Journal of

Risk and Financial

Management

Article
Portfolio Optimization on Multivariate Regime-Switching
GARCH Model with Normal Tempered Stable Innovation
Cheng Peng 1 , Young Shin Kim 2, * and Stefan Mittnik 3

1 Department of Applied Mathematics and Statistics, College of Engineering and Applied Sciences, Stony
Brook University, Stony Brook, NY 11794, USA; [email protected]
2 College of Business, Stony Brook University, Stony Brook, NY 11794, USA
3 Chair of Financial Econometrics, Institute of Statistics, Ludwig Maximilian University Munich,
Akademiestr. 1/I, 80799 Munich, Germany; [email protected]
* Correspondence: [email protected]

Abstract: This paper uses simulation-based portfolio optimization to mitigate the left tail risk of
the portfolio. The contribution is twofold. (i) We propose the Markov regime-switching GARCH
model with multivariate normal tempered stable innovation (MRS-MNTS-GARCH) to accommodate
fat tails, volatility clustering and regime switch. The volatility of each asset independently follows
the regime-switch GARCH model, while the correlation of joint innovation of the GARCH models
follows the Hidden Markov Model. (ii) We use tail risk measures, namely conditional value-at-risk
(CVaR) and conditional drawdown-at-risk (CDaR), in the portfolio optimization. The optimization
is performed with the sample paths simulated by the MRS-MNTS-GARCH model. We conduct an
empirical study on the performance of optimal portfolios. Out-of-sample tests show that the optimal
portfolios with tail measures outperform the optimal portfolio with standard deviation measure and
Citation: Peng, Cheng, Young Shin the equally weighted portfolio in various performance measures. The out-of-sample performance of
Kim, and Stefan Mittnik. 2022. the optimal portfolios is also more robust to suboptimality on the efficient frontier.
Portfolio Optimization on
Multivariate Regime-Switching Keywords: Markov regime-switching model; GARCH model; normal tempered stable distribution;
GARCH Model with Normal portfolio optimization; conditional drawdown-at-risk; conditional value-at-risk
Tempered Stable Innovation. Journal
of Risk and Financial Management 15:
230. https://doi.org/10.3390/
jrfm15050230 1. Introduction
Academic Editor: Zbigniew Empirical studies have found in the return of various financial instruments skewness
Palmowski and leptokurtotic—asymmetry, and higher peak around the mean with fat tails. Normal
Received: 14 April 2022
distribution has long been recognized as insufficient to accommodate these stylized facts,
Accepted: 12 May 2022
relying on which could drastically underestimate the tail risk of a portfolio. The α-stable
Published: 23 May 2022
distribution is a candidate to incorporate this fact into decision-making, but its lack of finite
moments could cause difficulties in modeling. The class of tempered stable distributions
Publisher’s Note: MDPI stays neutral
serves as a natural substitution, since it has finite moments while retaining many attractive
with regard to jurisdictional claims in
properties of the α-stable distribution. The class of tempered stable distributions is derived
published maps and institutional affil-
by tempering the tails of the α-stable distribution (See Koponen 1995; Boyarchenko and
iations.
Levendorskiĭ 2000; and Carr et al. 2002), or from the time changed Brownian motion.
Since Barndorff-Nielsen and Levendorskii (2001) and Shephard et al. (2001) presented the
normal tempered stable (NTS) distribution in finance using the time changed Brownian
Copyright: © 2022 by the authors.
motion, it has been successfully applied for modeling the stock returns with high accuracy
Licensee MDPI, Basel, Switzerland. in literature including Kim et al. (2012), Kurosaki and Kim (2018), Anand et al. (2016) and
This article is an open access article Kim (2022).
distributed under the terms and Deviation from normality exists not only in raw returns, but also in filtered innovations
conditions of the Creative Commons of time series models. Since the foundational work in Engle (1982) and Bollerslev (1986),
Attribution (CC BY) license (https:// GARCH model has been widely applied to model volatility. This motivates us to use
creativecommons.org/licenses/by/ NTS distribution to accommodate the asymmetry, interdependence, and fat tails of the
4.0/). innovations of GARCH models. Several studies have found NTS distribution to be more

J. Risk Financial Manag. 2022, 15, 230. https://doi.org/10.3390/jrfm15050230 https://www.mdpi.com/journal/jrfm

J. Risk Financial Manag. 2022, 15, 230 2 of 23

favorable than other candidates. Kim et al. (2011) found that normal and t-distribution are
rejected as innovation of GARCH model in hypothesis testing. Shi and Feng (2016) found
that tempered stable distribution with exponential tempering yields better calibration of
Markov Regime-Switching (MRS) GARCH model than t or generalized error distribution.
Generalized hyperbolic distribution, while very flexible, has too many parameters for
estimation. NTS distribution has only three standardized parameters and is flexible enough
to serve the purpose.
A drawback of GARCH model is the inadequate ability in modeling volatility spikes,
which could indicate that the market is switching within regimes. Various types of MRS-
GARCH models have been proposed, many of which suggest that the regime-switching
GARCH model achieves a better fit for empirical data (for example, in Hamilton 1996).
Marcucci (2005) finds that MRS-GARCH models outperform standard GARCH models
in volatility forecasting in a time horizon shorter than one week. Naturally, the most
flexible model allows all parameters to switch among regimes. However, as is shown in
Henneke et al. (2011), the sampling procedure in the MCMC method for estimating such
a model is time-consuming and renders it improper for practical use. We construct a
new model based on the regime-switching GARCH model specified in Haas et al. (2004),
which circumvents the path dependence problem in the Markov Chain model by specifying
parallel GARCH models.
Bollerslev (1990) proposes the GARCH model with constant conditional correlation.
The parsimonious DCC-GARCH model in Engle (2002) opens the door to modeling multi-
variate GARCH process with different persistence between variance and correlation. While
flexible models allowing time-varying correlation are preferred in many cases, specification
of multivariate GARCH models with both regime-specific correlations and variance dy-
namics involves a balance between flexibility and tractability. The univariate MRS-GARCH
model in Haas et al. (2004) is generalized in Haas and Liu (2004) to a multivariate case.
Unfortunately, it suffers from the curse of dimensionality, and thus is unsuitable for a
high dimensional empirical study. In our model, we decompose variance and correlation
so that the variance of each asset evolves independently according to a univariate MRS-
GARCH model. The correlation is incorporated in the innovations modeled by a flexible
Hidden Markov Model (HMM) that has multivariate NTS distribution as the conditional
distribution in each regime. We will use the calibrated model to simulate returns for
portfolio optimizations.
Modern portfolio theory is formulated as a trade-off between return and risk. The
classical Markowitz Model finds the portfolio with the highest Sharpe ratio. However,
variance has been criticized for not containing enough information on the tail of the
distribution. Moreover, correlation is not sufficient to describe the interdependence of asset
returns with non-elliptical distribution. Current regulations for financial business utilize the
concept of Value at Risk (VaR), which is the percentile of the loss distribution, to model the
risk of left tail events. There are several undesired properties that rendered it an insufficient
criterion. First, it is not a coherent risk measure due to a lack of sub-additivity. Second,
VaR is a non-convex and non-smooth function of positions with multiple local extrema
for non-normal distributions, which causes difficulty in developing efficient optimization
techniques. Third, a single percentile is insufficient to describe the tail behavior of a
distribution, and thus might lead to an underestimation of risk.
Theory and algorithm for portfolio optimization with a conditional value-at-risk
(CVaR) measure proposed in Krokhmal et al. (2001) and Rockafellar and Uryasev (2000)
effectively addresses these problems. For continuous distributions, CVaR is defined by a
conditional expectation of losses exceeding a certain VaR level. For discrete distributions,
CVaR is defined by a weighted average of some VaR levels that exceed a specified VaR
level. In this way, CVaR concerns both VaR and the losses exceeding VaR. As a convex
function of asset allocation, a coherent risk measure and a more informative statistic, CVaR
serves as an ideal alternative to VaR. A study on the comparison of the two measures can
be found in Sarykalin et al. (2014).
J. Risk Financial Manag. 2022, 15, 230 3 of 23

Another closely related tail risk measure is conditional drawdown-at-risk (CDaR).

Drawdown has been a constant concern for investors and is often used in the performance
evaluation of a portfolio. It is much more difficult to climb out of a drawdown than drop
into one, considering that it takes 100% return to recover from 50% relative drawdown.
In behavioral finance, it is well documented that investors fear losses more than they
value gains. However, the commonly used maximum drawdown only considers the worst
scenario that only occur under some very special circumstances, and thus is very sensitive
to the testing period and asset allocation. On the other hand, small drawdowns included in
the calculation of average drawdown are acceptable and might be caused by pure noise, of
which the minimization might result in overfitting. For instance, a Brownian motion would
have drawdowns in a simulated sample path.
CDaR is proposed in Checkhlov et al. (2004) to address these concerns. While CVaR
is determined by the distribution of return, CDaR is path-dependent. CDaR is essentially
CVaR of the distribution of drawdowns. By this, we overcome the drawbacks of average
drawdown and maximum drawdown. CDaR takes not only the depth of drawdowns into
consideration, but also the length of them. Since the CDaR risk measure is the application
of CVaR in a dynamic case, it naturally holds nice properties of CVaR, such as convexity
with respect to asset allocation. The optimization method with constraints on CDaR has
also been developed and studied in Checkhlov et al. (2004, 2005).
An optimization procedure could lead to an underperformed portfolio by magnify-
ing the estimation error. Using historical sample paths as input implies an assumption
that what happened in the past will happen in the future, which requires careful exam-
ination. It is found in Lim et al. (2011) that estimation errors of CVaR and the mean is
large, resulting in unreliable allocation. An alternative way is to use multiple simulated
returns. It is reasonable to expect outperformance during a crisis if we use the simula-
tion of a model that captures extreme tail events as input for optimization with tail risk
measures. Relevant research that resorts to copula does not address a regime switch (See
Sahamkhadam et al. 2018).
We have identified several issues in GARCH-simulation-based portfolio optimiza-
tion: deviation from normality, regime switch, high dimensional calibration and tail risk
measures. This paper intends to address these issues in one shot. First, we propose the
MRS-MNTS-GARCH model to accommodate fat tails, volatility clustering and regime
switch. In the model, the volatility of each asset independently follows a regime-switch
GARCH model, while the correlation of joint innovation of GARCH models follows a
Hidden Markov Model. We specify the method for efficient model calibration. The MRS-
MNTS-GARCH model is used to simulate sample paths. Then, the sample paths are used
as input to portfolio optimization with tail risk measures CVaR and CDaR. We conduct
in-sample tests sow show the goodness-of-fit. We conduct out-of-sample tests to show
the outperformance of our approach in various measures. The optimal portfolios are also
more robust to suboptimality of the optimization. The results suggest that, in practice,
performance ratios can be improved compared to equally weighted portfolio by adopting
simulation-based portfolio optimization with the MRS-MNTS-GARCH model. The empiri-
cal study suggests that using tail risk measures outperforms using standard deviation in
terms of various performance measures and robustness.
The remainder of the paper is organized as follows. Section 2 introduces the prelimi-
naries on NTS distribution and GARCH model. Section 3 specifies our model and methods
for estimation and simulation. Section 4 introduces the portfolio optimization with tail risk
measures. Section 5 is an empirical study on in-sample goodness-of-fit and out-of-sample
performance in recent years.

2. Preliminaries
This section reviews the background knowledge on different risk measures, scenario-
based estimation, normal tempered stable (NTS) distribution, and GARCH and regime-
switching GARCH model.
J. Risk Financial Manag. 2022, 15, 230 4 of 23

2.1. Tail Risk Measures

In this subsection, we discuss and summarize popular tail risk measures in finance
such as Value at Risk (VaR), Conditional VaR (CVaR), and conditional drawdown-at-
risk (CDaR). Definitions of CDaR, and related properties of drawdown are following
Checkhlov et al. (2004, 2005).
Consider a probability space (Ω, F∞ , P) and a portfolio with N assets. Suppose that
Pn is a stochastic process of a price for the n-th asset in the portfolio on the space

Pn : [0, ∞) × Ω −→ R, n = 1, 2, · · · , N

with the real initial value Pn (0, ·) = Pn,0 > 0.

The stochastic process of the compounded return of the n-th asset between time 0 to
time t > 0 is defined by

Pn (t, ω ) − Pn,0
Rn (t, ω ) = , t > 0,
Pn,0

with Rn (0, ·) = 0. Then, the compounded portfolio return R( x, t, ω ) at time t > 0 is

equal to
N
R( x, t, ω ) = ∑ xn Rn (t, ω ).
n =1

The definition of VaR for R( x, t, ·) with the confidence level η is

VaRη (R( x, t, ·)) = min{z|P(R( x, t, ·) ≤ −z) ≥ η }.

If R( x, t, ·) has a continuous cumulative distribution, then we have

−1
VaRη (R( x, t, ·)) = F−R( x,t,·)
(1 − η ),

−1
where F−R( x,t,·)
is the inverse cumulative distribution function of −R( x, t, ·). The definition
of CVaR for R( x, t, ·) with the confidence level η is
Z 1
1
CVaRη (R( x, t, ·)) = VaRz (R( x, t, ·))dz.
1−η η

Equivalently, CVaR can be obtained by a minimization formula

 
1
CVaRη (R( x, t, ·)) = min θ + E[max{0, −R( x, t, ·) − θ }] . (1)
θ η

Following Checkhlov et al. (2004), denote the uncompounded return of the n-th asset
by Qn (t, w). The uncompounded portfolio return is defined by

N
Q( x, t, ω ) = ∑ xn Qn (t, ω ).
n =1

Let T > 0, and ω ∈ Ω, then ( R( x, t, ω ))t∈[0,T ] = { R( x, t, ω )|t ∈ [0, T ]} is one sample

path of portfolio return with the capital allocation vector x from time 0 to T. The drawdown
(DD(·, ω ))t∈[0,T ] of the portfolio return is defined by

DD(t, ω ) = max Q( x, s, ω ) − Q( x, t, ω ), for t ∈ [0, T ] (2)

s∈[0,t]
J. Risk Financial Manag. 2022, 15, 230 5 of 23

is a risk measure assessing the decline from a historical peak in some variable, and
{DD(t, ω )|t ∈ [0, T ], ω ∈ Ω} is a stochastic process of the drawdown. The average
drawdown (ADD) up to time T for ω ∈ Ω is defined by
Z T
1
ADD( T, ω ) = DD(t, ω )dt. (3)
T 0

It is the time average of drawdowns observed between time 0 to T. The maximum

drawdown (ADD) up to time T for ω ∈ Ω is defined by

MDD( T, ω ) = max DD(t, ω ). (4)

t∈(0,T )

It is the maximum of drawdowns that have occurred up to time T for ω ∈ Ω.

Let
1 T
Z
FDD (z, ω ) = 1 dt (5)
T 0 DD(t,ω )≤z
and (
inf{z| FDD (z, ω ) ≥ η } if η ∈ (0, 1]
ζ η (ω ) = . (6)
0 if η = 0
According to Checkhlov et al. (2005), the CDaR is defined as the CVaR of drawdowns.
Applying (1) to drawdowns, we have
 Z T 
1
CDaRη ( T, ω ) = min ζ + max{DD(t, ω ) − ζ, 0}dt .
ζ ηT 0

It can also be represented as

CDaRη ( T, ω )
FDD (ζ η (ω ), ω ) − η Z T
 
1
= ζ η (ω ) + DD(t, ω )1DD(t,ω )>ζ η (ω ) dt. (7)
1−η (1 − η ) T 0

Note that CDaR0 ( T, ω ) = ADDω ( T ) and CDaR1 ( T, ω ) = MDDω ( T ).

Let Z T 
1
FDD (z) = E 1DD(t,·)≤z dt (8)
T 0

and (
−1 inf{z| FDD (z) ≥ η } if η ∈ (0, 1]
ζη = FDD (η ) = . (9)
0 if η = 0
Considering all the sample path {R( x, t, ω )|t ∈ [0, T ], ω ∈ Ω}, we define CDaR at
η by

CDaRη ( T )
Z T
FDD (ζ (η )) − η
  
1
= ζ (η ) + E DD(t, ·)1DD(t,·)>ζ (η ) dt . (10)
1−η (1 − η ) T 0

2.2. Scenario-Based Estimation

In this subsection, we discuss the risk estimation using given scenarios (historical
scenario or simulation). Suppose that the time interval [0, T ] is divided by a partition
{0 = t0 < t1 < · · · < t M = T }, and denote

Rm ( x ) = R( x, tm , ·).
J. Risk Financial Manag. 2022, 15, 230 6 of 23

We select ωs ∈ Ω where s ∈ {1, 2, · · · , S} and S is the number of scenarios. Then, we

obtain scenarios of the portfolio return process R at time tm :

Rsm ( x ) = R( x, tm , ωs )

where m ∈ {0, 1, 2, · · · , M }, and s ∈ {1, 2, · · · , S}. We calculate VaR, CVaR, DD, and
CDaR under the simulated scenarios. The VaR with significant level η under the simulated
scenario is estimated by
( )
1 S
VaRη ( Rm ( x )) = − inf u  ∑ 1Rsm ( x)<u > 1 − η . (11)
S s =1

(k)
Let Rm ( x ) be the k-th smallest value in { Rsm ( x ) | s = 1, 2, · · · , S}, then CVaR at the
significant level η is estimated according to the formula

CVaRη ( Rm ( x ))
dS(η )e−1
!
dSη e − 1
 
1 1 (dSη e)
∑
(k)
=− Rm ( x ) + η− Rm (x) , (12)
η S k =1
S

where d x e denotes the smallest integer larger than x (See Rachev et al. 2008 for details).
The rate of return of the n-th asset between time ti−1 and time ti is defined by

Pn (ti , ω ) − Pn (ti−1 , ω )
r n ( ti , ω ) = , t > 0,
Pn (ti−1 , ω )

with rn (0, ·) = 0. It is referred to as return in this paper. Let x = ( x1 , x2 , · · · , x N ) T ∈ R N be

a capital allocation vector of a long-only portfolio satisfying ∑nN=1 xn = 1 and xn ∈ [0, 1] for
all n ∈ {1, 2, · · · , N }. Then, the portfolio return U ( x, ti , ωs ) between time ti−1 and time ti is

N
U ( x, ti , ωs ) = ∑ x n r n ( t i , ω s ).
n =1

The scenario-based estimation on uncompounded cumulative return at time ti is

t
Q( x, ti , ωs ) = ∑ Un (x, ti , ωs ).
t =1

Denote Q( x, ti , ωs ) by Qis ( x ). Using (2)–(4), DD, ADD, and MDD on a single simulated
scenario are estimated, respectively, by

DDm,s := DD(tm , ωs ) = max Qsj ( x ) − Qsm ( x ), (13)

j∈{0,1,2,··· ,m}
M
1
ADD M,s := ADD(t M , ωs ) =
M ∑ DDm,s , (14)
m =1
MDD M,s := MDD(t M , ωs ) = max DDm,s . (15)
m∈{1,2,··· ,M }

Furthermore, using (5)–(7), CDaR is estimated on a single simulated scenario by

M
1
CDaRη ( T, s) := CDaRη ( T, ωs ) =
(1 − η ) M ∑ DDm,s 1DDm,s >ζ ηs ,
m =1

where (
inf{z| FDD (z, s) ≥ η } if η ∈ (0, 1]
ζ ηs : = ζ η ( ws ) = .
0 if η = 0
J. Risk Financial Manag. 2022, 15, 230 7 of 23

with
M
1
FDD (z, s) =
M ∑ 1DDm,s ≤z .
m =1

Equivalently, it is estimated by the optimization formula

( )
M
1
(1 − η ) M m∑
CDaRη ( T, s) = min ζ + max(DDm,s − ζ, 0) .
ζ =1

With (8)–(10), DD and CDaR on multiple scenarios are estimated by

S
1
DD(m) =
S ∑ DDm,s
s =1

and

CDaRη ( T )
S M
FDD (ζ (η )) − η
 
1 1
=
1−η
ζ (η ) +
(1 − η ) M ∑ ∑ S
DDm,s 1DDm,s >ζ (η ) , (16)
s =1 m =1

respectively, where
S
1
FDD (z) =
S ∑ FDD (z, s)
s =1

and (  
inf z FDD (z) ≥ η if η ∈ (0, 1]
ζη = .
0 if η = 0
In this paper, we will apply time series models to generate the scenario of rn (m, s) for
m ∈ {1, 2, · · · , M}, s ∈ {1, 2, · · · , S} and n ∈ {1, 2, · · · , N }.

2.3. Multivariate Normal Tempered Stable Distribution

Let T be a strictly positive random variable defined by the characteristic function for
λ ∈ (0, 2) and θ > 0
!
2θ 1− 2
λ
λ λ
φT (u) = exp − ((θ − iu) 2 − θ 2 ) .
λ

Then, T is referred to as a tempered stable subordinator with parameters λ and θ.

Suppose that ξ = (ξ 1 , · · · , ξ N ) T is a N-dimensional standard normal distributed random
vector with a N × N covariance matrix Σ, i.e., ξ ∼ Φ(0, Σ). The N-dimensional NTS
distributed random vector X = ( X1 , · · · , X N ) T is defined by
√
X = µ + ν ( T − 1) + Tdiag(γ)ξ,

where µ = (µ1 , · · · , µ N ) T ∈ R N , ν = (ν1 , · · · , νN ) T ∈ R N , γ = (γ1 , · · · , γ N ) T ∈ R+

N and T

is independent of ξ. The N-dimensional multivariate NTS distribution specified above is

denoted by
X ∼ MNTS N (λ, θ, ν, γ, µ, Σ).
q q
− λ ), | ν | <
1 − νn2 ( 22θ 2θ
Let µn = 0, and γn = n 2−λ for n ∈ {1, · · · , N }. This
yields a random variable having zero mean and unit variance. In this case, the ran-
J. Risk Financial Manag. 2022, 15, 230 8 of 23

dom variable is referred to as standard NTS distributed random variable and denoted by
X ∼ stdMNTS N (λ, θ, ν, Σ). The covariance matrix of X is given by

2−λ >
Σ X = diag(γ)Σdiag(γ) + ν ν.
2θ

2.4. Regime-Switching GARCH Model

GARCH(p, q) model has been studied extensively as a model for volatility.

rt = η + σt et ,
ut = σt et ,
p q
σt2 = ω + ∑ αi u2t−i + ∑ β i σt2−i .
i =1 i =1

where rt is the return at time t, σt is the variance at time t, η, ω, αi , β i are parameters. We

will use GARCH(1,1) in this paper.
Before specifying our model, it would be clear to first specify the univariate Markov
regime-switching model in Haas et al. (2004) as follows

rt = η∆t + σ∆t ,t et ,
ut = σ∆t ,t et ,
(17)
σt2 = ω + αu2t−1 + β ◦ σt2−1 ,
iid
et ∼ N(0, 1),

where
• k = number of regimes in a Markov chain;
• ∆t = {1, · · · , k} = Markov chain with an irreducible and primitive transition matrix
that determines the regime at time t;
• rt = return at time t;
• σt2 = (σ1,t
2 , · · · , σ2 ) = vector of parallel variance;
k,t
• ω = (ω1 , · · · , ωk ), α = (α1 , · · · , αk ), β = ( β 1 , · · · , β k ). ω, α, β are vectors of coefficients;
• η∆t = regime specific mean return in regime ∆t at time t;
• σ∆t ,t = the standard deviation in regime ∆t at time t;
• ◦ denotes element-wise product.
There are k parallel GARCH models evolving simultaneously. The Markov chain ∆t
determines which GARCH model is realized at next moment.
To better understand (17), let us create the following matrix
 
σ1,1 σ1,2 ... σ1,t ...
σ2,1 σ2,2 ... σ1,t . . .
[σ∆t ,t ]∆t =1,...,k, t=1,...T = . .
 
.. ..
 .. . . ... . . .
σk,1 σk,2 ... σk,t ...

Each column is a total of k parallel standard deviations at time t. Each row is the
process of one regime through time 1 to T. The process of standard deviation is generated
as follows:
Step 1: At t = 1, the initial column is generated.
Step 2: ∆1 decides which row is realized.
For example, suppose ∆1 = 2. That is, σ2,1 is realized in real-world at t = 1.
Step 3: By vector calculation, 2nd column is generated.
J. Risk Financial Manag. 2022, 15, 230 9 of 23

For example, suppose σ2,1 is realized at t = 1. We calculate

         
σ1,2 ω1 α1 β1 σ1,1
σ2,2  ω2  α2   β 2  σ2,1 
 ..  =  ..  + σ2,1 e1  ..  +  ..  ◦  .. .
         
 .   .  .  .   . 
σk,2 ωk αk βk σk,1

Step 4: ∆2 Decides which row is realized.

For example, suppose ∆2 = 1. That is, σ1,2 is realized in real world at t = 2. A regime
switch from regime 2 to regime 1 takes place.
Step 5: Repeat Step 1 to Step 4.
It is important to note that in the example, the realized variance at time t = 2, σ1,2 , is
calculated with both the realized variance at time t = 1, σ2,1 , and unrealized σ1,1 . This is
obvious from the vector equation shown above. σ1,1 is in the parallel process and is not
realized in real world.
More generally, when there is a regime switch, from the vector equation σt2 = ω +
αut + β ◦ σt2−1 , we know that the variance σ∆t ,t is determined by σ∆t ,t−1 rather than
2

σ∆t−1 ,t−1 . σ∆t ,t−1 is a variance in regime ∆t at time t, which is generated simultaneously with
σ∆t−1 ,t−1 , but does not exist in reality at time t or t − 1. This makes the model different from
the one in Henneke et al. (2011) that requires all parameters to switch regime according
to a Markov chain. In that model, there is no parallel process, and σ∆t ,t is determined
by σ∆t−1 ,t−1 .
The stationary conditions derived in Haas et al. (2004) require definitions of the matrices:

M ji = p ji ( β + αei> ), i, j = 1, . . . , k

and the block matrix

M = [ M ji ], i, j = 1, . . . , k.
The necessary and sufficient condition for stationarity is ρ( M ) < 1, where ρ( M )
denotes the largest eigenvalue of matrix M.

3. MRS-MNTS-GARCH Model
This section defines the MRS-MNTS-GARCH model and introduces the procedures
for model fitting and sample path simulation.

3.1. Model Specification

To model a multivariate process, we assume that the variance of each individual asset
evolves independently according to the univariate regime-switching GARCH model speci-
fied previously with possibly different number of regimes, while the correlation between
assets is modeled separately by stdMNTS distribution in the joint standard innovations.
The joint innovations is defined bya HMM with stdMNTS as conditional distribution in
each regime.
The MRS-MNTS-GARCH model is defined by

r t = η t + σt ◦ et
u t = σt ◦ et
2
(i ) 2 (i ) 2
    
(i )
σt = ω(i) + α(i) ut−1 + β(i) ◦ σt−1 , i = 1, . . . , N
iid
et ∼ stdMNTS(λ∆D , θ∆D , ν∆D , Σ∆D ),
t t t t

where
• N = number of assets;
• k(i) = number of regimes of the i-th asset;
J. Risk Financial Manag. 2022, 15, 230 10 of 23

• ∆(i) = {1, · · · , k(i) } = Markov chain with an irreducible and primitive transition
matrix that determines the regime of the i-th asset at time t;
(i )
• ∆t = {1, · · · , k(i) } = realization of ∆(i) at time t;
• ∆ D = {1, · · · , k D } = Markov chain with an irreducible and primitive transition matrix
that determines the regime of the joint innovations at time t;
• ∆tD = {1, · · · , k D } = realization of ∆ D at time t;
(1) (N)
• r t = (r t , . . . , r t ) = vector return of N assets at time t;
(1) (N)
• ηt = ( η (1) , . ..,η (N) ) = vector mean return at time t;
∆t ∆t
(i ) (i )
• η (i ) = mean return of the i-th asset at time t, η (i ) is determined by the regime of the
∆t ∆t
(i )
 at time t, ∆t ; 
i-th asset
(1) (N)
• σt = σ ( 1 ) , . . . , σ ( N ) = vector of standard deviation of N assets at time t;
∆t ,t ∆t ,t
(i ) 2
   
(i ) (i ) (i )
• σt = σ1,t , . . . , σ (i) = standard deviation vector of the i-th asset with σt =
 k ,t 
2  2
(i ) (i )
σ1,t , . . . , σ (i) ;
k ,t
 
(i ) (1) (N)
• ut−1 = the i-th element of ut , with ut = ut , . . . , ut ;
(i ) (i ) (i ) (i ) (i ) (i )
• ω ( i ) = ( ω1 , . . . , ω ), α (i ) = ( α1 , . . . , α ), β (i ) = ( β 1 , . . . , β (i ) ). ω(i) , α(i) , β(i) are
k (i ) k (i ) k
the vector of coefficients of the i-th asset in k(i) regimes;
(1) (N)
• et = (et , . . . , et ) = joint innovations;
• ◦ denotes element-wise product.
For each asset, the volatility process is the same as that of the univariate regime-
switching GARCH model in (17). It is a classical GARCH process when it does not shift
within regimes. Unlike the most flexible model in which the variance at time t is calculated
with the variance at time t − 1 in the last regime, when a regime shift takes place at time t,
the variance in the model at time t is determined by the variance at time t − 1 within the new
regime. The regimes of each asset and joint innovations evolve independently, mitigating
the difficulty in estimation caused by all parameters switching regimes simultaneously.

3.2. Parameter Estimation

Although NTS distribution is flexible enough to accommodate many stylized facts
of asset return, the absence of an analytical density function presents some difficulties
in estimation. Our estimation methodology is adapted from Kim et al. (2011, 2012),
which are among the first works to incorporate NTS distribution in portfolio optimization.
Another estimation of stdMNTS distribution with EM algorithm combined with fast Fourier
transform is studied in Bianchi et al. (2016). Below we describe the procedure to fit
the model.
First, we fit the univariate Markov regime-switching GARCH model with t innovation
on the index return and extract the innovations and the regimes at each time t, ∆tD . It is
intuitive to assume that the correlation between assets change drastically when a market
regime shift takes place. Thus, here we assume that the Markov chain ∆ D that determines
the regime of innovations is the same as the Markov chain that determines the regime of
the market index. That is, the sample path of the regime of the innovation is derived by
extracting the sample path of the regime of the market index. The innovations of the model
calibrated by the market index are used to estimate tail parameters λ∆D , θ∆D in each regime.
Next, we fit the univariate model on each asset and extract the innovations for sub-
sequent estimation of stdMNTS distribution. In each regime, the stdMNTS distribution
has two tail parameters λ∆D , θ∆D and one skewness parameter vector ν∆D . Common tail
parameters λ∆D , θ∆D are assumed for individual constituents, which are estimated from the
market index in each regime. The skewness parameter ν∆D is calibrated by curve fitting for
each asset.
J. Risk Financial Manag. 2022, 15, 230 11 of 23

Finally, we plug the empirical covariance matrix of the innovations in each regime
2− λ ∆ D >
Σ X ∆D in the formula Σ∆D = diag(γ∆D )−1 (Σ X ∆D − 2θ∆ D ν∆ D ν∆ D )diag( γ∆ D )
−1 to compute
Σ∆D . Note that Σ∆D is supposed to be a positive definite matrix. To guarantee this, we
can either substitute ν∆D with the closest vector to ν∆D in L2 norm which renders Σ X ∆D −
2− λ ∆ D >
2θ∆ D ν∆ D ν∆ D positive definite matrix, or directly find the closest positive definite matrix to
Σ∆D . We choose the second method. Furthermore, the usual issue of estimating covariance
matrix arises here as well, especially when a regime only has a short lasting period. To
address this issue, we apply the denoising technique in Laloux et al. (1999) on the positive
definite matrix derived earlier to estimate Σ∆D .
The number of regimes of each asset is set as equal to that of the market index. We
find that univariate Markov switching model with more than three regimes often has one
unstable regime that lasts for a very short period and switches frequently and sometimes
has one regime with clearly bimodal innovations distribution. Thus, it is desirable to limit
the number of regimes smaller than 4, check unimodal distribution with Dip test and
choose the one with the highest BIC value.
The procedure is summarized as follows.
Step 1: Fit the univariate Markov regime-switching GARCH model with t innovation on
the index return and extract the innovations and the sample path of regimes.
Step 2: Estimate common tail parameters λ∆D , θ∆D in each regime.
Step 3: Fit univariate model on each asset and extract the innovations.
r 4: Estimate skewness parameters ν∆D for assets in each regime, calculate γ∆D =
Step
2− λ ∆ D
1 − ν∆D 2 ( 2θ∆ D ).
2− λ ∆ D >
Step 5: Calculate the matrix diag(γ∆D )−1 (Σ X ∆D − −1
2θ∆ D ν∆ D ν∆ D )diag( γ∆ D ) , find the
closest positive definite matrix and apply the denoising technique to estimate Σ∆D .

3.3. Simulation
To conduct simulation with the calibrated model, we follow the procedures speci-
fied below.
Step 1: Simulate S sample paths of standard deviation of N assets for T days with the
fitted model.
Step 2: Simulate S sample paths of a Markov chain ∆ D with the market’s transition matrix.
Calculate the total number of each regime in all sample paths.
Step 3: Draw i.i.d. samples from stdMNTS distribution in each regime. The number of
samples is determined by the calculation in Step 2. To draw one sample, we follow the
procedure below.
Step 3.1: Sample from multivariate normal distribution N(0,Σ∆D ).
√ subordinator T with parameters λ∆D and θ∆D .
Step 3.2: Sample from the tempered stable
Step 3.3: Calculate X = ν∆D ( T − 1) + T (γ∆D ◦ ξ ∆D ).
Step 4: Multiply the standard deviation in Step 1 with standard joint innovations in Step 3
accordingly. Add regime-specific mean η∆D to get simulated asset returns.

4. Portfolio Optimization
In this section, we discuss issues on portfolio optimization.

4.1. Problem Formulation

Conditioned on given sample path(s), classical portfolio optimization is formulated as
a trade-off between risk and return

min W (R( x, t, ω )|t ∈ [0, T ], ω ∈ Ω)

x
s.t. E[R( x, T, ω )|ω ∈ Ω] ≥ d,
x ∈ V,
J. Risk Financial Manag. 2022, 15, 230 12 of 23

where d is the benchmark return, R( x, t, ω ) is the portfolio return at time t ∈ [0, T ] in

given sample paths ω ∈ Ω, W (R( x, t, ω )|t ∈ [0, T ]) is a risk measure of R( x, t, ω ) for time
t ∈ [0, T ] estimated based on given sample paths Ω, and x = ( x1 , . . . , xn ) is the allocation
vector of n assets. A typical setting of V is { x | ∑iN=1 xi = 1, xi ≥ 0}, meaning that short
selling is not allowed.

4.2. Discussion on Risk Measures and Constraint

If the historical sample paths of asset returns are used as input to the CVaR optimiza-
tion, we minimize the CVaR of daily portfolio return from time t = 1 to t = T. In the
setting where we use simulation as input, we can choose to minimize the CVaR of daily
returns from time t = 1 to t = T or CVaR of compounded returns at time t = T. We can
set constraints on average daily returns from time t = 1 to t = T or compounded portfolio
return at time t = T. Notice that the daily return in the simulation of GARCH model is not
i.i.d. Furthermore, it is reasonable to focus on the the return at the final time. Thus, we
choose to minimize the CVaR of return at time t = T instead of return from time t = 1 to
t = T subject to constraint on compounded portfolio return at time t = T.
The definition of drawdown needs some clarification as well. The portfolio drawdown
at time t is defined in (13).
m
DDm,s := max
j∈{0,1,2,··· ,m}
Q( x, t j , ωs ) − Q( x, tm , ωs ) = ∑ r(x, ti , ws ),
i=h

where h = arg max j∈{0,1,2,··· ,m} Q( x, t j , ωs ), is the sum of daily returns from its peak. It is
somewhat unconventional at first sight compared with the absolute drawdown defined by
m
absDDm,s := max P( x, t j , ωs ) − P( x, tm , ωs ) = P( x, th , ωs ) ∏(1 + r ( x, ti , ws ))
j∈{0,1,2,··· ,m} i=h

and the relative drawdown defined by

max j∈{0,1,2,··· ,m} P( x, t j , ωs ) − P( x, t j , ωs ) m

reDDm,s := = ∏(1 + r ( x, ti , ws )),
max j∈{0,1,2,··· ,m} P( x, t j , ωs ) i=h

where h = arg max j∈{0,1,2,··· ,m} Q( x, t j , ωs ). CDaR is essentially an average of drawdowns

that exceed the threshold. CDaR defined in (16) with DDm,s satisfies good properties such
as nonnegativity, insensitivity to constant shift, positive homogeneity and convexity (See
Checkhlov et al. 2005), which gives great advantage in developing optimization techniques.
CDaR can be defined in a similar way with absDDm,s and reDDm,s .
It is possible to use the algorithm designed for CDaR defined by DDm,s to mini-
mize CDaR defined by absDDm,s . By substituting the input r ( x, ti , ws ) with P( x, ti , ωs ) −
P( x, ti−1 , ωs ), the calculation of DDm,s becomes
m
∑ P(x, ti , ωs ) − P(x, ti−1 , ωs ) = absDDm,s
i=h

where h = arg max j∈{0,1,2,··· ,m} Q( x, t j , ωs ). However, it is obvious from the definitions that
CDaR defined absDDm,s and reDDm,s do not satisfy basic axioms such as positive homogeneity.
Another drawback of absolute drawdown is that when we consider a long time period,
drawdowns could vary greatly in absolute value but be close in relative value, the latter of
which we are more concerned about. Uncompounded cumulative return is determined by
rate of returns regardless of the price. This discussion justifies our definition of drawdown
with DDm,s .
J. Risk Financial Manag. 2022, 15, 230 13 of 23

5. Empirical Study
In this section, we demonstrate the superiority of our approach with various in-sample
and out-of-sample tests. We conduct model fitting, sample path simulation and portfolio
optimization. In the in-sample test, we conduct a KS test on the marginal NTS distribution
and marginal t-distribution to show that the NTS distribution has a much better fit on
the innovations. We also provide the transition matrix and the correlation matrices of the
joint innovations in each regime. In the out-of-sample test, we use various performance
measures and visualizations for the rolling-window studies in recent years to show the
outperformance of our portfolio.
For diversification purposes, we set the range of weights as [0.01, 0.15]. A case study
in Krokhmal et al. (2002) found that without constraints on weights, the optimal portfolio
only consists of a few assets among hundreds. Investors often empirically categorize the
market as bull, bear and sideways market. Haas et al. (2004) experiments with two and
three regimes. We limit the number of regimes to be smaller than or equal to three. The
Dip test is conducted on innovations to ensure unimodal innovation distribution. Starting
fitting with three regimes, a model with fewer regimes is used instead when the p-value
is lower than 0.1 or have a regime lasting shorter than 40 days in total. Preliminary tests
show that without these selection criteria, the model would have a risk of overfit in some
cases. For example, the innovation could be multimodal, and the regime switches hundreds
of times within the tested period. The phenomena is even more pronounced when the
number of regimes is higher than three. To be concise in notation, we denote the portfolios
in a convenient manner. For example, 0.9-CDaR portfolio denotes the optimal portfolio
derived from the optimization with 0.9-CDaR as the risk measure. The standard deviation
optimal portfolio is the optimal portfolio in the classical Markowitz model that maximizes
Sharpe ratio, which we also denoted by mean-variance (MV) optimal portfolio. The word
optimal is sometimes omitted. Since we simulate returns for 10 days, all CVaR with varying
confidence levels are calculated with the simulated cumulative returns on the 10-th day.
We omit the time and denote the optimal portfolio simply as CVaR portfolio.

5.1. Data
The data are comprised of the adjusted daily price of DJIA index, 29 of the constituents
of DJIA Index and three ETFs of bond, gold and shorting index (Tickers: TMF, SDOW and
UGL) from January 2010 to September 2020. One constituent DOW is removed because it
is not included in the index throughout the time period. Since we use 1764 trading days’
(about 7 years) data to fit the model, the time period for out-of-sample rolling-window test
is from January 2017 to September 2020, which includes some of the most volatile periods
in history caused by the a pandemic and some trade tensions. By reweighting the index
constituents, it can be regarded as an enhanced index portfolio.

5.2. Performance Measures

Various performance measures are discussed in Biglova et al. (2004), Rachev et al. (2008),
Cheridito and Kromer (2013). Similar to Markowitz Model, an efficient frontier can be derived
by changing the value of constraint. Each portfolio on the efficient frontier is optimal in
the sense that no portfolio has a higher return with the same value of risk measure. In
E[ R( x,T,·)]
this paper, we refer to the portfolio with the highest performance ratio W ( R( x,t,·)|t∈[0,T ]) as
an optimal portfolio and the others on the efficient frontier as suboptimal portfolios. Note
that E[ R( x, T, ·)] is CVaR0 ( R( x, T, ·)). Thus, the mean-CVaR ratio can be regarded as a
CVaRη1 ( R( x,T,·))
special case of the Rachev ratio CVaRη2 ( R( x,T,·))
. We test with η1 = η2 = 0.1 to focus on the
distribution tails.

5.3. In-Sample Tests

We present various in-sample test results. The time period during which 2-regime
model is first selected is used in fitting is from 30 April 2010 to 5 May 2017. 100 days is
J. Risk Financial Manag. 2022, 15, 230 14 of 23

classified as regime 1, and 1665 days is classified as regime 2. The standard deviation of the
DJIA index is 0.00217 in regime 1 and 0.00801 in regime 2. Regime 2 is more volatile than
regime 1. One might expect that the market is in a less volatile regime longer and has a
spiked standard deviation during a short but much more volatile regime. It is not the case
in this tested period according to our model.

5.3.1. Kolmogorov–Smirnov Tests on Marginal Distributions

We conduct a Kolmogorov–Smirnov test (KS test) on the marginal distributions of
the joint innovation of MRS-MNTS-GARCH model in the tested period. The results
are presented in Table 1. For comparison, we also fit multivariate t-distribution on the
joint innovations and report the results of KS tests on the marginal distributions. The
degree of freedom of multivariate t-distribution in regime 1 and regime 2 are 5.34 and
5.68, respectively. Note that the marginal distribution of stdMNTS distribution is still NTS
distribution. Since we assume common parameters λ and θ in MNTS distribution, we report
the parameter β of each asset in both regimes. The data are rounded to 3 decimals place.

Table 1. Kolmogorov–Smirnov tests on marginal distributions of joint innovation.

Regime Beta KS Statistics of NTS p-Value KS Statistics of t p-Value

AAPL 1 2.048 0.129 0.067 0.125 0.081
2 0.038 0.018 0.624 0.055 0
AMGN 1 1.133 0.054 0.917 0.058 0.875
2 0.139 0.012 0.955 0.045 0.002
AXP 1 −0.513 0.022 1 0.027 1
2 −0.021 0.022 0.392 0.06 0
BA 1 −1.129 0.016 1 0.039 0.996
2 −0.075 0.009 0.999 0.041 0.007
CAT 1 1.681 0.083 0.476 0.09 0.369
2 0.069 0.012 0.973 0.043 0.004
CRM 1 −0.861 0.041 0.993 0.045 0.982
2 0.095 0.032 0.071 0.071 0
CSCO 1 1.297 0.084 0.454 0.066 0.75
2 0.058 0.043 0.004 0.08 0
CVX 1 −1.523 0.064 0.781 0.063 0.791
2 −0.055 0.019 0.563 0.029 0.11
DIS 1 −0.644 0.115 0.132 0.103 0.225
2 0.025 0.014 0.878 0.053 0
GS 1 1.274 0.038 0.998 0.031 1
2 −0.046 0.014 0.917 0.036 0.026
HD 1 −1.431 0.035 0.999 0.056 0.901
2 0.025 0.01 0.995 0.047 0.001
HON 1 −1.496 0.064 0.783 0.064 0.776
2 0.131 0.015 0.843 0.054 0
IBM 1 0.64 0.023 1 0.041 0.993
2 −0.019 0.019 0.587 0.057 0
INTC 1 −1.551 0.045 0.981 0.085 0.443
2 0.061 0.008 1 0.044 0.003
JNJ 1 1.87 0.055 0.908 0.109 0.174
2 −0.013 0.008 1 0.041 0.007
JPM 1 1.857 0.023 1 0.083 0.464
2 0.026 0.008 1 0.041 0.007
KO 1 −1.674 0.072 0.656 0.078 0.546
2 0.013 0.009 0.999 0.047 0.001
MCD 1 −1.956 0.067 0.742 0.092 0.343
2 −0.005 0.022 0.396 0.061 0
MMM 1 0.658 0.019 1 0.025 1
2 −0.1 0.014 0.882 0.054 0
MRK 1 2.367 0.156 0.013 0.157 0.013
2 0.076 0.013 0.928 0.046 0.002
MSFT 1 −2.175 0.176 0.003 0.165 0.007
2 0.26 0.016 0.753 0.057 0
NKE 1 1.652 0.05 0.956 0.1 0.258
2 0.079 0.022 0.416 0.059 0
PG 1 1.035 0.03 1 0.062 0.815
2 0.12 0.015 0.824 0.055 0
TLT 1 −0.283 0.056 0.897 0.042 0.992
2 −0.161 0.036 0.025 0.028 0.144
TMF 1 −0.273 0.055 0.907 0.041 0.993
2 −0.152 0.035 0.036 0.028 0.135
J. Risk Financial Manag. 2022, 15, 230 15 of 23

Table 1. Cont.

Regime Beta KS Statistics of NTS p-Value KS Statistics of t p-Value

TRV 1 −1.532 0.055 0.91 0.058 0.864
2 −0.033 0.011 0.988 0.048 0.001
UGL 1 1.139 0.066 0.749 0.068 0.721
2 −0.074 0.012 0.973 0.051 0
UNH 1 1.543 0.05 0.951 0.098 0.274
2 0.054 0.012 0.962 0.051 0
V 1 1.45 0.044 0.985 0.05 0.955
2 0.016 0.025 0.26 0.061 0
VZ 1 −0.406 0.115 0.131 0.109 0.17
2 −0.043 0.017 0.716 0.033 0.052
WBA 1 1.011 0.026 1 0.048 0.966
2 0.166 0.022 0.368 0.062 0
WMT 1 1.804 0.08 0.52 0.076 0.582
2 −0.047 0.016 0.8 0.054 0
For NTS distribution, there are 5 p-values smaller than 0.05. For t-distribution, there are 31 p-values smaller than
0.05. Most of the rejections correspond to Regime 2, indicating that the marginal t-distribution is outperformed by
marginal NTS distribution in the more volatile regime.

For NTS distribution, there are 5 p-values smaller than 0.05. For t-distribution, there
are 31 p-values smaller than 0.05. Most of the rejections correspond to Regime 2, indicating
that the marginal t-distribution is outperformed by marginal NTS distribution in describing
the return in the more volatile regime. We can also observe that β varies significantly in
different regimes. Generally, for all assets, β in regime 1 has larger absolute values.

5.3.2. Transition Matrix and Denoised Correlation Matrices of Joint Innovation

The transition matrix of the innovations is presented in Table 2. The self-transition
probability in two regimes are close, and both are high.

Table 2. Transition matrix of joint innovation.

Regime 1 Regime 2
regime 1 0.8538 0.1462
regime 2 0.0301 0.9699
This table presents the transition matrix of the joint innovation of MRS-MNTS-GARCH model.

We also provide the denoised correlation matrices of stdMNTS innovations in two regimes
in Table 3. Since there are two regimes identified in this period, we combine the two correlation
matrices for easier comparison. The upper triangle of the matrix is the upper triangle of
correlation matrix in regime 1, while the lower triangle of the matrix is the lower triangle
of correlation matrix in regime 2. We find that the innovations have distinctively different
correlation matrices in two regimes, validating the regime-switching assumption. The
innovations are highly correlated in regime 2, which corresponds to more volatile periods.

5.4. Out-of-Sample Tests

We conduct out-of-sample tests to demonstrate the outperformance of the optimal
portfolios. We use 3 types of risk measures with different confidence levels in the optimiza-
tion, namely, maximum drawdown, 0.7-CDaR, 0.3-CDaR, average drawdown, 0.5-CVaR,
0.7-CVaR, 0.9-CVaR and standard deviation. Note that 0-CVaR is equal to the expected
return, which does not make sense as a risk measure. Minimizing α-CVaR with small α
means that we include the positive part of the return distribution as risk. This is a drawback
of standard deviation, and thus we set α at 0.5, 0.7, and 0.9 to demonstrate the superiority.
The rolling window technique is employed with 10-day forward-moving time window.
In each time window, we simulate 10,000 sample paths of length 10 with the fitted model.
The simulation is used as input to portfolio optimization. The portfolio is held for 10 trading
days before rebalancing. The portfolio optimization is performed with software Portfolio
Safeguard (PSG) with precoded numerical optimization procedures.
J. Risk Financial Manag. 2022, 15, 230 16 of 23

Table 3. Denoised correlation matrices of joint innovation in two regimes.

AAPL AMGN AXP BA CAT CRM CSCO CVX DIS GS HD HON IBM INTC JNJ JPM KO MCD MMM MRK MSFT NKE PG SDOW TMF TRV UGL UNH V VZ WBA WMT
AAPL 1 0.15 0.14 0.09 0.17 0.23 0.21 0.09 0.14 0.12 0.15 0.25 0.16 0.13 0.28 0.08 0.10 0.04 0.20 0.11 0.19 0.23 0.07 −0.31 −0.05 0.08 −0.01 0.04 0.34 0.22 0.21 0.21
AMGN 0.28 1 0.15 0.11 0.13 0.40 0.18 0.12 0.27 0.16 0.27 0.29 0.20 0.18 0.30 0.16 0.02 0.06 0.24 0.39 0.13 0.29 0.13 −0.33 −0.22 −0.05 −0.02 0.04 0.31 0.13 0.25 0.10
AXP 0.34 0.39 1 0.37 0.44 0.15 0.29 0.33 0.38 0.50 0.21 0.38 0.13 0.13 0.22 0.48 0.04 0.15 0.29 0.28 0.01 0.27 0.09 −0.55 −0.23 0.18 −0.16 0.30 0.16 0.15 0.21 0.16
BA 0.36 0.40 0.50 1 0.33 0.09 0.24 0.13 0.25 0.28 0.09 0.35 0.13 0.05 0.22 0.28 0.08 0.13 0.27 0.18 −0.01 0.20 0.08 −0.44 −0.14 0.13 −0.09 0.26 0.06 0.17 0.19 0.12
CAT 0.38 0.32 0.48 0.49 1 0.18 0.30 0.30 0.26 0.36 0.15 0.43 0.16 0.28 0.10 0.33 0.04 0.06 0.30 0.15 0.16 0.11 0.10 −0.49 −0.16 0.14 −0.04 0.17 0.11 0.23 0.10 0.21
CRM 0.31 0.30 0.37 0.34 0.36 1 0.23 0.14 0.36 0.18 0.32 0.29 0.29 0.24 0.23 0.20 0.09 0.17 0.30 0.22 0.28 0.32 0.07 −0.33 −0.18 0.003 −0.10 −0.14 0.39 0.15 0.23 −0.03
CSCO 0.35 0.28 0.37 0.39 0.40 0.38 1 0.27 0.36 0.27 −0.02 0.30 0.25 0.28 0.19 0.29 0.16 0.13 0.30 0.21 0.24 0.09 0.16 −0.42 −0.15 0.12 −0.09 0.10 0.22 0.19 0.19 0.24
CVX 0.32 0.34 0.46 0.46 0.58 0.31 0.38 1 0.22 0.30 0.10 0.27 0.17 0.22 0.22 0.32 0.14 0.08 0.34 0.13 0.11 0.16 0.17 −0.45 −0.30 0.14 −0.04 0.13 0.11 0.20 0.19 0.17
DIS 0.33 0.39 0.49 0.49 0.44 0.37 0.41 0.44 1 0.32 0.29 0.40 0.26 0.09 0.25 0.32 0.11 0.19 0.34 0.08 0.16 0.34 0.19 −0.48 −0.29 0.13 −0.17 0.11 0.34 0.18 0.21 0.10
GS 0.34 0.39 0.55 0.48 0.50 0.35 0.41 0.47 0.49 1 0.16 0.31 0.09 0.21 0.10 0.64 −0.08 0.01 0.26 0.12 0.09 0.25 −0.01 −0.49 −0.34 0.10 −0.30 0.30 0.20 0.004 0.16 −0.04
HD 0.34 0.39 0.48 0.44 0.41 0.34 0.36 0.41 0.48 0.43 1 0.30 0.27 0.12 0.12 0.24 −0.04 0.14 0.29 0.13 0.18 0.29 0.04 −0.38 −0.23 0.13 −0.17 0.05 0.29 0.21 0.17 0.17
HON 0.41 0.43 0.56 0.63 0.64 0.42 0.46 0.57 0.57 0.55 0.54 1 0.27 0.22 0.28 0.37 0.21 0.24 0.47 0.17 0.27 0.28 0.31 −0.60 −0.31 0.31 −0.18 0.16 0.33 0.21 0.36 0.18
IBM 0.36 0.34 0.43 0.46 0.46 0.35 0.44 0.47 0.43 0.44 0.41 0.52 1 0.28 0.03 0.11 0.08 0.01 0.30 0.12 0.30 0.14 0.14 −0.39 −0.13 0.04 −0.10 −0.07 0.31 0.22 0.14 0.13
INTC 0.37 0.38 0.44 0.44 0.46 0.37 0.45 0.45 0.43 0.43 0.41 0.50 0.48 1 0.06 0.24 0.10 −0.04 0.27 0.17 0.45 0.08 0.16 −0.31 −0.01 −0.04 0.01 −0.02 0.22 0.21 0.12 0.09
JNJ 0.28 0.52 0.45 0.48 0.41 0.27 0.37 0.49 0.45 0.44 0.44 0.53 0.45 0.41 1 0.09 0.18 0.17 0.33 0.36 0.04 0.21 0.25 −0.37 −0.06 0.02 0.04 0.10 0.34 0.16 0.21 0.17
JPM 0.35 0.40 0.59 0.51 0.52 0.37 0.43 0.52 0.52 0.77 0.46 0.59 0.47 0.46 0.49 1 −0.04 0.09 0.30 0.15 0.14 0.24 0.05 −0.51 −0.35 0.24 −0.31 0.24 0.20 0.10 0.18 0.08
KO 0.27 0.35 0.39 0.42 0.35 0.28 0.33 0.46 0.43 0.33 0.40 0.47 0.43 0.40 0.48 0.40 1 0.23 0.10 0.13 0.21 0.06 0.35 −0.23 −0.02 0.40 0.06 0.05 0.17 0.26 0.31 0.14
MCD 0.30 0.35 0.35 0.39 0.34 0.33 0.33 0.38 0.38 0.33 0.42 0.42 0.40 0.35 0.44 0.35 0.47 1 0.26 0.09 0.02 0.15 0.09 −0.25 −0.16 0.35 −0.14 0.14 −0.01 0.02 0.24 0.07
MMM 0.39 0.42 0.52 0.56 0.57 0.37 0.45 0.55 0.53 0.51 0.50 0.67 0.51 0.50 0.56 0.55 0.48 0.45 1 0.17 0.13 0.31 0.21 −0.56 −0.30 0.29 −0.20 0.11 0.27 0.20 0.23 0.21
MRK 0.24 0.47 0.40 0.37 0.35 0.25 0.32 0.41 0.38 0.39 0.35 0.43 0.37 0.37 0.52 0.43 0.37 0.36 0.44 1 0.05 0.06 0.18 −0.36 −0.06 −0.03 0.05 0.27 0.24 0.16 0.18 0.22
MSFT 0.37 0.35 0.43 0.40 0.43 0.37 0.46 0.42 0.42 0.43 0.40 0.49 0.48 0.53 0.40 0.45 0.39 0.39 0.47 0.34 1 0.14 0.17 −0.28 0.06 0.03 0.0002 −0.04 0.31 0.29 0.21 0.12
NKE 0.30 0.32 0.41 0.41 0.36 0.38 0.33 0.33 0.41 0.36 0.45 0.48 0.35 0.35 0.36 0.39 0.37 0.43 0.43 0.31 0.37 1 0.12 −0.36 −0.18 0.12 −0.13 −0.06 0.33 0.07 0.21 0.14
PG 0.27 0.39 0.36 0.38 0.31 0.24 0.33 0.42 0.40 0.33 0.38 0.42 0.40 0.36 0.52 0.38 0.54 0.40 0.47 0.40 0.38 0.32 1 −0.32 0.01 0.15 0.01 0.08 0.31 0.19 0.33 0.21
SDOW −0.48 −0.54 −0.67 −0.70 −0.70 −0.47 −0.56 −0.71 −0.68 −0.68 −0.64 −0.79 −0.69 −0.62 −0.68 −0.73 −0.61 −0.57 −0.78 −0.57 −0.61 −0.54 −0.58 1 0.35 −0.33 0.20 −0.34 −0.42 −0.34 −0.35 −0.30
TMF −0.27 −0.24 −0.38 −0.33 −0.37 −0.27 −0.28 −0.34 −0.36 −0.42 −0.31 −0.38 −0.32 −0.30 −0.32 −0.45 −0.25 −0.24 −0.37 −0.26 −0.28 −0.29 −0.23 0.45 1 −0.27 0.41 −0.10 −0.18 −0.01 −0.10 0.03
TRV 0.30 0.39 0.46 0.46 0.45 0.31 0.38 0.48 0.49 0.51 0.45 0.54 0.45 0.42 0.50 0.56 0.48 0.42 0.56 0.39 0.41 0.38 0.47 −0.68 −0.30 1 −0.19 0.16 0.03 0.11 0.23 0.15
UGL 0.05 −0.06 −0.01 −0.01 0.10 −0.03 −0.01 0.14 −0.05 −0.05 −0.06 0.01 0.001 −0.01 −0.001 −0.07 0.01 −0.01 0.02 −0.02 −0.02 −0.07 0.03 −0.02 0.16 −0.01 1 −0.05 −0.22 0.09 −0.04 0.04
UNH 0.30 0.40 0.37 0.38 0.33 0.26 0.30 0.38 0.38 0.39 0.38 0.44 0.38 0.33 0.42 0.42 0.34 0.31 0.41 0.36 0.35 0.33 0.30 −0.54 −0.25 0.41 −0.002 1 −0.03 0.09 0.13 0.07
V 0.32 0.37 0.51 0.43 0.38 0.36 0.34 0.39 0.43 0.44 0.41 0.49 0.40 0.37 0.42 0.46 0.35 0.36 0.46 0.35 0.38 0.39 0.34 −0.60 −0.31 0.43 −0.02 0.34 1 0.16 0.17 0.13
VZ 0.26 0.36 0.39 0.35 0.36 0.23 0.30 0.42 0.40 0.34 0.37 0.44 0.38 0.36 0.47 0.40 0.46 0.37 0.46 0.38 0.36 0.31 0.43 −0.56 −0.21 0.46 0.01 0.26 0.33 1 0.18 0.27
WBA 0.25 0.36 0.33 0.36 0.31 0.28 0.26 0.32 0.34 0.33 0.35 0.41 0.33 0.31 0.41 0.35 0.33 0.31 0.38 0.34 0.33 0.29 0.36 −0.48 −0.22 0.36 −0.01 0.32 0.29 0.30 1 0.19
WMT 0.20 0.30 0.30 0.32 0.24 0.18 0.28 0.28 0.33 0.28 0.39 0.37 0.30 0.27 0.40 0.32 0.38 0.34 0.36 0.32 0.31 0.30 0.41 −0.47 −0.17 0.38 −0.02 0.29 0.27 0.37 0.30 1
This table presents the denoised correlation matrices of joint innovations in two regimes. The upper triangle corresponds the regime 1 while the lower triangle corresponds to regime 2
which is more volatile. The correlations in regime 2 are generally higher than those in regime 1.
J. Risk Financial Manag. 2022, 15, 230 17 of 23

5.4.1. Optimal Portfolios

We report the performance of the optimal portfolios in various forms. Due to a large
number of risk measures, we sometimes only present representative ones in graphs for
better visualization. The other optimal portfolios have similar results.

Performance Measures
In Table 4, we measure the performance of the optimal portfolios by various perfor-
mance ratios. The row names are the risk measures used in portfolio optimization. The
columns are the performance measures. For example, the 0.3-CDaR portfolio is optimized
every 10 days to maximize the ratio of expected cumulative return over 0.3-CDaR. Note
that 0-CDaR is the average drawdown while 1-CDaR is the maximum drawdown. The
risk measure standard deviation is studied in the classical Markowitz model, of which the
optimization is also called MV optimization.
We can observe that the optimal portfolios of CDaR and CVaR measures have very
close performance regardless of performance measures. The confidence level has a marginal
impact on the ratios. Considering all the ratios, 0.3-CDaR portfolio and 0.5-CVaR portfolio
are the best among the ten portfolios. 0.3-CDaR portfolio outperforms the others in all
return-CVaR ratios, while 0.5-CVaR portfolio outperforms the others in return-CDaR ratios,
slightly but consistently. All of the optimal portfolios of CDaR and CVaR measures consis-
tently outperform the MV optimal portfolio, which significantly outperforms the DJIA and
the equally weighted portfolio.

Table 4. Performance ratios of optimal portfolios with different risk measures.

Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Sharpe Ratio Rachev Ratio
0-CDaR 0.3-CDaR 0.7-CDaR 1-CDaR 0.5-CVaR 0.7-CVaR 0.9-CVaR

0-CDaR 0.072 0.051 0.027 0.008 0.258 0.156 0.077 0.117 0.965
0.3-CDaR 0.074 0.052 0.027 0.008 0.262 0.159 0.078 0.119 0.968
0.7-CDaR 0.073 0.052 0.027 0.008 0.260 0.158 0.077 0.118 0.965
1-CDaR 0.075 0.053 0.028 0.007 0.259 0.157 0.078 0.117 1.012
0.5-CVaR 0.076 0.054 0.028 0.007 0.259 0.158 0.076 0.120 1.002
0.7-CVaR 0.072 0.051 0.027 0.007 0.257 0.157 0.077 0.121 1.000
0.9-CVaR 0.071 0.050 0.027 0.007 0.243 0.147 0.072 0.116 0.986
Standard
0.064 0.045 0.024 0.006 0.238 0.145 0.071 0.109 0.966
Deviation
DJIA 0.011 0.008 0.004 0.001 0.064 0.040 0.019 0.033 0.855
Equal
0.032 0.023 0.011 0.003 0.136 0.083 0.037 0.065 0.900
Weight
The column names are different ratios used to measure the performance. The row names show the risk measures
used in the portfolio optimization. The DJIA index and the equally weighed portfolio are included as benchmarks.

Log Cumulative Return

In Figure 1, we plot the time series of log cumulative returns of the optimal portfolios
with different risk measures in out-of-sample tests to visualize the performance. The legend
shows colors that represent different risk measures used in each portfolio optimization. We
use log base 10 compounded cumulative returns as a vertical axis so that the scale of relative
drawdown can be easily compared in graphs by counting the grids. The performance with
different risk measures is reported separately. The labels in the legend show the confidence
level of the risk measure. The names of the subfigures indicate the risk measures used
in the optimization. DJIA index and the equally weighted portfolio are included in each
graph for comparison.
As can be observed in the graphs, all the optimal portfolios follow a similar trend,
though they differ in overall performance. They tend to alleviate both left tail and right
tail events. CVaR optimal portfolios have higher cumulative returns than CDaR optimal
portfolios. The confidence level has only a marginal impact. CVaR optimal portfolios with
J. Risk Financial Manag. 2022, 15, 230 18 of 23

confidence levels 0.5 and 0.7 are almost indistinguishable. CDaR optimal portfolios with
confidence levels 0.5, 0.7 and 0.9 are almost indistinguishable.

Relative Drawdown
Since the CVaR and CDaR risk measures only concern the tail behavior of a portfolio,
we plot the relative drawdown of the optimal portfolios in out-of-sample testing period
in Figure 2 to demonstrate their ability to alleviate extreme left tail events. Due to a large
number of optimal portfolios with different risk measures, we only plot 0-CDaR, 0.5-CVaR
and MV optimal portfolios here for better visualization. The others have similar results. The
0-CDaR, 0.5-CVaR and MV optimal portfolios have significantly smaller relative drawdown
most of the time in the out-of-sample test, especially in year 2020. 0-CDaR and 0.5-CVaR
optimal portfolios are slightly better than the MV optimal portfolio.

0.4

Equal Weight
DJIA
0.3 0−CDaR
0.3−CDaR
0.7−CDaR
log cumulative return

1−CDaR
0.5−CVaR
0.7−CVaR
0.2 0.9−CVaR
standard deviation

0.1

0.0

2017 2018 2019 2020

Date

Figure 1. Log cumulative returns: this figure plots the time series of log cumulative return of optimal
portfolios with different risk measures, the DJIA index and the equally weighted portfolio. The
risk measures used in portfolio optimization are 0-CDaR, 0.3-CDaR, 0.7-CDaR, 1-CDaR, 0.5-CVaR,
0.7-CVaR, 0.9-CVaR and standard deviation.

0.3−CDaR
0.3 0.5−CVaR
DJIA
Relative Drawdown

Equal Weight
Standard Deviation

0.2

0.1

0.0
2017 2018 2019 2020
Date
Figure 2. Relative drawdown: this figure plots the relative drawdown paths of optimal portfolios
with different risk measures, the DJIA index and the equally weighted portfolio. The risk measures
include 0-CDaR, 0.5-CVaR and standard deviation.
J. Risk Financial Manag. 2022, 15, 230 19 of 23

Portfolio Return Distribution

In Figure 3, we plot the kernel density estimation on the return distribution. To better
compare the tails of the return distribution, we also plot the log base 10 density. We can
easily observe that the optimal portfolios are very close and alleviate both right and left
tail events. Unlike standard deviation (MV) optimal portfolio, 0.3-CDaR and 0.5-CVaR
portfolio have thinner tails on both sides than DJIA and the equally weighted portfolio.
0.3-CDaR and standard deviation portfolio have a higher peak than the equally weighted
portfolio. Among the three optimal portfolios, the 0.5-CVaR portfolio has the thinnest left
tail and a fatter right tail than the other two optimal portfolios.

80

10−1
60

log density
density

40 10−5

0.3−CDaR 0.3−CVaR
0.5−CVaR 0.5−CVaR
Standard Deviation Standard Deviation
20 Equal Weight 10−9 Equal Weight
DJIA DJIA

0
−0.10 −0.05 0.00 0.05 0.10 −0.10 −0.05 0.00 0.05 0.10
return return

(a) (b)

Figure 3. Kernel density estimation and log kernel density estimation. (a) Kernel density estimation:
this figure plots the kernel density estimation of optimal portfolios with different risk measures,
the DJIA index and the equally weighted portfolio. The risk measures include 0-CDaR, 0.5-CVaR
and standard deviation. (b) Log kernel density estimation: this figure plots the log kernel density
estimation of optimal portfolios with different risk measures, the DJIA index and the equally weighted
portfolio. The risk measures include 0-CDaR, 0.5-CVaR and standard deviation.

Allocation
In Figure 4, we report the time series of optimal weights of the 0-CDaR optimal portfo-
lio as a representative case. The DJIA constituents are aggregated for better visualization.
It is reasonable that when the total weight on DJIA constituents is high, the weights on
shortselling ETF is low. The weights on ETFs hit the lower and upper bounds 0.01 and 0.15
in many periods, indicating that the constraints on weights are active in the optimizations.

1.00

0.75
Weight

0.50

0.25

0.00
2017 2018 2019 2020
Date
DJIA Constituents SDOW TMF UGL

Figure 4. Allocation: this figure plots the weights of 0-CDaR optimal portfolio on DJIA constituents
and 3 ETFs.
J. Risk Financial Manag. 2022, 15, 230 20 of 23

5.4.2. Robustness to Suboptimality in Optimization

So far, we have been studying the optimal portfolios that maximize performance
ratios. In this section, we study the sensitivity of the performance by comparing suboptimal
portfolios with the optimal ones. We show that the portfolio with tail risk measure is more
robust to suboptimality in optimization than the mean-variance portfolio. The performance
ratios of CDaR and CVaR optimal portfolios are shown to be not sensitive to changing the
value of return constraint, while the performance ratios of mean-variance optimal portfolio
shows significant change. The graphs of log cumulative return show that the suboptimal
portfolios follow a similar trend, sometimes overlapping with each other.
We use 9 portfolios with different constraints on return to approximate the efficient
frontier for each risk measure. For example, in each 0.3-CDaR optimization, we perform 10
optimizations with varying constraints on return. The portfolio with the highest return-risk
ratio is the approximated optimal portfolio. We denote the portfolio that has n lower level
of constraint on return as level Ln suboptimal portfolio, the one that has n higher level
of constraint on return as level Hn suboptimal portfolio. When a certain optimization is
unfeasible, we set the allocation the same as that of a lower level. The constraints on return
are (0.002, 0.010, 0.020, 0.030, 0.035, 0.040, 0.045, 0.050, 0.060, 0.065). For example, when
the portfolio with constraint 0.050 on return has the highest performance ratio among the
10 portfolios, it is labeled as the optimal portfolio. Accordingly, the portfolio with one-level
higher constraint 0.060 is labeled H1. In this case, H2 to H4 have the same constraint
0.065, since there is no optimization performed with higher constraint. Note that at each
rebalance, the optimal portfolio changes, so do portfolios of other levels, i.e., constraint
0.060 may no longer be optimal. The performance of each label is measured with portfolios
of corresponding level determined at each rebalance.
We report suboptimal portfolios with risk measures of 0-CDaR, 0.5-CVaR and standard
deviation in Figure 5 and Table 5 as representative cases. We find that the optimal portfolio
is consistently too conservative for all risk measures and input. That is, with the same
risk measure, suboptimal portfolios with a higher constraint on return achieve higher
performance ratios than the optimal portfolio. From H4 to L4, the ratios do not show a
pattern of first increasing the decreasing as expected. In other words, the out-of-sample
efficient frontiers are usually non-convex with irregular shapes. Overall, the performance
ratios of CDaR and CVaR optimal portfolios are shown to be not sensitive to changing the
value of return constraint, while the performance ratios of mean-variance optimal portfolio
shows significant change.

Table 5. Performance ratios of suboptimal portfolios with different risk measures.

Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Sharpe Ratio Rachev Ratio
0-CDaR 0.3-CDaR 0.7-CDaR 1-CDaR 0.5-CVaR 0.7-CVaR 0.9-CVaR

0-CDaR
L4 0.061 0.043 0.023 0.008 0.239 0.146 0.074 0.113 0.965
L3 0.058 0.041 0.021 0.007 0.232 0.142 0.071 0.108 0.959
L2 0.061 0.043 0.023 0.007 0.236 0.144 0.072 0.110 0.960
L1 0.062 0.044 0.023 0.007 0.236 0.144 0.072 0.110 0.959
optimal 0.072 0.051 0.027 0.008 0.258 0.156 0.077 0.117 0.965
H1 0.074 0.052 0.028 0.008 0.251 0.151 0.073 0.115 0.968
H2 0.082 0.058 0.030 0.008 0.259 0.157 0.076 0.120 0.993
H3 0.087 0.061 0.032 0.009 0.267 0.161 0.078 0.124 0.995
H4 0.087 0.062 0.032 0.009 0.268 0.162 0.079 0.125 0.989
0.5-CVaR
L4 0.073 0.052 0.027 0.006 0.252 0.154 0.074 0.114 1.011
L3 0.074 0.052 0.027 0.007 0.253 0.155 0.075 0.115 1.011
L2 0.074 0.052 0.027 0.007 0.253 0.155 0.075 0.116 1.008
L1 0.075 0.053 0.027 0.007 0.256 0.156 0.076 0.118 1.006
optimal 0.076 0.054 0.028 0.007 0.259 0.158 0.076 0.120 1.002
H1 0.075 0.053 0.027 0.007 0.255 0.155 0.075 0.118 0.990
H2 0.075 0.053 0.027 0.007 0.256 0.156 0.075 0.119 0.987
H3 0.073 0.052 0.027 0.007 0.256 0.155 0.075 0.119 0.982
H4 0.071 0.050 0.026 0.007 0.254 0.154 0.074 0.117 0.977
J. Risk Financial Manag. 2022, 15, 230 21 of 23

Table 5. Cont.

Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Mean Return Sharpe Ratio Rachev Ratio
0-CDaR 0.3-CDaR 0.7-CDaR 1-CDaR 0.5-CVaR 0.7-CVaR 0.9-CVaR

Standard
Deviation
L4 0.041 0.029 0.015 0.004 0.176 0.110 0.055 0.084 0.990
L3 0.042 0.030 0.016 0.004 0.177 0.111 0.056 0.083 1.005
L2 0.049 0.035 0.019 0.005 0.196 0.122 0.062 0.092 1.013
L1 0.059 0.042 0.022 0.006 0.225 0.138 0.069 0.103 1.005
optimal 0.064 0.045 0.024 0.006 0.238 0.145 0.071 0.109 0.966
H1 0.069 0.049 0.026 0.007 0.232 0.141 0.069 0.108 0.972
H2 0.071 0.050 0.027 0.007 0.232 0.141 0.069 0.110 0.983
H3 0.074 0.052 0.028 0.007 0.237 0.144 0.070 0.113 0.986
H4 0.073 0.052 0.027 0.007 0.234 0.142 0.069 0.112 0.980
DJIA 0.011 0.008 0.004 0.001 0.064 0.040 0.019 0.033 0.855
Equal
0.032 0.023 0.011 0.003 0.136 0.083 0.037 0.065 0.900
Weight
This table presents the performance ratios of suboptimal portfolios with different risk measures. The risk measures
are shown in the row names: 0-CDaR, 0.5-CVaR and standard deviation. The constraint on return is adjusted
from high to low (H4 to L4) to show the impact of suboptimality. Portfolio optimization with tail risk measures
demonstrates smaller variation in out-of-sample performance ratios compared with mean-variance portfolio.

0.4
Equal Weight
H1
H2
H3
log cumulative return

0.3 H4
L1
L2
L3
L4
0.2 Optimal

0.1

0.0

2017 2018 2019 2020

Date

(a)

0.4
Equal Weight
0.4 H1
Equal Weight H2
H1 H3
log cumulative return

H2 0.3 H4
H3 L1
log cumulative return

0.3 H4 L2
L1 L3
L2 L4
L3 Optimal
L4 0.2
0.2 Optimal

0.1
0.1

0.0
0.0

2017 2018 2019 2020 2017 2018 2019 2020

Date Date

(b) (c)

Figure 5. Time series of log cumulative return of suboptimal portfolios with different risk measures.
(a) 0-CDaR Suboptimal portfolios: this figure plots the paths of 0-CDaR suboptimal portfolios from
level H1 to L4, and the equally weighted portfolio. (b) 0.5-CVaR Suboptimal portfolios: this figure
plots the paths of 0.5-CVaR suboptimal portfolios from level H1 to L4, and the equally weighted
portfolio. (c) MV suboptimal portfolios: this figure plots the paths of mean variance suboptimal
portfolios from level H1 to L4, and the equally weighted portfolio.

The portfolios have increasing returns as well as risk from L1 to H4. The realized
paths follow a similar trend and rarely cross. The optimal portfolios, as expected, are in
the medium part of all paths. The 0.5-CVaR suboptimal portfolios have almost identical
performance. Some paths are not visible due to overlap. For example, the constraints on the
return of H4 are sometimes not feasible, leading to the same performance with H3 portfolio.
J. Risk Financial Manag. 2022, 15, 230 22 of 23

6. Conclusions
We propose the MRS-MNTS-GARCH model that is sufficiently flexible to accommo-
date fat tails, skewness and regime switch in asset returns. The model is used to simulate
sample paths of portfolio returns, which serves as input to portfolio optimization with
tail risk measures. We conduct various in-sample and out-of-sample tests to demonstrate
the effectiveness of our approach. In-sample tests show that the NTS distribution fits the
innovations with high accuracy compared with t-distribution. Out-of-sample tests show
that our approach significantly improves the performance of optimal portfolios measured
by performance ratios and it successfully mitigates left tail risk. We also find that out-
of-sample performance ratios of the portfolios with tail risk measures are more robust to
suboptimality on the efficient frontier compared with mean-variance portfolio.

Author Contributions: Conceptualization, C.P. and Y.S.K.; formal analysis, C.P. and Y.S.K.; inves-
tigation, C.P.; data curation, C.P.; methodology, C.P.; visualization, C.P.; writing—original draft
preparation, C.P.; writing—review and editing, Y.S.K. and S.M.; supervision, S.M. All authors have
read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: The data is available at https://finance.yahoo.com (accessed 12
January 2021).
Conflicts of Interest: The authors declare no conflict of interest.

Abbreviations
The following abbreviations are used in this manuscript:

NTS Normal tempered stable

stdMNTS Standard multivariate normal tempered stable
Markov regime-switching GARCH model with normal
MRS-MNTS-GARCH
tempered stable innovation
CVaR Conditional Value-at-Risk
CDaR Conditional Drawdown-at-Risk

References
Anand, Abhinav, Tiantian Li, Tetsuo Kurosaki, and Young Shin Kim. 2016. Foster—Hart optimal portfolios. Journal of Banking &
Finance 68: 117–30.
Barndorff-Nielsen, Ole Eiler, and Sergei Z. Levendorskii. 2001. Feller processes of normal inverse gaussian type. Journal of Business &
Economic Statistics 1: 318–31.
Bianchi, Michele Leonardo, Gian Luca Tassinari, and Frank J. Fabozzi. 2016. Riding with the four horsemen and the multivariate
normal tempered stable model. International Journal of Theoretical and Applied Finance 19: 1650027. [CrossRef]
Biglova, Almira, Sergio Ortobelli, Svetlozar T. Rachev, and Stoyan Stoyanov. 2004. Different approaches to risk estimation in portfolio
theory. The Journal of Portfolio Management 31: 103–12. [CrossRef]
Bollerslev, Tim. 1986. Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics 31: 307–27. [CrossRef]
Bollerslev, Tim. 1990. Modelling the coherence in short-run nominal exchange rates: A multivariate generalized arch model. The
Review of Economics and Statistics 72: 498–505. [CrossRef]
Boyarchenko, Svetlana I., and Sergei Z. Levendorskiĭ. 2000. Option pricing for truncated Lévy processes. International Journal of
Theoretical and Applied Finance 3: 549–52. [CrossRef]
Carr, Peter, Hélyette Geman, Dilip B. Madan, and Marc Yor. 2002. The fine structure of asset returns: An empirical investigation.
Journal of Business 75: 305–32. [CrossRef]
Checkhlov, Alexei, Stanislav Uryasev, and Mickael Zabarankin. 2004. Portfolio optimization with drawdown constraints. Supply Chain
and Finance 2: 209–28.
Checkhlov, Alexei, Stanislav Uryasev, and Mickael Zabarankin. 2005. Drawdown measure in portfolio optimization. International
Journal of Theoretical and Applied Finance 8: 13–58. [CrossRef]
Cheridito, Patrick, and Eduard Kromer. 2013. Reward–risk ratios. Journal of Investment Strategies 3: 3–18. [CrossRef]
J. Risk Financial Manag. 2022, 15, 230 23 of 23

Engle, Robert. 2002. Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional
heteroskedasticity models. Journal of Business & Economic Statistics 20: 339–50.
Engle, Robert F. 1982. Autoregressive conditional heteroscedasticity with estimates of the variance of united kingdom inflation.
Econometrica 50: 987–1007. [CrossRef]
Haas, Markus, and Ji-Chun Liu. 2004. A multivariate regime-switching GARCH model with an application to global stock market and
real estate equity returns. Studies in Nonlinear Dynamics & Econometrics 2: 493–530.
Haas, Markus, Stefan Mittnik, and Marc S. Paolella. 2004. A new approach to Markov-switching GARCH models. Journal of Financial
Econometrics 2: 493–530. [CrossRef]
Hamilton, James D. 1996. Specification testing in markov-switching time-series models. Journal of Econometrics 70: 127–57. [CrossRef]
Henneke, Jan S., Svetlozar T. Rachev, Frank J. Fabozzi, and Metodi Nikolov. 2011. MCMC-based estimation of Markov switching
ARMA–GARCH models. Applied Economics 43: 259–71. [CrossRef]
Kim, Young Shin. 2022. Portfolio optimization and marginal contribution to risk on multivariate normal tempered stable model.
Annals of Operations Research 1–29. [CrossRef]
Kim, Young Shin, Rosella Giacometti, Svetlozar T. Rachev, Frank J. Fabozzi, and Domenico Mignacca. 2012. Measuring financial risk
and portfolio optimization with a non-Gaussian multivariate model. Annals of Operations Research 201: 325–42. [CrossRef]
Kim, Young Shin, Svetlozar T. Rachev, Michele Leonardo Bianchi, Ivan Mitov, and Frank J. Fabozzi. 2011. Time series analysis for
financial market meltdowns. Journal of Banking & Finance 35: 1879–91.
Koponen, Ismo. 1995. Analytic approach to the problem of convergence of truncated Lévy flights towards the gaussian stochastic
process. Physical Review E 52: 1197–99. [CrossRef] [PubMed]
Krokhmal, Pavlo, Stanislav Uryasev, and Grigory Zrazhevsky. 2002. Comparative analysis of linear portfolio rebalancing strategies:
An application to hedge funds. The Journal of Alternative Investments 5: 10–29. [CrossRef]
Krokhmal, Pavlo, Stanislav Uryasev, and Jonas Palmquist. 2001. Portfolio optimization with conditional value-at-risk objective and
constraints. Journal of Risk 4: 43–68. [CrossRef]
Kurosaki, Tetsuo, and Young Shin Kim. 2018. Foster-Hart optimization for currency portfolios. Studies in Nonlinear Dynamics &
Econometrics 23: 1–15.
Laloux, Laurent, Pierre Cizeau, Jean-Philippe Bouchaud, and Marc Potters. 1999. Noise dressing of financial correlation matrices.
Physical Review Letters 83: 1467–70. [CrossRef]
Lim, Andrew E. B., J. George Shanthikumar, and Gah-Yi Vahn. 2011. Conditional value-at-risk in portfolio optimization: Coherent but
fragile. Operations Research Letters 39: 163–71. [CrossRef]
Marcucci, Juri. 2005. Forecasting stock market volatility with regime-switching garch models. Studies in Nonlinear Dynamics &
Econometrics 9: 6. doi: [CrossRef]
Rachev, Svetlozar T., Stoyan V. Stoyanov, and Frank J. Fabozzi. 2008. Advanced Stochastic Models, Risk Assessment, and Portfolio
Optimization: The Ideal Risk, Uncertainty, and Performance Measures. New York: Wiley.
Rockafellar, R. Tyrrell, and Stanislav Uryasev. 2000. Optimization of conditional value-at-risk. Journal of Risk 2: 21–41. [CrossRef]
Sahamkhadam, Maziar, Andreas Stephan, and Ralf Östermark. 2018. Portfolio optimization based on garch-evt-copula forecasting
models. International Journal of Forecasting 34: 497–506. doi: [CrossRef]
Sarykalin, Sergey, Gaia Serraino, and Stan Uryasev. 2014. Value-at-Risk vs. Conditional Value-at-Risk in Risk Management and
Optimization. INFORMS TutORials in Operations Research 270–94. Available online: https://pubsonline.informs.org/doi/abs/10
.1287/educ.1080.0052 (accessed on 13 May 2022). [CrossRef]
Shephard, Neil, Ole E. Barndorff-Nielsen, and University of Aarhus. 2001. Normal Modified Stable Processes. Technical Report 72.
Available online: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.199.5129&rep=rep1&type=pdf (accessed on 13
May 2022).
Shi, Yanlin, and Lingbing Feng. 2016. A discussion on the innovation distribution of the Markov regime-switching GARCH model.
Economic Modelling 23: 278–88. [CrossRef]