurred during the year 2007. In general, VaR estimates based on normal distri-
Backtesting based on KPOF test for t_VaR model is bution have underestimated the VaR numbers. Among
accepted for all years (p ≤ 0.05) except for the year 2007. the three models, Student’s t VaR model has performed
Backtesting based on regulatory test for t_VaR model has better. Intuitively, the parametric standard deviation-based
Swami et al. 9

Table 5. Backtesting of Student’s t VaR Model

No. of Percentage of Kupiec’s Proportion of Failures Test


Year Exceptions No. of Exceptions Likelihood Ratio Accept/Reject Regulatory Test
2000 1 0.4 1.1765 Accept Green zone
2001 1 0.4 1.1765 Accept Green zone
2002 1 0.4 1.1765 Accept Green zone
2003 3 1.2 0.0949 Accept Green zone
2004 6 2.4 3.5554 Accept Yellow zone
2005 2 0.8 0.1084 Accept Green zone
2006 1 0.4 1.1765 Accept Green zone
2007 12 4.8 19.0162 Reject Red zone
2008 6 2.4 3.5554 Accept Yellow zone
2009 1 0.4 1.1765 Accept Green zone
2010 2 0.8 0.1084 Accept Green zone
2011 4 1.6 0.7691 Accept Green zone
2012 1 0.4 1.1765 Accept Green zone
2013 2 0.8 0.1084 Accept Green zone
Source: Authors’ calculation.

approach should be more precise. Indeed, estimates of Interestingly, HS method has performed better than
standard deviation use information about whole distribu- Normal_VaR model. However, most accurate VaR esti-
tion, whereas quantile uses only the ranking of observa- mates are obtained from Student’s t VaR model.
tions and the two observations around the estimated value,
that is, parametric methods are inherently more precise Acknowledgements
because the sample standard deviation contains far more We are extremely grateful to Sudarshan Sen, Principal Chief
information than sample quantiles (Jorion, 2007). General Manager, Department of Banking Regulation, Reserve
Bank of India, Mumbai, for his constant guidance and support
in the preparation of this article. Further, helpful discussion and
Conclusion suggestions from Madhusmita Dutta, Manager, Foreign Exchange
Department, Reserve Bank of India, Mumbai, for improving the
In this empirical study, we have applied various models/ article are highly acknowledged.
methods for estimating VaR for the portfolio of foreign
exchange currencies. Value-at-Risk has been estimated References
for foreign exchange rate risk by using variance–covariance
Abad, Pilar, Benito, Sonia, & López, Carmen. (2014). A
approach and non-parametric HS method. For estimat- comprehensive review of Value at Risk methodologies. The
ing the VaR based on various models, we have followed Spanish Review of Financial Economics, 12(1), 15–32.
the regulatory framework by RBI on Prudential Guidelines Abor, Joshua. (2005). Managing foreign exchange risk among
on Capital Adequacy—Implementation of Internal Models Ghanaian firms. The Journal of Risk Finance, 6(4), 306–318.
Approach for Market Risk in India (RBI, 2007). Alexander, Carol. (2008a). Market risk analysis Volume IV:
Estimation of VaR would be made simply by using Value-at-Risk models. The Atrium, Southern Gate, Chichester,
mean and standard deviation of the return distribution if West Sussex, UK: John Wiley & Sons Ltd.
returns are normally distributed. But the financial market ———. (2008b). Value-at-Risk models. England, UK: John
returns usually do not follow normal distribution. The Wiley & Sons.
returns in our study are leptokurtic in nature. This observed Angelidis, Timotheos, Benos, Alexandros, & Degiannakis,
Stavros. (2007). A robust VaR model under different time
non-normality of returns should be handled suitably while
periods and weighting schemes. Review of Quantitative
estimating VaR. Accordingly, we employed non-normal Finance and Accounting, 28(2), 187–201.
VaR models, such as HS and Student’s t VaR model. Ashley, Richard, & Randal, Verbrugge. (2009). Frequency
Our empirical results based on backtesting show that dependence in regression model coefficients: An alternative
the VaR estimates based on the conventional ‘normal’ approach for modeling nonlinear dynamics relationships in
method are usually underestimated (lower than actual). time series. Econometric Reviews, 28(1/3), 4–20.
10 Asia-Pacific Journal of Management Research and Innovation 12(1)

Bank for International Settlements (BIS). (2005), Amendment to Reserve Bank of India (RBI). (2010). Prudential Guidelines
the Capital Accord to Incorporate Market Risks. Retrieved on Capital Adequacy – Implementation of Internal Models
from http://www.bis.org/publ/bcbs119.htm Approach for Market Risk, RBI, Mumbai, April 7, 2010.
Basel Committee on Banking Supervision (BCBS). (2006), Basel Retrieved from https://www.rbi.org.in/scripts/NotificationUser.
II: International Convergence of Capital Measurement and aspx?Id=5574&Mode=0
Capital Standards: A Revised Framework – Comprehensive Rossignolo, Adrian F., Duygun, Fethi Meryem, & Mohamed,
Version. Available at http://www.bis.org/publ/bcbs128.htm Shaban. (2012). Value-at-Risk models and Basel capital
Elliott J., Robert, & Miao, Hong. (2009). VaR and expected charges evidence from emerging and frontier stock markets.
shortfall: A non-normal regime switching framework. Journal of Financial Stability, 8(4), 303–319.
Quantitative Finance, 9(6), 747–755.
Sirr, Gordon, Garvey, John, & Gallagher, Liam. (2011).
Jorion, P. (2007). Value at Risk: The new benchmark for managing
Emerging markets and portfolio foreign exchange risk: An
financial risk (3rd ed.). New York, NY: McGraw-Hill.
empirical investigation using a value-at-risk decomposition
Kupiec, Paul H. (1995). Techniques for Verifying the Accuracy
technique. Journal of International Money and Finance,
of Risk Measurement Models. The Journal of Derivatives,
3(2), 73–84. 30(8), 1749–1772.
Lin, Chu-Hsiung, & Shen, Shan-Shan. (2006). Can the student-t Trenca, I. (2009). The use in banks of VaR method in market risk
distribution provide accurate value at risk. The Journal of management. Scientific Annals of the ‘Alexandru Ioan Cuza’,
Risk Finance, 7(3), 292–300. University of Iasi, Economic Sciences Series, 56, 186–196.
Nieppola, O. (2009). Backtesting value-at-risk models. Helsinki: Retrieved from http://anale.feaa.uaic.ro/anale/resurse/16_
Helsinki School of Economics. Retrieved from https:// F12_Trenca.pdf
aaltodoc.aalto.fi/handle/123456789/181 Wang, Zongrun, Wu, Weitao, Chen, Chao, & Zhou, Yanju.
Pérignon, Christophe, & Daniel, Smith R. (2010). The level and (2010). The exchange rate risk of Chinese yuan: Using VaR
quality of Value-at-Risk disclosure by commercial banks. and ES based on extreme value theory. Journal of Applied
Journal of Banking & Finance, 34(2), 362–377. Statistics, 37, 265–282.

Anda mungkin juga menyukai