A copula entropy approach to correlation measurement at the country level
Introduction
Correlation is an important measure in finance research which is widely applied in many finance applications, such as risk management, banking business, pricing, etc. There are two kinds of correlation relationships involved in financial data: One kind is a linear relationship which mainly exists in regression models measured by covariance and correlation coefficient, and it is based on the multivariate normal distribution to model the dependence structure between financial returns [31]. The potent problem is that the method of linear relationship ignores some fluctuations such as high peak and fat tail relative to kurtosis and skewness, which have been frequently reported in financial data analyses. If the sample is not large enough, the normality assumption is untenable or, at least, questionable. Under this situation, it is impossible to measure nonlinear dependence and it is possible to underestimate risk [10], [22], [31].
The other type of dependence relationship is measured by copula due to Sklar [29], which has been observed in nonlinear dependence researches and has received a lot of attention [1], [10], [21], [22], [31]. A copula is a function that links together univariate distribution functions to form a flexible multivariate distribution instead of a multivariate normal distribution. The theorem shows that any n-dimensional joint distribution function may be decomposed into n marginal distributions and the copula completely describes the dependence between the n variables [19]. Thus, the copula is a special multivariate distribution function which fully captures asymmetric dependence and tail dependence of the data used in many studies. Thus, the implication is that correlation represents an illustration of dependence, but dependence should not be taken to be synonymous with correlation.
Several recent papers have applied the copula theory to study the dependence among financial variables. Examples include, but are not limited to, these studies: Patton [21] who studies the dependence among major foreign exchange rates and develops conditional copulas which allow for a time-varying dependence space; Hu [10] who uses mixed copula functions to examine the dependence among financial markets; and Xu [31] who uses a copula-based model to structure the portfolio model.
In this paper, we use copula and the definition of entropy to structure nonlinear dependence. The entropy value is obtained from the copula function in order to develop our copula entropy models.
The definition of “entropy” is generated from the field of thermodynamics and statistical mechanics to represent a measure of disorder. Shannon [27] uses a similar measure for information in his theory of communication and devises an entropy function to estimate the average information content associated with a random variable. After that, entropy has been considered as a useful statistical tool to measure volatilities from observed market prices in economics and finance studies [8], [9], [25], [30]. Unlike the variance and the regression model, entropy has the advantage of depending on more moments than just the second moment which allows only for measuring the dispersion around the mean. Consequently, entropy depends on much more information about a vector of random variables than its variance–covariance matrix.
Entropy optimization models, which are based on the Jaynes’s principle [11] of maximum entropy, have been widely used in uncertainty and risk measurement recently. The rationale behind the proposed principle of maximum entropy is that the desired probability distribution has maximum uncertainty (minimum information content), subject to representative and known information (some of which can be explicitly stated).
Virtually all the applications of entropy in finance have focused on forecasting and measurement research with the probabilistic description of the future market price of a common stock traded in an open securities market, such as portfolio optimization, derivatives pricing, credit risk measurement, etc. The principle of maximum entropy provides a method of generating a probability distribution from limited information. Philippatos and Wilson [23] refer entropy to portfolio and market risk measurement and propose a model with entropy, instead of using the traditional mean–variance approach to portfolios for inferring risk-neutral probabilities. It was considered as the first attempt to use entropy to measure the risk in finance. Since then, many relative studies [8], [9], [16], [18], [24] have been born.
Entropy was used as a criterion to choose the most fitted copula function in the copula family [1], [4]. As a matter of fact, the entropy principle could be used jointly with copula. Thus, the objective of this research is to present a copula entropy approach based on the entropy theory and copula theory to measure the dependence relationship between the financial variables, with practical applications.
The paper is organized as follows. Section 2 presents the definition of copula entropy, its mathematical properties, and the extensions of Jaynes’s entropy theory. In Section 3, we compare the copula entropy approach with mutual information and the linear correlation coefficient. Section 4 provides empirical evidence of the copula entropy approach. Finally, Section 5 concludes the paper.
Section snippets
Definition and basic properties of copula entropy
The definitions of Shannon entropy [27] have the discrete form given by Eq. (1) that can be rewritten into the continuous form denoted by Eq. (2) [3], [15], [17]:There is a prevalent assumption underlying the principle of maximum entropy [11], namely, and the entropy variables are mutually independent in an entropy model. However, if we would like to describe the entropy variables with dependence, the copula theory is needed. Based on the theory
Copula entropy and mutual information
In probability theory and information theory [2], [7], the mutual information of two random variables is a quantity that measures the mutual dependence of the two variables. The most common unit of measurement of mutual information is “bit”, when the logarithms with the base 10 (denoted by log) are used. Formally, the mutual information of two discrete random variables X and Y can be defined as:where p(x, y) is the joint p.d.f. of X and Y, and p1(x) and p
Data statistics and problems revealed
One primary stock index per county is chosen for examining the economic dependence among the different stock indexes. The data on Pri are the weekly close price of the stock index returns over the period from January 1, 1990 to March 1, 2010 collected from the WRDS site.
The sample is composed of 12 stocks indexes from 12 countries selected by two methods. First, they are chosen from three economic circles, the European Union (EU), the North American Free Trade Agreement (NAFTA), and the
Conclusion
In this research, the copula entropy model was constructed by the copula and the entropy theory. Thus the copula entropy model covers the advantages of both of them. It is not limited to measuring the linear correlation; it also can capture the nonlinear correlation. It not only measures the degree of the dependence, but considers the structure.
The entropy theory was expanded. In the function of constrained optimization, the copula entropy can be considered as the objective function. Also, the
Acknowledgments
Then authors would like to express our warm thanks to the anonymous referees of this Journal for their helpful and invaluable comments and suggestions that have led to important and significant improvements. The usual disclaimer applied.
References (32)
Recovering copulas from limited information and an application to asset allocation
J. Banking Finance
(2011)- et al.
On the recovery of joint distributions from limited information
J. Economet.
(2002) Estimating market shares in each market segment using the information entropy concept
Appl. Math. Comput.
(2007)- et al.
A note on a minimax rule for portfolio selection and equilibrium price system
Appl. Math. Comput.
(2009) - et al.
Dependence structure and risk measure
J. Bus.
(2003) - et al.
Clustering by compression
IEEE Trans. Inform. Theory
(2005) - et al.
Empirical copulas for CDO tranche pricing using relative entropy
Int. J. Theoretical. Appl. Finance
(2007) - et al.
Modeling Dependence with Copulas and Applications to Risk Management
(2003) - et al.
Nonlinear Time Series: Nonparametric and Parmetric Methods
(2003) Information Theory with Applications
(1977)
The entropy theory of bond option pricing
Int. J. Theor. Appl. Finance
Dependence patterns across financial markets: a mixed copula approach
Appl. Finance Econ.
Information theory and statistical mechanics
Phys. Rev.
The shape of neural dependence
Neural Comput.
Discrete copulas
IEEE Trans. Fuzzy. Syst.
Cited by (32)
A multiphase information fusion strategy for data-driven quality prediction of industrial batch processes
2022, Information SciencesCitation Excerpt :MI is a measure of nonlinear associations in information theory, which has been used for the critical variable selection of assembly quality prediction of diesel engines [35], schedule forecast of wafer manufacturing [36], and air temperature forecast [37]. Thomas et al. [38] pointed out that it is challenging to calculate MI accurately, so maximal information coefficient [39] and copula entropy [40] are proposed as the approximate estimators of MI. Although these advanced association analysis methods have achieved competitive results on real-world datasets, most of them focus on binary correlation and ignore the one-to-many cases.
Approximate entropy and sample entropy algorithms in financial time series analyses
2022, Procedia Computer SciencePredicting the portfolio risk of high-dimensional international stock indices with dynamic spatial dependence
2022, North American Journal of Economics and FinanceCitation Excerpt :The dependence of stock indices is a key aspect of global asset allocation, as dependence should be computed before predicting investment risk. Among the various types of asset dependence, linear correlation involves normally distributed random variables and has been broadly investigated (Zhao, & Lin, 2011). However, this type of correlation ignores a distribution’s high peak and fat tail, which are common in financial research (Chen, Wei, Lang, Lin, & Liu, 2014; Mensah, & Alagidede, 2017).
A GLM copula approach for multisite annual streamflow generation
2021, Journal of HydrologyCitation Excerpt :Thus, CE is a useful multivariate estimator of MI. CE has been used to measure the association between stock market variables (Zhao and Lin, 2011), multiple degradation processes (Sun et al., 2019) and river flows (Chen et al., 2013). It was also used as a performance measure in feature selection for rainfall-runoff modeling and drought prediction (Chen et al., 2014; Huang and Zhang, 2019) and in selecting vine copula structure for multisite streamflow simulation (Ni et al., 2020).
Flood forecasting and error simulation using copula entropy method
2021, Advances in Streamflow Forecasting: From Traditional to Modern ApproachesJoint dependence distribution of data set using optimizing Tsallis copula entropy
2019, Physica A: Statistical Mechanics and its Applications