Extreme conditional value at risk a coherent scenario for risk management
Extreme cyberbanking losses that occurred during the 2007-2008 cyberbanking crisis reignited questions of whether complete methodologies, which are abundantly based on the accustomed distribution, are able and acceptable for the purpose of accident altitude and management. The aloft assumptions active in these frameworks are that cyberbanking allotment are apart and analogously distributed, and chase the accustomed distribution. However, weaknesses in these methodologies has connected been articular in the literature. Firstly, it is now broadly accustomed that cyberbanking allotment are not commonly distributed; they are asymmetric, skewed, leptokurtic and fat-tailed. Secondly, it is a accustomed actuality that cyberbanking allotment display animation clustering, appropriately the acceptance of apart broadcast is violated.
The accumulated affirmation apropos the august facts of cyberbanking allotment necessitates the charge for adapting complete methodologies or developing new methodologies that will annual for all the stylised facts of cyberbanking allotment explicitly. In this paper, I altercate two accompanying measures of risk; acute value-at-risk (EVaR) and acute codicillary value-at-risk (ECVaR). I altercate that ECVaR is a bigger admeasurement of acute bazaar accident than EVaR utilised by Kabundi and Mwamba (2009) back it is coherent, and captures the furnishings of acute markets events. In contrast, alike admitting EVaR captures the aftereffect of acute bazaar events, it is non-coherent.
Markowitz (1952), Roy (1952), Appearance (1964), Black and Scholes (1973), and Merton’s (1973) aloft toolkit in the development of avant-garde portfolio access (MPT) and the acreage of cyberbanking engineering consisted of means, variance, correlations and covariance of asset returns. In MPT, the about-face or analogously the accustomed aberration was the catholicon admeasurement of risk. A aloft acceptance active in this access is that cyberbanking asset allotment are commonly distributed. Beneath this assumption, acute bazaar contest rarely happen. Back they do occur, accident managers can artlessly amusement them as outliers and apathy them back modelling cyberbanking asset returns.
The acceptance of commonly broadcast asset allotment is too simplistic for use in cyberbanking modelling of acute bazaar events. During acute bazaar action agnate to the 2007-2008 cyberbanking crisis, cyberbanking allotment display behavior that is aloft what the accustomed administration can model.
Starting with the assignment of Mandelbrot (1963) there is added added acceptable empiric affirmation that advance that asset allotment are not commonly distributed. They display agee behavior, ‘fat tails’ and aerial kurtosis than the accustomed administration can accommodate. The association is that acute abrogating allotment do occur, and are added accepted than predicted by the accustomed distribution. Therefore, measures of accident based on the accustomed administration will belittle the accident of portfolios and advance to huge cyberbanking losses, and potentially insolvencies of cyberbanking institutions. To abate the furnishings of bare accident basal buffers stemming from aberration of accident by normality-based cyberbanking modelling, accident measures such as EVaR that go aloft the acceptance of commonly broadcast allotment accept been developed. However, EVaR is non-coherent aloof like VaR from which it is developed. The association is that, alike admitting it captures the furnishings of acute bazaar events, it is not a acceptable admeasurement of accident back it does not reflect about-face – a bucking to one of the cornerstone of portfolio theory. ECVaR artlessly overcomes these problems back it articular and can abduction acute bazaar events.
1.2 RSEARCH PROBLEM
The purpose of this cardboard is to advance acute codicillary value-at-risk (ECVaR), and adduce it as a bigger admeasurement of accident than EVaR beneath altitude of acute bazaar action with cyberbanking allotment that display animation clustering, and are not commonly distributed. Kabundi and Mwamba (2009) accept proposed EVaR as a bigger admeasurement of acute accident than the broadly acclimated VaR, however, it is non-coherent. ECVaR is coherent, and captures the aftereffect of acute bazaar activity, appropriately it is added ill-fitted to archetypal acute losses during bazaar turmoil, and reflects diversification, which is an important claim for any accident admeasurement in portfolio theory.
1.3 RELEVENCE OF THE STUDY
The acceptance that cyberbanking asset allotment are commonly broadcast understates the achievability of exceptional acute contest whose appulse is added adverse than that of contest that are added frequent. Use of VaR and CVaR belittle the riskiness of assets and portfolios, and eventually advance to huge losses and bankruptcies during times of acute bazaar activity.
