手法を比較

	DCC-GARCH（動的条件付き相関）	ARIMA（自己回帰和分移動平均）モデル	コピュラモデル（正規分布、t分布、Clayton、Gumbel、Frank）	極値理論 (EVT)
分野	ファイナンス	計量経済学	ファイナンス	ファイナンス
系統	Regression model	Regression model	Regression model	Regression model
提唱年	2002	2015	1959	2001
提唱者	Robert F. Engle	Box & Jenkins (Box-Jenkins methodology)	Sklar (1959); dependence-concept treatment by Joe (1997)	Coles (textbook treatment); McNeil, Frey & Embrechts
種類	Multivariate volatility model	Univariate time-series model	Dependence model	Tail / extreme-event model
原典	Engle, R. (2002). Dynamic Conditional Correlation: A Simple Class of Multivariate GARCH Models. Journal of Business & Economic Statistics, 20(3), 339-350.	Box, G. E. P., Jenkins, G. M., Reinsel, G. C. & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley. ISBN: 978-1118675021	Sklar, A. (1959). Fonctions de répartition à n dimensions et leurs marges. Publications de l'Institut Statistique de l'Université de Paris, 8, 229-231.	Coles, S. (2001). An Introduction to Statistical Modeling of Extreme Values. Springer. ISBN: 978-1852334598
別名	dynamic conditional correlation, Engle DCC, multivariate GARCH, DCC-GARCH — Dinamik Koşullu Korelasyon	Box-Jenkins model, ARIMA(p,d,q), ARIMA Modeli	copulas, dependence copulas, vine copulas, Kopula Modelleri (Gaussian, t, Clayton, Gumbel, Frank)	EVT, generalized extreme value, generalized Pareto distribution, peaks over threshold
関連	5	5	5	5
概要	DCC-GARCH is Engle's (2002) multivariate volatility model that lets the correlations between several assets change over time. A separate univariate GARCH model is fitted to each series, and then the dynamic correlation matrix is estimated in a second, separate step.	ARIMA is a univariate time-series forecasting model that combines autoregressive, integrated (differencing), and moving-average components to predict a single continuous series from its own past. It is the centrepiece of the Box-Jenkins methodology set out in Box, Jenkins, Reinsel & Ljung's Time Series Analysis (5th ed., 2015).	Copula models are a family of functions that describe the dependence structure between variables separately from their individual (marginal) distributions. The foundation is Sklar's theorem (1959), which shows that any multivariate distribution can be split into its marginals plus a copula; Joe (1997) developed the modern catalogue of dependence concepts. They are central to portfolio risk and credit modelling.	Extreme Value Theory is a statistical framework for modelling the rare events that live in the tail of a probability distribution. As developed in Coles (2001) and applied to risk by McNeil, Frey & Embrechts (2005), it offers two standard routes: the Generalized Extreme Value (GEV) distribution for block maxima and the Generalized Pareto Distribution (GPD), used in the peaks-over-threshold approach, for exceedances above a high threshold.