Efficient Iterative Maximum Likelihood Estimation of High-Parameterized Time Series Models

32 Pages Posted: 1 Oct 2014

See all articles by Nikolaus Hautsch

Nikolaus Hautsch

University of Vienna - Department of Statistics and Operations Research; Center for Financial Studies (CFS); Vienna Graduate School of Finance (VGSF)

Ostap Okhrin

Humboldt University of Berlin - School of Business and Economics

Alexander Ristig

Date Written: January 20, 2014

Abstract

We propose an iterative procedure to efficiently estimate models with complex log-likelihood functions and the number of parameters relative to the observations being potentially high. Given consistent but inefficient estimates of sub-vectors of the parameter vector, the procedure yields computationally tractable, consistent and asymptotic efficient estimates of all parameters. We show the asymptotic normality and derive the estimator's asymptotic covariance in dependence of the number of iteration steps. To mitigate the curse of dimensionality in high-parameterized models, we combine the procedure with a penalization approach yielding sparsity and reducing model complexity. Small sample properties of the estimator are illustrated for two time series models in a simulation study. In an empirical application, we use the proposed method to estimate the connectedness between companies by extending the approach by Diebold and Yilmaz (2014) to a high-dimensional non-Gaussian setting.

Keywords: Multi-Step estimation, Sparse estimation, Multivariate time series, Maximum likelihood estimation, Copula

JEL Classification: C18, C32, C52

Suggested Citation

Hautsch, Nikolaus and Okhrin, Ostap and Ristig, Alexander, Efficient Iterative Maximum Likelihood Estimation of High-Parameterized Time Series Models (January 20, 2014). Available at SSRN: https://ssrn.com/abstract=2385880 or http://dx.doi.org/10.2139/ssrn.2385880

Nikolaus Hautsch (Contact Author)

University of Vienna - Department of Statistics and Operations Research ( email )

Oskar-Morgenstern-Platz 1
Vienna, A-1090
Austria

Center for Financial Studies (CFS) ( email )

Gr├╝neburgplatz 1
Frankfurt am Main, 60323
Germany

Vienna Graduate School of Finance (VGSF) ( email )

Welthandelsplatz 1
Vienna, 1020
Austria

Ostap Okhrin

Humboldt University of Berlin - School of Business and Economics ( email )

Unter den Linden 6
Berlin, AK Berlin 10099
Germany

No contact information is available for Alexander Ristig

Register to save articles to
your library

Register

Paper statistics

Downloads
35
Abstract Views
257
PlumX Metrics