EconStor >
Humboldt-Universität zu Berlin >
Sonderforschungsbereich 649: Ökonomisches Risiko, Humboldt-Universität Berlin >
SFB 649 Discussion Papers, HU Berlin >

Please use this identifier to cite or link to this item:
Title:JBendge: an object-oriented system for solving, estimating and selecting nonlinear dynamic models PDF Logo
Authors:Winschel, Viktor
Krätzig, Markus
Issue Date:2008
Series/Report no.:SFB 649 discussion paper 2008,034
Abstract:We present an object-oriented software framework allowing to specify, solve, and estimate nonlinear dynamic general equilibrium (DSGE) models. The implemented solution methods for finding the unknown policy function are the standard linearization around the deterministic steady state, and a function iterator using a multivariate global Chebyshev polynomial approximation with the Smolyak operator to overcome the course of dimensionality. The operator is also useful for numerical integration and we use it for the integrals arising in rational expectations and in nonlinear state space filters. The estimation step is done by a parallel Metropolis-Hastings (MH) algorithm using a linear or nonlinear state space filters. Implemented are the Kalman, Extended Kalman, Particle, Smolyak Kalman, Smolyak Sum, and Smolyak Kalman Particle filters. The MH sampling step can be monitored and controlled interactively by sequence and statistics plots. The number of parallel threads can be adjusted to benefit from multiprocessor environments. JBendge is based on the framework JStatCom, which provides a standardized application interface. All tasks are supported by an elaborate multi-threaded graphical user interface (GUI) with project management and data handling facilities.
Subjects:Dynamic stochastic general equilibrium (DSGE) models
Bayesian time series econometrics
software development
Document Type:Working Paper
Appears in Collections:SFB 649 Discussion Papers, HU Berlin

Files in This Item:
File Description SizeFormat
57173135X.PDF935.92 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.