Personal tools

9th International Conference on Social Science Methodology: Estimation of Stochastic Differential Equations with Time Series, Panel and Spatial Data.

Session Title: Estimation of Stochastic Differential Equations with Time Series, Panel and Spatial Data.

Session Convenor(s):

Hermann Singer (hermann.singer@fernuni-hagen.de), FernUniversitaet in Hagen.

Fakultaet fuer Wirtschaftswissenschaft, Lehrstuhl fuer angewandte Statistik und Methoden der empirischen Sozialforschung, Postfach 940, D-58084 Hagen

Session Information:

Stochastic differential equations (SDE) describe the time evolution of random vectors in continuous time. In the social sciences and economics, only discrete time (sampled) measurements are available (e.g. daily, weekly, quarterly etc.). Then, the drift and diffusion parameters of the continuous time system (SDE) must be estimated on time series, panel or spatial data. The likelihood function for sampled measurements can be obtained exactly only in the linear case, whereas for nonlinear systems, in most cases, only approximations can be computed. More generally, a measurement equation can be joined (continuous-discrete state space model) in order to model measurement error and latent variables. The session will invite papers on parameter and state estimation of SDE and continuous-discrete state space models including: application of linear systems (filtering and structural equations methods), approximate nonlinear filters (linearization and numerical integration; EKF, GHF etc.), analytical and Monte Carlo approximations, as well as Bayesian methods.

Share this page: