Misplaced Pages

Expected shortfall

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.
(Redirected from Expected tail loss) Measure of financial risk

Expected shortfall (ES) is a risk measure—a concept used in the field of financial risk measurement to evaluate the market risk or credit risk of a portfolio. The "expected shortfall at q% level" is the expected return on the portfolio in the worst q % {\displaystyle q\%} of cases. ES is an alternative to value at risk that is more sensitive to the shape of the tail of the loss distribution.

Expected shortfall is also called conditional value at risk (CVaR), average value at risk (AVaR), expected tail loss (ETL), and superquantile.

ES estimates the risk of an investment in a conservative way, focusing on the less profitable outcomes. For high values of q {\displaystyle q} it ignores the most profitable but unlikely possibilities, while for small values of q {\displaystyle q} it focuses on the worst losses. On the other hand, unlike the discounted maximum loss, even for lower values of q {\displaystyle q} the expected shortfall does not consider only the single most catastrophic outcome. A value of q {\displaystyle q} often used in practice is 5%.

Expected shortfall is considered a more useful risk measure than VaR because it is a coherent spectral measure of financial portfolio risk. It is calculated for a given quantile-level q {\displaystyle q} and is defined to be the mean loss of portfolio value given that a loss is occurring at or below the q {\displaystyle q} -quantile.

Formal definition

If X L p ( F ) {\displaystyle X\in L^{p}({\mathcal {F}})} (an L) is the payoff of a portfolio at some future time and 0 < α < 1 {\displaystyle 0<\alpha <1} then we define the expected shortfall as

ES α ( X ) = 1 α 0 α VaR γ ( X ) d γ {\displaystyle \operatorname {ES} _{\alpha }(X)=-{\frac {1}{\alpha }}\int _{0}^{\alpha }\operatorname {VaR} _{\gamma }(X)\,d\gamma }

where VaR γ {\displaystyle \operatorname {VaR} _{\gamma }} is the value at risk. This can be equivalently written as

ES α ( X ) = 1 α ( E [ X   1 { X x α } ] + x α ( α P [ X x α ] ) ) {\displaystyle \operatorname {ES} _{\alpha }(X)=-{\frac {1}{\alpha }}\left(\operatorname {E} +x_{\alpha }(\alpha -P)\right)}

where x α = inf { x R : P ( X x ) α } = VaR α ( X ) {\displaystyle x_{\alpha }=\inf\{x\in \mathbb {R} :P(X\leq x)\geq \alpha \}=-\operatorname {VaR} _{\alpha }(X)} is the lower α {\displaystyle \alpha } -quantile and 1 A ( x ) = { 1 if  x A 0 else {\displaystyle 1_{A}(x)={\begin{cases}1&{\text{if }}x\in A\\0&{\text{else}}\end{cases}}} is the indicator function. Note, that the second term vanishes for random variables with continuous distribution functions.

The dual representation is

ES α ( X ) = inf Q Q α E Q [ X ] {\displaystyle \operatorname {ES} _{\alpha }(X)=\inf _{Q\in {\mathcal {Q}}_{\alpha }}E^{Q}}

where Q α {\displaystyle {\mathcal {Q}}_{\alpha }} is the set of probability measures which are absolutely continuous to the physical measure P {\displaystyle P} such that d Q d P α 1 {\displaystyle {\frac {dQ}{dP}}\leq \alpha ^{-1}} almost surely. Note that d Q d P {\displaystyle {\frac {dQ}{dP}}} is the Radon–Nikodym derivative of Q {\displaystyle Q} with respect to P {\displaystyle P} .

Expected shortfall can be generalized to a general class of coherent risk measures on L p {\displaystyle L^{p}} spaces (Lp space) with a corresponding dual characterization in the corresponding L q {\displaystyle L^{q}} dual space. The domain can be extended for more general Orlicz Hearts.

If the underlying distribution for X {\displaystyle X} is a continuous distribution then the expected shortfall is equivalent to the tail conditional expectation defined by TCE α ( X ) = E [ X X VaR α ( X ) ] {\displaystyle \operatorname {TCE} _{\alpha }(X)=E} .

Informally, and non-rigorously, this equation amounts to saying "in case of losses so severe that they occur only alpha percent of the time, what is our average loss".

Expected shortfall can also be written as a distortion risk measure given by the distortion function

g ( x ) = { x 1 α if  0 x < 1 α , 1 if  1 α x 1. {\displaystyle g(x)={\begin{cases}{\frac {x}{1-\alpha }}&{\text{if }}0\leq x<1-\alpha ,\\1&{\text{if }}1-\alpha \leq x\leq 1.\end{cases}}\quad }

Examples

Example 1. If we believe our average loss on the worst 5% of the possible outcomes for our portfolio is EUR 1000, then we could say our expected shortfall is EUR 1000 for the 5% tail.

Example 2. Consider a portfolio that will have the following possible values at the end of the period:

probability
of event
ending value
of the portfolio
10% 0
30% 80
40% 100
20% 150

Now assume that we paid 100 at the beginning of the period for this portfolio. Then the profit in each case is (ending value−100) or:

probability
of event
profit
10% −100
30% −20
40% 0
20% 50

From this table let us calculate the expected shortfall ES q {\displaystyle \operatorname {ES} _{q}} for a few values of q {\displaystyle q} :

q {\displaystyle q} expected shortfall ES q {\displaystyle \operatorname {ES} _{q}}
5% 100
10% 100
20% 60
30% 46.6
40% 40
50% 32
60% 26.6
80% 20
90% 12.2
100% 6

To see how these values were calculated, consider the calculation of ES 0.05 {\displaystyle \operatorname {ES} _{0.05}} , the expectation in the worst 5% of cases. These cases belong to (are a subset of) row 1 in the profit table, which have a profit of −100 (total loss of the 100 invested). The expected profit for these cases is −100.

Now consider the calculation of ES 0.20 {\displaystyle \operatorname {ES} _{0.20}} , the expectation in the worst 20 out of 100 cases. These cases are as follows: 10 cases from row one, and 10 cases from row two (note that 10+10 equals the desired 20 cases). For row 1 there is a profit of −100, while for row 2 a profit of −20. Using the expected value formula we get

10 100 ( 100 ) + 10 100 ( 20 ) 20 100 = 60. {\displaystyle {\frac {{\frac {10}{100}}(-100)+{\frac {10}{100}}(-20)}{\frac {20}{100}}}=-60.}

Similarly for any value of q {\displaystyle q} . We select as many rows starting from the top as are necessary to give a cumulative probability of q {\displaystyle q} and then calculate an expectation over those cases. In general, the last row selected may not be fully used (for example in calculating ES 0.20 {\displaystyle -\operatorname {ES} _{0.20}} we used only 10 of the 30 cases per 100 provided by row 2).

As a final example, calculate ES 1 {\displaystyle -\operatorname {ES} _{1}} . This is the expectation over all cases, or

0.1 ( 100 ) + 0.3 ( 20 ) + 0.4 0 + 0.2 50 = 6. {\displaystyle 0.1(-100)+0.3(-20)+0.4\cdot 0+0.2\cdot 50=-6.\,}

The value at risk (VaR) is given below for comparison.

q {\displaystyle q} VaR q {\displaystyle \operatorname {VaR} _{q}}
0 % q < 10 % {\displaystyle 0\%\leq q<10\%} −100
10 % q < 40 % {\displaystyle 10\%\leq q<40\%} −20
40 % q < 80 % {\displaystyle 40\%\leq q<80\%} 0
80 % q 100 % {\displaystyle 80\%\leq q\leq 100\%} 50

Properties

The expected shortfall ES q {\displaystyle \operatorname {ES} _{q}} increases as q {\displaystyle q} decreases.

The 100%-quantile expected shortfall ES 1 {\displaystyle \operatorname {ES} _{1}} equals negative of the expected value of the portfolio.

For a given portfolio, the expected shortfall ES q {\displaystyle \operatorname {ES} _{q}} is greater than or equal to the Value at Risk VaR q {\displaystyle \operatorname {VaR} _{q}} at the same q {\displaystyle q} level.

Optimization of expected shortfall

Expected shortfall, in its standard form, is known to lead to a generally non-convex optimization problem. However, it is possible to transform the problem into a linear program and find the global solution. This property makes expected shortfall a cornerstone of alternatives to mean-variance portfolio optimization, which account for the higher moments (e.g., skewness and kurtosis) of a return distribution.

Suppose that we want to minimize the expected shortfall of a portfolio. The key contribution of Rockafellar and Uryasev in their 2000 paper is to introduce the auxiliary function F α ( w , γ ) {\displaystyle F_{\alpha }(w,\gamma )} for the expected shortfall: F α ( w , γ ) = γ + 1 1 α ( w , x ) γ [ ( w , x ) γ ] + p ( x ) d x {\displaystyle F_{\alpha }(w,\gamma )=\gamma +{1 \over {1-\alpha }}\int _{\ell (w,x)\geq \gamma }\left_{+}p(x)\,dx} Where γ = VaR α ( X ) {\displaystyle \gamma =\operatorname {VaR} _{\alpha }(X)} and ( w , x ) {\displaystyle \ell (w,x)} is a loss function for a set of portfolio weights w R p {\displaystyle w\in \mathbb {R} ^{p}} to be applied to the returns. Rockafellar/Uryasev proved that F α ( w , γ ) {\displaystyle F_{\alpha }(w,\gamma )} is convex with respect to γ {\displaystyle \gamma } and is equivalent to the expected shortfall at the minimum point. To numerically compute the expected shortfall for a set of portfolio returns, it is necessary to generate J {\displaystyle J} simulations of the portfolio constituents; this is often done using copulas. With these simulations in hand, the auxiliary function may be approximated by: F ~ α ( w , γ ) = γ + 1 ( 1 α ) J j = 1 J [ ( w , x j ) γ ] + {\displaystyle {\widetilde {F}}_{\alpha }(w,\gamma )=\gamma +{1 \over {(1-\alpha )J}}\sum _{j=1}^{J}_{+}} This is equivalent to the formulation: min γ , z , w γ + 1 ( 1 α ) J j = 1 J z j , s.t.  z j ( w , x j ) γ , z j 0 {\displaystyle \min _{\gamma ,z,w}\;\gamma +{1 \over {(1-\alpha )J}}\sum _{j=1}^{J}z_{j},\quad {\text{s.t. }}z_{j}\geq \ell (w,x_{j})-\gamma ,\;z_{j}\geq 0} Finally, choosing a linear loss function ( w , x j ) = w T x j {\displaystyle \ell (w,x_{j})=-w^{T}x_{j}} turns the optimization problem into a linear program. Using standard methods, it is then easy to find the portfolio that minimizes expected shortfall.

Formulas for continuous probability distributions

Closed-form formulas exist for calculating the expected shortfall when the payoff of a portfolio X {\displaystyle X} or a corresponding loss L = X {\displaystyle L=-X} follows a specific continuous distribution. In the former case, the expected shortfall corresponds to the opposite number of the left-tail conditional expectation below VaR α ( X ) {\displaystyle -\operatorname {VaR} _{\alpha }(X)} :

ES α ( X ) = E [ X X VaR α ( X ) ] = 1 α 0 α VaR γ ( X ) d γ = 1 α VaR α ( X ) x f ( x ) d x . {\displaystyle \operatorname {ES} _{\alpha }(X)=E=-{\frac {1}{\alpha }}\int _{0}^{\alpha }\operatorname {VaR} _{\gamma }(X)\,d\gamma =-{\frac {1}{\alpha }}\int _{-\infty }^{-\operatorname {VaR} _{\alpha }(X)}xf(x)\,dx.}

Typical values of α {\textstyle \alpha } in this case are 5% and 1%.

For engineering or actuarial applications it is more common to consider the distribution of losses L = X {\displaystyle L=-X} , the expected shortfall in this case corresponds to the right-tail conditional expectation above VaR α ( L ) {\displaystyle \operatorname {VaR} _{\alpha }(L)} and the typical values of α {\displaystyle \alpha } are 95% and 99%:

ES α ( L ) = E [ L L VaR α ( L ) ] = 1 1 α α 1 VaR γ ( L ) d γ = 1 1 α VaR α ( L ) + y f ( y ) d y . {\displaystyle \operatorname {ES} _{\alpha }(L)=\operatorname {E} ={\frac {1}{1-\alpha }}\int _{\alpha }^{1}\operatorname {VaR} _{\gamma }(L)\,d\gamma ={\frac {1}{1-\alpha }}\int _{\operatorname {VaR} _{\alpha }(L)}^{+\infty }yf(y)\,dy.}

Since some formulas below were derived for the left-tail case and some for the right-tail case, the following reconciliations can be useful:

ES α ( X ) = 1 α E [ X ] + 1 α α ES α ( L )  and  ES α ( L ) = 1 1 α E [ L ] + α 1 α ES α ( X ) . {\displaystyle \operatorname {ES} _{\alpha }(X)=-{\frac {1}{\alpha }}\operatorname {E} +{\frac {1-\alpha }{\alpha }}\operatorname {ES} _{\alpha }(L){\text{ and }}\operatorname {ES} _{\alpha }(L)={\frac {1}{1-\alpha }}\operatorname {E} +{\frac {\alpha }{1-\alpha }}\operatorname {ES} _{\alpha }(X).}

Normal distribution

If the payoff of a portfolio X {\displaystyle X} follows the normal (Gaussian) distribution with p.d.f. f ( x ) = 1 2 π σ e ( x μ ) 2 2 σ 2 {\displaystyle f(x)={\frac {1}{{\sqrt {2\pi }}\sigma }}e^{-{\frac {(x-\mu )^{2}}{2\sigma ^{2}}}}} then the expected shortfall is equal to ES α ( X ) = μ + σ φ ( Φ 1 ( α ) ) α {\displaystyle \operatorname {ES} _{\alpha }(X)=-\mu +\sigma {\frac {\varphi (\Phi ^{-1}(\alpha ))}{\alpha }}} , where φ ( x ) = 1 2 π e x 2 2 {\displaystyle \varphi (x)={\frac {1}{\sqrt {2\pi }}}e^{-{\frac {x^{2}}{2}}}} is the standard normal p.d.f., Φ ( x ) {\displaystyle \Phi (x)} is the standard normal c.d.f., so Φ 1 ( α ) {\displaystyle \Phi ^{-1}(\alpha )} is the standard normal quantile.

If the loss of a portfolio L {\displaystyle L} follows the normal distribution, the expected shortfall is equal to ES α ( L ) = μ + σ φ ( Φ 1 ( α ) ) 1 α {\displaystyle \operatorname {ES} _{\alpha }(L)=\mu +\sigma {\frac {\varphi (\Phi ^{-1}(\alpha ))}{1-\alpha }}} .

Generalized Student's t-distribution

If the payoff of a portfolio X {\displaystyle X} follows the generalized Student's t-distribution with p.d.f. f ( x ) = Γ ( ν + 1 2 ) Γ ( ν 2 ) π ν σ ( 1 + 1 ν ( x μ σ ) 2 ) ν + 1 2 {\displaystyle f(x)={\frac {\Gamma \left({\frac {\nu +1}{2}}\right)}{\Gamma \left({\frac {\nu }{2}}\right){\sqrt {\pi \nu }}\sigma }}\left(1+{\frac {1}{\nu }}\left({\frac {x-\mu }{\sigma }}\right)^{2}\right)^{-{\frac {\nu +1}{2}}}} then the expected shortfall is equal to ES α ( X ) = μ + σ ν + ( T 1 ( α ) ) 2 ν 1 τ ( T 1 ( α ) ) α {\displaystyle \operatorname {ES} _{\alpha }(X)=-\mu +\sigma {\frac {\nu +(\mathrm {T} ^{-1}(\alpha ))^{2}}{\nu -1}}{\frac {\tau (\mathrm {T} ^{-1}(\alpha ))}{\alpha }}} , where τ ( x ) = Γ ( ν + 1 2 ) Γ ( ν 2 ) π ν ( 1 + x 2 ν ) ν + 1 2 {\displaystyle \tau (x)={\frac {\Gamma {\bigl (}{\frac {\nu +1}{2}}{\bigr )}}{\Gamma {\bigl (}{\frac {\nu }{2}}{\bigr )}{\sqrt {\pi \nu }}}}{\Bigl (}1+{\frac {x^{2}}{\nu }}{\Bigr )}^{-{\frac {\nu +1}{2}}}} is the standard t-distribution p.d.f., T ( x ) {\displaystyle \mathrm {T} (x)} is the standard t-distribution c.d.f., so T 1 ( α ) {\displaystyle \mathrm {T} ^{-1}(\alpha )} is the standard t-distribution quantile.

If the loss of a portfolio L {\displaystyle L} follows generalized Student's t-distribution, the expected shortfall is equal to ES α ( L ) = μ + σ ν + ( T 1 ( α ) ) 2 ν 1 τ ( T 1 ( α ) ) 1 α {\displaystyle \operatorname {ES} _{\alpha }(L)=\mu +\sigma {\frac {\nu +(\mathrm {T} ^{-1}(\alpha ))^{2}}{\nu -1}}{\frac {\tau (\mathrm {T} ^{-1}(\alpha ))}{1-\alpha }}} .

Laplace distribution

If the payoff of a portfolio X {\displaystyle X} follows the Laplace distribution with the p.d.f.

f ( x ) = 1 2 b e | x μ | / b {\displaystyle f(x)={\frac {1}{2b}}e^{-|x-\mu |/b}}

and the c.d.f.

F ( x ) = { 1 1 2 e ( x μ ) / b if  x μ , 1 2 e ( x μ ) / b if  x < μ . {\displaystyle F(x)={\begin{cases}1-{\frac {1}{2}}e^{-(x-\mu )/b}&{\text{if }}x\geq \mu ,\\{\frac {1}{2}}e^{(x-\mu )/b}&{\text{if }}x<\mu .\end{cases}}}

then the expected shortfall is equal to ES α ( X ) = μ + b ( 1 ln 2 α ) {\displaystyle \operatorname {ES} _{\alpha }(X)=-\mu +b(1-\ln 2\alpha )} for α 0.5 {\displaystyle \alpha \leq 0.5} .

If the loss of a portfolio L {\displaystyle L} follows the Laplace distribution, the expected shortfall is equal to

ES α ( L ) = { μ + b α 1 α ( 1 ln 2 α ) if  α < 0.5 , μ + b [ 1 ln ( 2 ( 1 α ) ) ] if  α 0.5. {\displaystyle \operatorname {ES} _{\alpha }(L)={\begin{cases}\mu +b{\frac {\alpha }{1-\alpha }}(1-\ln 2\alpha )&{\text{if }}\alpha <0.5,\\\mu +b&{\text{if }}\alpha \geq 0.5.\end{cases}}}

Logistic distribution

If the payoff of a portfolio X {\displaystyle X} follows the logistic distribution with p.d.f. f ( x ) = 1 s e x μ s ( 1 + e x μ s ) 2 {\displaystyle f(x)={\frac {1}{s}}e^{-{\frac {x-\mu }{s}}}\left(1+e^{-{\frac {x-\mu }{s}}}\right)^{-2}} and the c.d.f. F ( x ) = ( 1 + e x μ s ) 1 {\displaystyle F(x)=\left(1+e^{-{\frac {x-\mu }{s}}}\right)^{-1}} then the expected shortfall is equal to ES α ( X ) = μ + s ln ( 1 α ) 1 1 α α {\displaystyle \operatorname {ES} _{\alpha }(X)=-\mu +s\ln {\frac {(1-\alpha )^{1-{\frac {1}{\alpha }}}}{\alpha }}} .

If the loss of a portfolio L {\displaystyle L} follows the logistic distribution, the expected shortfall is equal to ES α ( L ) = μ + s α ln α ( 1 α ) ln ( 1 α ) 1 α {\displaystyle \operatorname {ES} _{\alpha }(L)=\mu +s{\frac {-\alpha \ln \alpha -(1-\alpha )\ln(1-\alpha )}{1-\alpha }}} .

Exponential distribution

If the loss of a portfolio L {\displaystyle L} follows the exponential distribution with p.d.f. f ( x ) = { λ e λ x if  x 0 , 0 if  x < 0. {\displaystyle f(x)={\begin{cases}\lambda e^{-\lambda x}&{\text{if }}x\geq 0,\\0&{\text{if }}x<0.\end{cases}}} and the c.d.f. F ( x ) = { 1 e λ x if  x 0 , 0 if  x < 0. {\displaystyle F(x)={\begin{cases}1-e^{-\lambda x}&{\text{if }}x\geq 0,\\0&{\text{if }}x<0.\end{cases}}} then the expected shortfall is equal to ES α ( L ) = ln ( 1 α ) + 1 λ {\displaystyle \operatorname {ES} _{\alpha }(L)={\frac {-\ln(1-\alpha )+1}{\lambda }}} .

Pareto distribution

If the loss of a portfolio L {\displaystyle L} follows the Pareto distribution with p.d.f. f ( x ) = { a x m a x a + 1 if  x x m , 0 if  x < x m . {\displaystyle f(x)={\begin{cases}{\frac {ax_{m}^{a}}{x^{a+1}}}&{\text{if }}x\geq x_{m},\\0&{\text{if }}x<x_{m}.\end{cases}}} and the c.d.f. F ( x ) = { 1 ( x m / x ) a if  x x m , 0 if  x < x m . {\displaystyle F(x)={\begin{cases}1-(x_{m}/x)^{a}&{\text{if }}x\geq x_{m},\\0&{\text{if }}x<x_{m}.\end{cases}}} then the expected shortfall is equal to ES α ( L ) = x m a ( 1 α ) 1 / a ( a 1 ) {\displaystyle \operatorname {ES} _{\alpha }(L)={\frac {x_{m}a}{(1-\alpha )^{1/a}(a-1)}}} .

Generalized Pareto distribution (GPD)

If the loss of a portfolio L {\displaystyle L} follows the GPD with p.d.f.

f ( x ) = 1 s ( 1 + ξ ( x μ ) s ) ( 1 ξ 1 ) {\displaystyle f(x)={\frac {1}{s}}\left(1+{\frac {\xi (x-\mu )}{s}}\right)^{\left(-{\frac {1}{\xi }}-1\right)}}

and the c.d.f.

F ( x ) = { 1 ( 1 + ξ ( x μ ) s ) 1 / ξ if  ξ 0 , 1 exp ( x μ s ) if  ξ = 0. {\displaystyle F(x)={\begin{cases}1-\left(1+{\frac {\xi (x-\mu )}{s}}\right)^{-1/\xi }&{\text{if }}\xi \neq 0,\\1-\exp \left(-{\frac {x-\mu }{s}}\right)&{\text{if }}\xi =0.\end{cases}}}

then the expected shortfall is equal to

ES α ( L ) = { μ + s [ ( 1 α ) ξ 1 ξ + ( 1 α ) ξ 1 ξ ] if  ξ 0 , μ + s [ 1 ln ( 1 α ) ] if  ξ = 0 , {\displaystyle \operatorname {ES} _{\alpha }(L)={\begin{cases}\mu +s\left&{\text{if }}\xi \neq 0,\\\mu +s\left&{\text{if }}\xi =0,\end{cases}}}

and the VaR is equal to

VaR α ( L ) = { μ + s ( 1 α ) ξ 1 ξ if  ξ 0 , μ s ln ( 1 α ) if  ξ = 0. {\displaystyle \operatorname {VaR} _{\alpha }(L)={\begin{cases}\mu +s{\frac {(1-\alpha )^{-\xi }-1}{\xi }}&{\text{if }}\xi \neq 0,\\\mu -s\ln(1-\alpha )&{\text{if }}\xi =0.\end{cases}}}

Weibull distribution

If the loss of a portfolio L {\displaystyle L} follows the Weibull distribution with p.d.f. f ( x ) = { k λ ( x λ ) k 1 e ( x / λ ) k if  x 0 , 0 if  x < 0. {\displaystyle f(x)={\begin{cases}{\frac {k}{\lambda }}\left({\frac {x}{\lambda }}\right)^{k-1}e^{-(x/\lambda )^{k}}&{\text{if }}x\geq 0,\\0&{\text{if }}x<0.\end{cases}}} and the c.d.f. F ( x ) = { 1 e ( x / λ ) k if  x 0 , 0 if  x < 0. {\displaystyle F(x)={\begin{cases}1-e^{-(x/\lambda )^{k}}&{\text{if }}x\geq 0,\\0&{\text{if }}x<0.\end{cases}}} then the expected shortfall is equal to ES α ( L ) = λ 1 α Γ ( 1 + 1 k , ln ( 1 α ) ) {\displaystyle \operatorname {ES} _{\alpha }(L)={\frac {\lambda }{1-\alpha }}\Gamma \left(1+{\frac {1}{k}},-\ln(1-\alpha )\right)} , where Γ ( s , x ) {\displaystyle \Gamma (s,x)} is the upper incomplete gamma function.

Generalized extreme value distribution (GEV)

If the payoff of a portfolio X {\displaystyle X} follows the GEV with p.d.f. f ( x ) = { 1 σ ( 1 + ξ x μ σ ) 1 ξ 1 exp [ ( 1 + ξ x μ σ ) 1 / ξ ] if  ξ 0 , 1 σ e x μ σ e e x μ σ if  ξ = 0. {\displaystyle f(x)={\begin{cases}{\frac {1}{\sigma }}\left(1+\xi {\frac {x-\mu }{\sigma }}\right)^{-{\frac {1}{\xi }}-1}\exp \left&{\text{if }}\xi \neq 0,\\{\frac {1}{\sigma }}e^{-{\frac {x-\mu }{\sigma }}}e^{-e^{-{\frac {x-\mu }{\sigma }}}}&{\text{if }}\xi =0.\end{cases}}} and c.d.f. F ( x ) = { exp ( ( 1 + ξ x μ σ ) 1 / ξ ) if  ξ 0 , exp ( e x μ σ ) if  ξ = 0. {\displaystyle F(x)={\begin{cases}\exp \left(-\left(1+\xi {\frac {x-\mu }{\sigma }}\right)^{-{1}/{\xi }}\right)&{\text{if }}\xi \neq 0,\\\exp \left(-e^{-{\frac {x-\mu }{\sigma }}}\right)&{\text{if }}\xi =0.\end{cases}}} then the expected shortfall is equal to ES α ( X ) = { μ σ α ξ [ Γ ( 1 ξ , ln α ) α ] if  ξ 0 , μ σ α [ li ( α ) α ln ( ln α ) ] if  ξ = 0. {\displaystyle \operatorname {ES} _{\alpha }(X)={\begin{cases}-\mu -{\frac {\sigma }{\alpha \xi }}{\big }&{\text{if }}\xi \neq 0,\\-\mu -{\frac {\sigma }{\alpha }}{\big }&{\text{if }}\xi =0.\end{cases}}} and the VaR is equal to VaR α ( X ) = { μ σ ξ [ ( ln α ) ξ 1 ] if  ξ 0 , μ + σ ln ( ln α ) if  ξ = 0. {\displaystyle \operatorname {VaR} _{\alpha }(X)={\begin{cases}-\mu -{\frac {\sigma }{\xi }}\left&{\text{if }}\xi \neq 0,\\-\mu +\sigma \ln(-\ln \alpha )&{\text{if }}\xi =0.\end{cases}}} , where Γ ( s , x ) {\displaystyle \Gamma (s,x)} is the upper incomplete gamma function, l i ( x ) = d x ln x {\displaystyle \mathrm {li} (x)=\int {\frac {dx}{\ln x}}} is the logarithmic integral function.

If the loss of a portfolio L {\displaystyle L} follows the GEV, then the expected shortfall is equal to ES α ( X ) = { μ + σ ( 1 α ) ξ [ γ ( 1 ξ , ln α ) ( 1 α ) ] if  ξ 0 , μ + σ 1 α [ y li ( α ) + α ln ( ln α ) ] if  ξ = 0. {\displaystyle \operatorname {ES} _{\alpha }(X)={\begin{cases}\mu +{\frac {\sigma }{(1-\alpha )\xi }}{\bigl }&{\text{if }}\xi \neq 0,\\\mu +{\frac {\sigma }{1-\alpha }}{\bigl }&{\text{if }}\xi =0.\end{cases}}} , where γ ( s , x ) {\displaystyle \gamma (s,x)} is the lower incomplete gamma function, y {\displaystyle y} is the Euler-Mascheroni constant.

Generalized hyperbolic secant (GHS) distribution

If the payoff of a portfolio X {\displaystyle X} follows the GHS distribution with p.d.f. f ( x ) = 1 2 σ sech ( π 2 x μ σ ) {\displaystyle f(x)={\frac {1}{2\sigma }}\operatorname {sech} \left({\frac {\pi }{2}}{\frac {x-\mu }{\sigma }}\right)} and the c.d.f. F ( x ) = 2 π arctan [ exp ( π 2 x μ σ ) ] {\displaystyle F(x)={\frac {2}{\pi }}\arctan \left} then the expected shortfall is equal to ES α ( X ) = μ 2 σ π ln ( tan π α 2 ) 2 σ π 2 α i [ Li 2 ( i tan π α 2 ) Li 2 ( i tan π α 2 ) ] {\displaystyle \operatorname {ES} _{\alpha }(X)=-\mu -{\frac {2\sigma }{\pi }}\ln \left(\tan {\frac {\pi \alpha }{2}}\right)-{\frac {2\sigma }{\pi ^{2}\alpha }}i\left} , where Li 2 {\displaystyle \operatorname {Li} _{2}} is the dilogarithm and i = 1 {\displaystyle i={\sqrt {-1}}} is the imaginary unit.

Johnson's SU-distribution

If the payoff of a portfolio X {\displaystyle X} follows Johnson's SU-distribution with the c.d.f. F ( x ) = Φ [ γ + δ sinh 1 ( x ξ λ ) ] {\displaystyle F(x)=\Phi \left} then the expected shortfall is equal to ES α ( X ) = ξ λ 2 α [ exp ( 1 2 γ δ 2 δ 2 ) Φ ( Φ 1 ( α ) 1 δ ) exp ( 1 + 2 γ δ 2 δ 2 ) Φ ( Φ 1 ( α ) + 1 δ ) ] {\displaystyle \operatorname {ES} _{\alpha }(X)=-\xi -{\frac {\lambda }{2\alpha }}\left} , where Φ {\displaystyle \Phi } is the c.d.f. of the standard normal distribution.

Burr type XII distribution

If the payoff of a portfolio X {\displaystyle X} follows the Burr type XII distribution the p.d.f. f ( x ) = c k β ( x γ β ) c 1 [ 1 + ( x γ β ) c ] k 1 {\displaystyle f(x)={\frac {ck}{\beta }}\left({\frac {x-\gamma }{\beta }}\right)^{c-1}\left^{-k-1}} and the c.d.f. F ( x ) = 1 [ 1 + ( x γ β ) c ] k {\displaystyle F(x)=1-\left^{-k}} , the expected shortfall is equal to ES α ( X ) = γ β α ( ( 1 α ) 1 / k 1 ) 1 / c [ α 1 + 2 F 1 ( 1 c , k ; 1 + 1 c ; 1 ( 1 α ) 1 / k ) ] {\displaystyle \operatorname {ES} _{\alpha }(X)=-\gamma -{\frac {\beta }{\alpha }}\left((1-\alpha )^{-1/k}-1\right)^{1/c}\left} , where 2 F 1 {\displaystyle _{2}F_{1}} is the hypergeometric function. Alternatively, ES α ( X ) = γ β α c k c + 1 ( ( 1 α ) 1 / k 1 ) 1 + 1 c 2 F 1 ( 1 + 1 c , k + 1 ; 2 + 1 c ; 1 ( 1 α ) 1 / k ) {\displaystyle \operatorname {ES} _{\alpha }(X)=-\gamma -{\frac {\beta }{\alpha }}{\frac {ck}{c+1}}\left((1-\alpha )^{-1/k}-1\right)^{1+{\frac {1}{c}}}{_{2}F_{1}}\left(1+{\frac {1}{c}},k+1;2+{\frac {1}{c}};1-(1-\alpha )^{-1/k}\right)} .

Dagum distribution

If the payoff of a portfolio X {\displaystyle X} follows the Dagum distribution with p.d.f. f ( x ) = c k β ( x γ β ) c k 1 [ 1 + ( x γ β ) c ] k 1 {\displaystyle f(x)={\frac {ck}{\beta }}\left({\frac {x-\gamma }{\beta }}\right)^{ck-1}\left^{-k-1}} and the c.d.f. F ( x ) = [ 1 + ( x γ β ) c ] k {\displaystyle F(x)=\left^{-k}} , the expected shortfall is equal to ES α ( X ) = γ β α c k c k + 1 ( α 1 / k 1 ) k 1 c 2 F 1 ( k + 1 , k + 1 c ; k + 1 + 1 c ; 1 α 1 / k 1 ) {\displaystyle \operatorname {ES} _{\alpha }(X)=-\gamma -{\frac {\beta }{\alpha }}{\frac {ck}{ck+1}}\left(\alpha ^{-1/k}-1\right)^{-k-{\frac {1}{c}}}{_{2}F_{1}}\left(k+1,k+{\frac {1}{c}};k+1+{\frac {1}{c}};-{\frac {1}{\alpha ^{-1/k}-1}}\right)} , where 2 F 1 {\displaystyle _{2}F_{1}} is the hypergeometric function.

Lognormal distribution

If the payoff of a portfolio X {\displaystyle X} follows lognormal distribution, i.e. the random variable ln ( 1 + X ) {\displaystyle \ln(1+X)} follows the normal distribution with p.d.f. f ( x ) = 1 2 π σ e ( x μ ) 2 2 σ 2 {\displaystyle f(x)={\frac {1}{{\sqrt {2\pi }}\sigma }}e^{-{\frac {(x-\mu )^{2}}{2\sigma ^{2}}}}} , then the expected shortfall is equal to ES α ( X ) = 1 exp ( μ + σ 2 2 ) Φ ( Φ 1 ( α ) σ ) α {\displaystyle \operatorname {ES} _{\alpha }(X)=1-\exp \left(\mu +{\frac {\sigma ^{2}}{2}}\right){\frac {\Phi \left(\Phi ^{-1}(\alpha )-\sigma \right)}{\alpha }}} , where Φ ( x ) {\displaystyle \Phi (x)} is the standard normal c.d.f., so Φ 1 ( α ) {\displaystyle \Phi ^{-1}(\alpha )} is the standard normal quantile.

Log-logistic distribution

If the payoff of a portfolio X {\displaystyle X} follows log-logistic distribution, i.e. the random variable ln ( 1 + X ) {\displaystyle \ln(1+X)} follows the logistic distribution with p.d.f. f ( x ) = 1 s e x μ s ( 1 + e x μ s ) 2 {\displaystyle f(x)={\frac {1}{s}}e^{-{\frac {x-\mu }{s}}}\left(1+e^{-{\frac {x-\mu }{s}}}\right)^{-2}} , then the expected shortfall is equal to ES α ( X ) = 1 e μ α I α ( 1 + s , 1 s ) π s sin π s {\displaystyle \operatorname {ES} _{\alpha }(X)=1-{\frac {e^{\mu }}{\alpha }}I_{\alpha }(1+s,1-s){\frac {\pi s}{\sin \pi s}}} , where I α {\displaystyle I_{\alpha }} is the regularized incomplete beta function, I α ( a , b ) = B α ( a , b ) B ( a , b ) {\displaystyle I_{\alpha }(a,b)={\frac {\mathrm {B} _{\alpha }(a,b)}{\mathrm {B} (a,b)}}} .

As the incomplete beta function is defined only for positive arguments, for a more generic case the expected shortfall can be expressed with the hypergeometric function: ES α ( X ) = 1 e μ α s s + 1 2 F 1 ( s , s + 1 ; s + 2 ; α ) {\displaystyle \operatorname {ES} _{\alpha }(X)=1-{\frac {e^{\mu }\alpha ^{s}}{s+1}}{_{2}F_{1}}(s,s+1;s+2;\alpha )} .

If the loss of a portfolio L {\displaystyle L} follows log-logistic distribution with p.d.f. f ( x ) = b a ( x / a ) b 1 ( 1 + ( x / a ) b ) 2 {\displaystyle f(x)={\frac {{\frac {b}{a}}(x/a)^{b-1}}{(1+(x/a)^{b})^{2}}}} and c.d.f. F ( x ) = 1 1 + ( x / a ) b {\displaystyle F(x)={\frac {1}{1+(x/a)^{-b}}}} , then the expected shortfall is equal to ES α ( L ) = a 1 α [ π b csc ( π b ) B α ( 1 b + 1 , 1 1 b ) ] {\displaystyle \operatorname {ES} _{\alpha }(L)={\frac {a}{1-\alpha }}\left} , where B α {\displaystyle B_{\alpha }} is the incomplete beta function.

Log-Laplace distribution

If the payoff of a portfolio X {\displaystyle X} follows log-Laplace distribution, i.e. the random variable ln ( 1 + X ) {\displaystyle \ln(1+X)} follows the Laplace distribution the p.d.f. f ( x ) = 1 2 b e | x μ | b {\displaystyle f(x)={\frac {1}{2b}}e^{-{\frac {|x-\mu |}{b}}}} , then the expected shortfall is equal to

ES α ( X ) = { 1 e μ ( 2 α ) b b + 1 if  α 0.5 , 1 e μ 2 b α ( b 1 ) [ ( 1 α ) ( 1 b ) 1 ] if  α > 0.5. {\displaystyle \operatorname {ES} _{\alpha }(X)={\begin{cases}1-{\frac {e^{\mu }(2\alpha )^{b}}{b+1}}&{\text{if }}\alpha \leq 0.5,\\1-{\frac {e^{\mu }2^{-b}}{\alpha (b-1)}}\left&{\text{if }}\alpha >0.5.\end{cases}}}

Log-generalized hyperbolic secant (log-GHS) distribution

If the payoff of a portfolio X {\displaystyle X} follows log-GHS distribution, i.e. the random variable ln ( 1 + X ) {\displaystyle \ln(1+X)} follows the GHS distribution with p.d.f. f ( x ) = 1 2 σ sech ( π 2 x μ σ ) {\displaystyle f(x)={\frac {1}{2\sigma }}\operatorname {sech} \left({\frac {\pi }{2}}{\frac {x-\mu }{\sigma }}\right)} , then the expected shortfall is equal to

ES α ( X ) = 1 1 α ( σ + π / 2 ) ( tan π α 2 exp π μ 2 σ ) 2 σ / π tan π α 2 2 F 1 ( 1 , 1 2 + σ π ; 3 2 + σ π ; tan ( π α 2 ) 2 ) , {\displaystyle \operatorname {ES} _{\alpha }(X)=1-{\frac {1}{\alpha (\sigma +{\pi /2})}}\left(\tan {\frac {\pi \alpha }{2}}\exp {\frac {\pi \mu }{2\sigma }}\right)^{2\sigma /\pi }\tan {\frac {\pi \alpha }{2}}{_{2}F_{1}}\left(1,{\frac {1}{2}}+{\frac {\sigma }{\pi }};{\frac {3}{2}}+{\frac {\sigma }{\pi }};-\tan \left({\frac {\pi \alpha }{2}}\right)^{2}\right),}

where 2 F 1 {\displaystyle _{2}F_{1}} is the hypergeometric function.

Dynamic expected shortfall

The conditional version of the expected shortfall at the time t is defined by

ES α t ( X ) = e s s sup Q Q α t E Q [ X F t ] {\displaystyle \operatorname {ES} _{\alpha }^{t}(X)=\operatorname {ess\sup } _{Q\in {\mathcal {Q}}_{\alpha }^{t}}E^{Q}}

where Q α t = { Q = P | F t : d Q d P α t 1  a.s. } {\displaystyle {\mathcal {Q}}_{\alpha }^{t}=\left\{Q=P\,\vert _{{\mathcal {F}}_{t}}:{\frac {dQ}{dP}}\leq \alpha _{t}^{-1}{\text{ a.s.}}\right\}} .

This is not a time-consistent risk measure. The time-consistent version is given by

ρ α t ( X ) = e s s sup Q Q ~ α t E Q [ X F t ] {\displaystyle \rho _{\alpha }^{t}(X)=\operatorname {ess\sup } _{Q\in {\tilde {\mathcal {Q}}}_{\alpha }^{t}}E^{Q}}

such that

Q ~ α t = { Q P : E [ d Q d P F τ + 1 ] α t 1 E [ d Q d P F τ ] τ t  a.s. } . {\displaystyle {\tilde {\mathcal {Q}}}_{\alpha }^{t}=\left\{Q\ll P:\operatorname {E} \left\leq \alpha _{t}^{-1}\operatorname {E} \left\;\forall \tau \geq t{\text{ a.s.}}\right\}.}

See also

Methods of statistical estimation of VaR and ES can be found in Embrechts et al. and Novak. When forecasting VaR and ES, or optimizing portfolios to minimize tail risk, it is important to account for asymmetric dependence and non-normalities in the distribution of stock returns such as auto-regression, asymmetric volatility, skewness, and kurtosis.

References

  1. Rockafellar, R. Tyrrell; Uryasev, Stanislav (2000). "Optimization of conditional value-at-risk" (PDF). Journal of Risk. 2 (3): 21–42. doi:10.21314/JOR.2000.038. S2CID 854622.
  2. Rockafellar, R. Tyrrell; Royset, Johannes (2010). "On Buffered Failure Probability in Design and Optimization of Structures" (PDF). Reliability Engineering and System Safety. 95 (5): 499–510. doi:10.1016/j.ress.2010.01.001. S2CID 1653873.
  3. Carlo Acerbi; Dirk Tasche (2002). "Expected Shortfall: a natural coherent alternative to Value at Risk" (PDF). Economic Notes. 31 (2): 379–388. arXiv:cond-mat/0105191. doi:10.1111/1468-0300.00091. S2CID 10772757. Retrieved April 25, 2012.
  4. Föllmer, H.; Schied, A. (2008). "Convex and coherent risk measures" (PDF). Retrieved October 4, 2011. {{cite journal}}: Cite journal requires |journal= (help)
  5. Patrick Cheridito; Tianhui Li (2008). "Dual characterization of properties of risk measures on Orlicz hearts". Mathematics and Financial Economics. 2: 2–29. doi:10.1007/s11579-008-0013-7. S2CID 121880657.
  6. "Average Value at Risk" (PDF). Archived from the original (PDF) on July 19, 2011. Retrieved February 2, 2011.
  7. Julia L. Wirch; Mary R. Hardy. "Distortion Risk Measures: Coherence and Stochastic Dominance" (PDF). Archived from the original (PDF) on July 5, 2016. Retrieved March 10, 2012.
  8. Balbás, A.; Garrido, J.; Mayoral, S. (2008). "Properties of Distortion Risk Measures" (PDF). Methodology and Computing in Applied Probability. 11 (3): 385. doi:10.1007/s11009-008-9089-z. hdl:10016/14071. S2CID 53327887.
  9. Rockafellar, R. Tyrrell; Uryasev, Stanislav (2000). "Optimization of conditional value-at-risk" (PDF). Journal of Risk. 2 (3): 21–42. doi:10.21314/JOR.2000.038. S2CID 854622.
  10. ^ Khokhlov, Valentyn (2016). "Conditional Value-at-Risk for Elliptical Distributions". Evropský časopis Ekonomiky a Managementu. 2 (6): 70–79.
  11. ^ Norton, Matthew; Khokhlov, Valentyn; Uryasev, Stan (2018-11-27). "Calculating CVaR and bPOE for Common Probability Distributions With Application to Portfolio Optimization and Density Estimation". arXiv:1811.11301 .
  12. ^ Khokhlov, Valentyn (2018-06-21). "Conditional Value-at-Risk for Uncommon Distributions". doi:10.2139/ssrn.3200629. S2CID 219371851. SSRN 3200629. {{cite journal}}: Cite journal requires |journal= (help)
  13. Stucchi, Patrizia (2011-05-31). "Moment-Based CVaR Estimation: Quasi-Closed Formulas". doi:10.2139/ssrn.1855986. S2CID 124145569. SSRN 1855986. {{cite journal}}: Cite journal requires |journal= (help)
  14. ^ Khokhlov, Valentyn (2018-06-17). "Conditional Value-at-Risk for Log-Distributions". SSRN 3197929.
  15. Detlefsen, Kai; Scandolo, Giacomo (2005). "Conditional and dynamic convex risk measures" (PDF). Finance Stoch. 9 (4): 539–561. CiteSeerX 10.1.1.453.4944. doi:10.1007/s00780-005-0159-6. S2CID 10579202. Retrieved October 11, 2011.
  16. Acciaio, Beatrice; Penner, Irina (2011). "Dynamic convex risk measures" (PDF). Archived from the original (PDF) on September 2, 2011. Retrieved October 11, 2011. {{cite journal}}: Cite journal requires |journal= (help)
  17. Cheridito, Patrick; Kupper, Michael (May 2010). "Composition of time-consistent dynamic monetary risk measures in discrete time" (PDF). International Journal of Theoretical and Applied Finance. Archived from the original (PDF) on July 19, 2011. Retrieved February 4, 2011.
  18. Embrechts P., Kluppelberg C. and Mikosch T., Modelling Extremal Events for Insurance and Finance. Springer (1997).
  19. Novak S.Y., Extreme value methods with applications to finance. Chapman & Hall/CRC Press (2011). ISBN 978-1-4398-3574-6.
  20. Low, R.K.Y.; Alcock, J.; Faff, R.; Brailsford, T. (2013). "Canonical vine copulas in the context of modern portfolio management: Are they worth it?" (PDF). Journal of Banking & Finance. 37 (8): 3085–3099. doi:10.1016/j.jbankfin.2013.02.036. S2CID 154138333.

External links

Categories: