Comparer des méthodes

	Modèle Multifractal à Commutation Markovienne	Autoregressive Vectoriel (VAR)
Domaine	Séries temporelles	Économétrie
Famille	Process / pipeline	Regression model
Année d'origine	2004	1980
Auteur d'origine	Luc E. Calvet	Christopher A. Sims
Type	Stochastic volatility model	Multivariate time-series model
Source fondatrice	Calvet, L. E., & Fisher, A. J. (2004). How to forecast long-run volatility: regime-switching and the estimation of multifractal processes. Journal of Financial Econometrics, 2(1), 49–83.	Sims, C. A. (1980). Macroeconomics and Reality. Econometrica, 48(1), 1–48.
Alias	MSM, Markov-switching multifractal volatility	VAR, VAR model, vector autoregressive model, multivariate autoregression
Apparentées	3	5
Résumé	The Markov-Switching Multifractal (MSM) model is a flexible framework for capturing time-varying volatility and long-memory effects in financial time series. Developed by Calvet and Fisher (2004), it combines Markov chain theory with multifractal scaling principles to generate volatility that exhibits multiple frequency components, each switching between high and low regimes. This approach is particularly effective for modeling asset returns with realistic fat tails and clustered volatility.	Vector Autoregression is a multivariate time-series model in which each variable is regressed on its own lags and the lags of all other variables in the system. Originally proposed by Sims (1980) as a data-driven alternative to large structural macroeconomic models, VAR has become the standard workhorse for dynamic analysis in empirical economics and finance.