There are abounding adverse furnishings of application the accustomed administration in the altitude of cyberbanking risk, the best arresting actuality the accident of money due to underestimating risk. During the all-around cyberbanking crisis, a cardinal of banks and non-financial institutions suffered huge cyberbanking losses; some went broke and failed, partly because of bare basal allocation stemming from aberration of accident by models that afflicted commonly broadcast returns.
Measures of accident that do not accept course of cyberbanking allotment accept been developed. One such admeasurement is EVaR (Kabundi and Mwamba (2009)). EVaR captures the aftereffect of acute bazaar events, about it is not coherent. As a result, EVaR is not a acceptable admeasurement of accident back it does not reflect diversification.
In cyberbanking markets characterised by assorted sources of accident and acute bazaar volatility, it is important to accept a accident admeasurement that is articular and can abduction the aftereffect of acute bazaar activity. ECVaR is advocated to fulfils this role of ensuring acute bazaar accident while befitting to portfolio theory’s acumen of diversification.
1.4 RESEARCH DESIGN
Chapter 2 will present a abstract assay of accident altitude methodologies currently acclimated by cyberbanking institutions, in particular, VaR and CVaR. I additionally altercate the strengths and weaknesses of these measures. Another accident admeasurement not broadly accustomed appropriately far is the EVaR. We altercate EVaR as an advance in accident altitude methodologies. I apostle that EVaR is not a acceptable admeasurement of accident back it is non-coherent. This leads to the abutting chapter, which presents ECVaR as a bigger accident admeasurement that is articular and can abduction acute bazaar events.
Chapter 3 will be anxious with acute codicillary value-at-risk (ECVaR) as a acceptable modelling framework that artlessly overcomes the course acceptance of asset allotment in the modelling of acute bazaar events. This is followed with a allusive assay of EVaR and ECVaR application cyberbanking abstracts accoutrement both the pre-financial crisis and the cyberbanking crisis periods.
Chapter 4 will be anxious with abstracts sources, basal abstracts description, and the admiration of EVaR, and ECVaR.
Chapter 5 will altercate the empiric after-effects and the association for accident measurement.
Finally, affiliate 6 will accord concussions and highlight the admonition for approaching research.
CHAPTER 2: RISK MEASUREMENT AND THE EMPIRICAL
DISTRIBUTION OF FINANCIAL RETURNS
2.1 Accident Altitude in Finance: A Assay of Its Origins
The abstraction of accident has been accustomed for abounding years afore Markowitz’s Portfolio Access (MPT). Bernoulli (1738) apparent the St. Petersburg absurdity and acquired axiological insights of risk-averse behavior and the allowances of diversification. In his conception of accustomed account theory, Bernoulli did not ascertain accident explicitly; however, he accustomed it from the appearance of the account action (Bulter et al. (2005:134); Brancinger & Weber, (1997: 236)). Irving Fisher (1906) appropriate the use of about-face to admeasurement bread-and-butter risk. Von Neumann and Morgenstern (1947) acclimated accustomed account access in the assay of amateur and appropriately deduced abounding of the avant-garde compassionate of accommodation authoritative beneath accident or uncertainty. Therefore, adverse to accustomed belief, the abstraction of accident has been accustomed able-bodied afore MPT.
Even admitting the abstraction of accident was accustomed afore MPT, Markowitz (1952) aboriginal provided a analytical algorithm to admeasurement accident application the about-face in the conception of the mean-variance archetypal for which he won the Nobel Prize in 1990. The development of the mean-variance archetypal aggressive assay in accommodation authoritative beneath accident and the development of accident measures. The abstraction of accident and accommodation authoritative beneath ambiguity (which is advised the aforementioned as accident in best cases) amplitude aloft disciplines. In accommodation science and psychology, Coombs and Pruitt (1960), Pruitt (1962), Coombs (1964), Coombs and Meyer (1969), and Coombs and Huang (1970a, 1970b) advised the acumen of gambles and how their another is afflicted by their perceived risk. In economics, accounts and altitude theory, Markowitz (1952, 1959), Tobin (1958), Pratt (1964), Pollatsek & Tversky (1970), Luce (1980) and others investigate portfolio another and the altitude of accident of those portfolios, and gambles in general. Their aggregate assignment produces a cardinal of accident measures that alter in how they rank the riskiness of options, portfolios, or gambles. Admitting the accident measures vary, Pollatsek and Tversky (1970: 541) recognises that they allotment the following: (1) Accident is admired as a acreage of allotment amid options. (2) Options can be advisedly ordered according to their riskiness. (3) As appropriate by Irving Fisher in 1906, the accident of an advantage is somehow accompanying to the about-face or burning in its outcomes. In accession to these basal properties, Markowitz commendations accident as a ‘bad’, implying article that is undesirable. Back Markowitz (1952), abounding accident measures such as the semi-variance, complete deviation, and the lower semi-variance etc. (see Brachinger and Weber, (1997)) were developed, however, the about-face connected to boss empiric finance. It was in the 1990s that a new measure, VaR was popularised and became industry accustomed as a accident measure. I present this accident admeasurement in the abutting section.
2.2 Value-at-risk (VaR)
2.2.1 Analogue and concepts
Besides these basal account apropos accident measures, there is no universally accustomed analogue of accident (Pollatsek and Tversky, 1970:541); as a result, accident measures abide to be developed. J.P Morgan & Reuters (1996) pioneered a aloft advance in the advance of accident altitude with the use of value-at-risk (VaR), and the consecutive Basel board advocacy that banks could use it for their centralized accident management.
VaR is anxious with barometer the accident of a cyberbanking position due to the ambiguity apropos the approaching levels of absorption rates, banal prices, article prices, and barter rates. The accident consistent in the movement of these bazaar factors is alleged bazaar risk. VaR is the accustomed best accident of a cyberbanking position with a accustomed akin of aplomb over a authentic horizon. VaR provides answers to question: what is the best accident that I can lose over, say the abutting ten canicule with 99 percent confidencePut differently, what is the best accident that will be exceeded alone one percent of the times in the abutting ten dayI allegorize the ciphering of VaR application one of the methods that is available, namely parametric VaR. I denote by the bulk of acknowledgment and by the portfolio bulk at time. Again is accustomed by
(1) The absolute accident (the abrogating of the profit, which is) is accustomed by
(2) Back is commonly broadcast (as is commonly assumed), the capricious has a accustomed accustomed administration with beggarly of and accustomed aberration of. We can account VaR from the afterward equation:
(3) area implies a aplomb level. If we accept a 99% aplomb level, we have
(4) In we accept -2.33 as our VaR at 99% aplomb level, and we will beat this VaR alone 1% of the times. From (4), it can be apparent that the 99% aplomb VaR is accustomed byVaR
(5)Generalising from (5), we can accompaniment the quantile VaR of the administration as follows
(6)VaR is an automatic admeasurement of accident that can be calmly implemented. This is axiomatic in its avant-garde use in the industry. However, is it an optimal measureThe abutting area addresses the limitations of VaR.
2.2.2 Limitations of VaR
Artzner et al. (1997,1999) developed a set of axioms that if annoyed by a accident measure, again that accident admeasurement is ‘coherent’. The association of articular measures of accident is that “it is not accessible to accredit a action for barometer accident unless it satisfies these axioms” (Mitra, 2009:8). Accident measures that amuse these axioms can be advised accustomed and optimal back they are founded on the aforementioned algebraic axioms that are about accepted.
Artzner et al. (1997, 1999) put avant-garde the aboriginal axioms of accident measures, and any accident admeasurement that satisfies them is a articular admeasurement of risk. Letting be a accident admeasurement authentic on two portfolios and. Then, the accident admeasurement is articular if it satisfies the afterward axioms:
(1)Monotonicity: if then
We adapt the monotonicity adage to beggarly that college losses are associated with college risk.
Assuming that there is no clamminess risk, the accord adage beggarly that accident is not a action of the abundance of a banal purchased, accordingly we cannot abate or access accident by advance altered amounts in the aforementioned stock.
(3)Translation invariance: , area is a assertive security;
This agency that advance in a assertive asset does not access accident with certainty.
(4)Sub-additivity: Possibly the best important axiom, sub-additivity insures that a accident admeasurement reflects about-face – the accumulated accident of two portfolios is beneath than the sum of the risks of alone portfolios. VaR does not amuse the best important adage of sub-additivity, appropriately it is non-coherent. Added so, VaR tells us what we can apprehend to lose if an acute accident does not occur, appropriately it does not acquaint us the extend of losses we can acquire if a “tail” accident occurs. VaR is accordingly not optimal admeasurement of risk.
The non-coherence, and therefor non-optimality of VaR as a barometer of accident led to the development of codicillary value-at-risk (CVaR) by Artzner et al. (1997, 1999), and Uryasev and Rockafeller (1999). I discus CVaR in the abutting section.
2.3 Codicillary Value-at-Risk
CVaR is additionally accustomed as “Expected Shortfall” (ES),“Tail VaR”, or “Tail codicillary expectation”, and it measures accident aloft VaR. Yamai and Yoshiba (2002) ascertain CVaR as the codicillary apprehension of losses accustomed that the losses beat VaR. Mathematically, CVaR is accustomed by the following:
(7) CVaR offers added insights apropos accident that VaR in that it tells us what we can apprehend to lose if the losses beat VaR. Unfortunately, the accounts industry has been apathetic in adopting CVaR as its adopted accident measure. This is besides the actuality that “the actuarial/insurance association has tended to aces up on developments in cyberbanking accident administration abundant added bound than cyberbanking accident managers accept best up on developments in actuarial science” (Dowd and Black (2006:194)). Hopefully, the furnishings of the cyberbanking crisis will change this observation.
In abundant of the applications of VaR and CVaR, allotment accept been afflicted to be commonly distributed. However, it is broadly accustomed that allotment are not commonly distributed. The association is that, VaR and CVaR as currently acclimated in accounts will not abduction acute losses. This will advance to aberration of accident and bare basal allocation aloft business units. In times of bazaar accent back added basal is required, it will be inadequate. This may advance to the defalcation of cyberbanking institutions. Methodologies that can abduction acute contest are accordingly needed. In the abutting section, I altercate the empiric affirmation on cyberbanking returns, and thereafter altercate acute bulk access (EVT) as a acceptable framework of modelling acute losses.
2.4 The Empiric Administration of Cyberbanking Returns
Back in 1947, Geary wrote, “Normality is a myth; there never was, and never will be a accustomed distribution” (as cited by Krishnaiah (1980: 279). Today this acknowledgment is accurate by a abundant bulk of empiric affirmation adjoin commonly broadcast returns; nevertheless, course continues to be the crammer of empiric finance. If the course acceptance fails to canyon empiric tests, why are practitioners so bedeviled with the alarm curveCould their allure be justifiedTo bare some of the accessible responses to these questions, let us aboriginal attending at the accent of actuality normal, and again attending at the dangers of afield bold normality.
2.4.1 The Accent of Actuality Normal
The accustomed administration is the broadly acclimated administration in statistical assay in all fields that utilises statistics in answer phenomenon. The accustomed administration can be afflicted for a population, and it gives a affluent set of algebraic after-effects (Mardia, 1980: 279). In another words, the algebraic representations are tractable, and are accessible to implement. The populations can artlessly be explained by its beggarly and about-face back the accustomed administration is assumed. The catholicon advantage is that the modelling action beneath course acceptance is actual simple.
In fields that accord with accustomed phenomenon, such as physics and geology, the accustomed administration has absolutely succeeded in answer the variables of interest. The aforementioned cannot be said in the accounts field. The accustomed anticipation administration has been accountable to accurate empiric rejection. A cardinal of august facts of asset returns, statistical tests of course and the accident of acute abrogating allotment disputes the accustomed administration as the basal abstracts breeding action for asset returns. We briefly altercate these empiric allegation next.
2.4.2 Deviations From Normality
Ever back Mandelbrot (1963), Fama (1963), Fama (1965) amid others, it is a accustomed actuality that asset allotment are not commonly distributed. The accumulated empiric affirmation back the 1960s credibility out the afterward august facts of asset returns:
(1)Volatility clustering: periods of aerial animation tend to be followed by periods of aerial volatility, and aeon of low animation tend to be followed by low volatility.
(2)Autoregressive amount changes: A amount change depends on amount changes in the accomplished period.
(3)Skewness: Absolute prices changes and abrogating amount changes are not of the aforementioned magnitude.
(4)Fat-tails: The probabilities of acute abrogating (positive) allotment are abundant beyond than predicted by the accustomed distribution.
(5)Time-varying appendage thickness: Added acute losses action during agitated bazaar action than during accustomed bazaar activity.
(6)Frequency abased fat-tails: aerial abundance abstracts tends to be added fat-tailed than low abundance data.
In accession to these august facts of asset returns, acute contest of 1974 Germany cyberbanking crisis, 1978 cyberbanking crisis in Spain, 1990s Japanese cyberbanking crisis, September 2001, and the 2007-2008 US acquaintance ( BIS, 2004) could not accept happened beneath the accustomed distribution. Alternatively, we could aloof accept advised them as outliers and abandoned them; however, acquaintance has apparent that alike those who are bedeviled with the Gaussian administration could not avoid the adverse furnishings of the 2007-2008 all-around cyberbanking crisis.
With these empiric facts accustomed to the quantitative accounts community, what is the action for the connected use of the course assumptionIt could be accessible that those that stick with the course acceptance apperceive alone how to accord with commonly broadcast data. It is their hammer; aggregate that comes their way seems like a nail! As Esch (2010) notes, for those that do accept another accoutrement to accord with non-normal data, they abide to use the accustomed administration on the area of parsimony. However, “representativity should not be sacrificed for simplicity” (Fabozzi et al., 2011:4).
Better modelling frameworks to accord with acute ethics that are appropriate of departures from course accept been developed. Acute bulk access is one such alignment that has enjoyed success in another fields alfresco finance, and has been acclimated to archetypal cyberbanking losses with success. In the abutting chapter, I present acute value-based methodologies as a applied and bigger alignment to affected non-normality in asset returns.
CHAPTER 3: EXTREME VALUE THEORY: A SUITABLE AND
1.3. Acute Bulk Theory
Extreme bulk access was developed to archetypal acute accustomed phenomena such as floods, acute winds, and temperature, and is able-bodied accustomed in fields such as engineering, insurance, and climatology. It provides a acceptable way to archetypal the cape of distributions that abduction non-normal activities. Back it concentrates on the cape of distributions, it has been adopted to archetypal asset allotment in time of acute bazaar action (see Embrechts et al. (1997); McNeil and Frey (2000); Danielsson and de Vries (2000).
Gilli and Kellezi (2003) credibility out two accompanying means of modelling acute events. The aboriginal way describes the best accident through a absolute administration accustomed as the generalised acute bulk administration (GED), which is a ancestors of asymptotic distributions that call normalised maxima or minima. The additional way provides asymptotic administration that describes the absolute administration of scaled excesses over aerial thresholds, and is accustomed as the generalised Pareto administration (GPD). The two absolute distributions after-effects into two approaches of EVT-based modelling – the block of maxima adjustment and the peaks over beginning adjustment respectively.
3.1. The Block of Maxima Method
Let us accede absolute and analogously broadcast (i.i.d) accidental capricious with accepted administration action ?. Let be the best of the aboriginal accidental variables. Also, let us accept is the high end of. For, the agnate after-effects for the minima can be acquired from the afterward identity
(8) about absolutely converges to whether it is bound or absolute since,
Following Embrechts et al. (1997), and Shanbhang and Rao (2003), the absolute access finds norming constants and a non-degenerate administration action in such a way that the administration action of a normalized adaptation of converges to as follows;, as
(9) is an acute bulk administration function, and ? is the area of allure of, (written as), if blueprint (2) holds for acceptable ethics of and. It can additionally be said that the two acute bulk administration functions and accord in the aforementioned ancestors if for someand all.
Fisher and Tippett (1928), De Haan (1970, 1976), Weissman (1978), and Embrechts et al. (1997) appearance that the absolute administration action belongs to one of the afterward three body functions for some.
Any acute bulk administration can be classified as one of the three types in (10), (11) and (12). and are the accustomed acute bulk administration and the agnate accidental variables are alleged accustomed acute accidental variables. For another assuming of the three distributions, see Nagaraja (1988), and Khan and Beg (1987).
3.2.The Generalized Acute Bulk Distribution
The three administration functions accustomed in (10), (11) and (12) aloft can be accumulated into one three-parameter administration alleged the generalised acute bulk administration (GEV) accustomed by,, with
(13) We denote the GEV by, and the ethics andgive acceleration to the three administration functions in (3). In blueprint (4) above, and represent the area parameter, the calibration parameter, and the tail-shape constant respectively. corresponds to the Frechet, and distributioncorresponds to the Weibull distribution. The case area reduces to the Gumbel distribution.
To access the estimates of we use the best likelihood method, afterward Kabundi and Mwamba (2009). To alpha with, we fit the sample of best losses to a GEV. Thereafter, we use the best likelihood adjustment to appraisal the ambit of the GEV from the logarithmic anatomy of the acceptable action accustomed by;
(14) To access the estimates of we booty fractional derivatives of blueprint (14) with account to and, and equating them to zero.
3.2.1. Acute Value-at-Risk
The EVaR authentic as the best likelihood quantile estimator of, is by analogue accustomed by
(15) The abundance is the quantile of, and I denote it as the alpha percept VaR authentic as follows afterward Kabundi and Mwamba (2009), and Embrech et al. (1997):
(16) Alike admitting EVaR captures acute losses, by addendum from VaR it is non-coherent. As such, it cannot be acclimated for the purpose of portfolio access back it does not reflect diversification. To affected this problem, In the abutting section, I extend CVaR to ECVaR so as to abduction acute losses coherently.
3.2.2. Acute Codicillary Value-at-Risk (ECVaR): An Acute Articular Admeasurement of Risk
I extend ECVaR from EVaR in a agnate address that I acclimated to extend CVaR from VaR. ECVaR can accordingly be bidding as follows:
(17) In the afterward chapter, we call the abstracts and its sources.
CHAPTER 4: DATA DISCRIPTION.
I will use banal bazaar indexes of bristles avant-garde economies absolute that of the United States, Japan, Germany, France, and United Kingdom, and bristles arising economies absolute Brazil, Russia, India, China, and South Africa. Accessible sources of abstracts that will be acclimated are I-net Bride, Bloomberg, and alone country axial banks.
CHAPTER 5: DISCUSION OF EMPIRICAL RESULTS
In this chapter, I will altercate the empiric results. Specifically, the capability of ECVaR will be discussed about to that of EVaR. Implications for accident altitude will additionally be discussed in this chapter.
CHAPTER 6: CONCLUSIONS
This affiliate will accord absolute remarks, and admonition for approaching research.
 Markowitz, H.M.: 1952, Portfolio selection, Journal of Accounts 7 (1952), 77-91
2 Roy, A.D.: 1952, Safety Aboriginal and the Holding of Assets. Econometrica, vol. 20 no 3 p 431-449.
3 Shape, W.F.: 1964, Basal Asset Prices: A Access of Bazaar Equilibrium beneath Altitude of Risk. The Journal of Finance, Vol. 19 No 3 p 425-442.
4 Black, F., and Scholes, M.: 1973, The Pricing of Options and Corporate Liabilities, Journal of Political Economy, vol. 18 () 637-59.
5 Merton, R. C.: 1973, The Access of Rational Advantage Pricing. Alarm Journal of Economics and Administration Science, Spring.
6 Artzner, Ph., F. Delbaen, J.-M. Eber, And D. Heath .: 1997, Thinking Coherently, Accident 10 (11) 68–71.
7 Artzner, Ph., Delbaen, F., Eber, J-M., And Heath , D.: 1999, Thinking Coherently. Algebraic Finance, Vol. 9, No. 3 203–228
8 Bernoulli, D.: 1954, Exposition of a new access on the altitude of risk, Econometrica 22 (1) 23-36, Translation of a cardboard originally appear in Latin in St. Petersburg in 1738.
9 Butler, J.C., Dyer, J.S., and Jia, J.: 2005, An Empiric Investigation of the Acceptance of Accident –Value Models. Journal of Accident and Uncertainty, vol. 30 (2), pp. 133-156.
10 Brachinger, H.W., and Weber, M.: 1997, Accident as a primitive: a analysis of measures of perceived risk. OR Spektrum, Vol 19 () 235-250
 Fisher, I.: 1906, The attributes of Basal and Income. Macmillan.
1 von Neumann, J. and Morgenstern, O.: 1947, Access of amateur and bread-and-butter behaviour, 2nd ed., Princeton University Press.
2 Coombs, C.H., and Pruitt, D.G.: 1960, Components of Accident in Accommodation Making: Anticipation and About-face preferences. Journal of Experimental Psychology, vol. 60 () pp. 265-277.
3 Pruitt, D.G.: 1962, Partten and Akin of accident in Gambling Decisions. Psychological Review, vol. 69 ()( pp. 187-201.
4 Coombs, C.H.: 1964, A Access of Data. New York: Wiley.
5 Coombs, C.H., and Meyer, D.E.: 1969, Accident another in Coin-toss Games. Journal of Algebraic Psychology, vol. 6 () p 514-527.
6 Coombs, C.H., and Huang, L.C.: 1970a, Polynomial Psychophysics of Risk. Journal of Experimental psychology, vol 7 (), pp. 317-338.
7 Markowitz, H.M.: 1959, Portfolio Selection: Efficient about-face of Investment. Yale University Press, New Haven, USA.
8 Tobin, J. E.: 1958, clamminess another as behavior appear risk. Assay of Bread-and-butter Studies p 65-86.
9 Pratt, J.W.: 1964, Accident Aversion in the Small and in the Large. Econometrica, vol. 32 () p 122-136.
20 Pollatsek, A. and Tversky, A.: 1970, A access of Risk. Journal of Algebraic Attitude 7 (no issue) 540-553.
2 Luce, D. R.:1980, Several accessible measures of risk. Access and Accommodation 12 (no issue) 217-228.
22 J.P. Morgan and Reuters.: 1996, RiskMetrics Technical document. Accessible at http://riskmetrics.comrmcovv.html Accessed…
23 Uryasev, S., and Rockafeller, R.T.: 1999, Access of Codicillary Value-at-Risk. Accessible at http://www.gloriamundi.org
24 Mitra, S.: 2009, Accident measures in Quantitative Finance. Accessible on line. [Accessed…]
25 Geary, R.C.: 1947, Testing for Normality, Biometrika, vol. 34, pp. 209-242.
26 Mardia, K.V.: 1980, P.R. Krishnaiah, ed., Handbook of Statistics, Vol. 1. North-Holland Publishing Company. Pp. 279-320.
27 Mandelbrot, B.: 1963, The aberration of assertive abstract prices. Journal of Business, vol. 26, pp. 394-419.
28 Fama, E.: 1963, Mandelbrot and the abiding paretian hypothesis. Journal of Business, vol. 36, pp. 420-429.
29 Fama, E.: 1965, The behavior of banal bazaar prices. Journal of Business, vol. 38, pp. 34-105.
30 Esch, D.: 2010, Non-Normality facts and fallacies. Journal of Investment Management, vol. 8 (1), pp. 49-61.
3 Stoyanov, S.V., Rachev, S., Racheva-Iotova, B., & Fabozzi, F.J.: 2011, Fat-tailed Models for Accident Estimation. Journal of Portfolio Management, vol. 37 (2). Accessible at http://www.iijournals.com/doi/abs/10.3905/jpm.2011.37.2.107
32 Embrechts, P., Uppelberg, C.K.L, and T. Mikosch.: 1997, Modeling extremal contest for allowance and finance, Springer
33 McNeil, A. and Frey, R.: 2000, Admiration of tail-related accident measures for heteroscedastic cyberbanking time series: an acute bulk approach, Journal of Empiric Finance, Volume 7, Issues 3-4, 271- 300.
34 Danielsson, J. and de Vries, C.: 2000, Value-at-Risk and Acute Returns, Annales d’Economie et deb Statistique, Volume 60, 239-270.
35Gilli, G., and Kellezi, E.: (2003), An Application of Acute Bulk Access for Barometer Risk, Department of Econometrics, University of Geneva, Switzerland. Accessible from: http://www.gloriamundi.org/picsresources/mgek.pdf
36 Shanbhag, D.N., and Rao, C.R.: 2003, Acute Bulk Theory, Models and Simulation. Handbook of Statistics, Vol 21(). Elsevier Science B.V.
37 Fisher, R. A. and Tippett, L.H.C.: 1928, Limiting forms of the abundance administration of the better or aboriginal affiliate of a sample. Proc. Cambridge Philos. Soc. Vol 24, 180-190.
38 De Haan, L.: 1970, On Regular Aberration and Its Application to the Weak Convergence of Sample Extremes. Algebraic Centre Tract, Vol. 32. Mathematisch Centmm, Amsterdam
39 De Haan, L.: 1976, Sample extremes: an elementary introduction. Statistica Neerlandica, vol. 30, 161-172.
40 Weissman, I.: 1978, Admiration of ambit and ample quantiles based on the k better observations. J. Amer. Statist. Assoc. vol. 73, 812-815.
4 Nagaraja, H. N.: 1988, Some characterizations of connected distributions based on regressions of adjoining adjustment statistics and almanac values. Sankhy A 50, 70-73.
42 Khan, A. H. and Beg, M.I.: 1987, Assuming of the Weibull administration by codicillary variance. Snaky A 49, 268-271.
43 Kabundi, A. and Mwamba, J.W.M.: 2009, Acute bulk at Risk: a Scenario for Accident management. SAJE Forthcoming.
Order a unique copy of this paper