Showing results 1 to 8 of approximately 8.(refine search)
Solving linear rational expectations models: a horse race
This paper compares the functionality, accuracy, computational efficiency, and practicalities of alternative approaches to solving linear rational expectations models, including the procedures of (Sims, 1996), (Anderson and Moore, 1983), (Binder and Pesaran, 1994), (King and Watson, 1998), (Klein, 1999), and (Uhlig, 1999). While all six procedures yield similar results for models with a unique stationary solution, the AIM algorithm of (Anderson and Moore, 1983) provides the highest accuracy; furthermore, this procedure exhibits significant gains in computational efficiency for larger-scale ...
A weekly perfect foresight model of the nonborrowed reserve operating procedure
Of the many studies analyzing the Federal Reserve's post-October 6, 1979 nonborrowed reserve (NBR) operating procedure, none has focused upon weekly money market dynamics under rational expectations. This paper employs the rational expectations assumption in an explicit institutional model of the NBR procedure. The paper is positive rather than normative, isolating the policy elements that comprise the procedure and investigating their dynamic interaction.
Using a projection method to analyze inflation bias in a micro-founded model
Since Kydland and Prescott (1977) and Barro and Gordon (1983), most studies of the problem of the inflation bias associated with discretionary monetary policy have assumed a quadratic loss function. We depart from the conventional linear-quadratic approach to the problem in favor of a projection method approach. We investigate the size of the inflation bias that arises in a microfounded nonlinear environment with Calvo price setting. The inflation bias is found to lie between 1% and 6% for a reasonable range of parameter values, when the bias is defined as the steady-state deviation of the ...
Reliably Computing Nonlinear Dynamic Stochastic Model Solutions: An Algorithm with Error Formulas
This paper provides a new technique for representing discrete time nonlinear dynamic stochastic time invariant maps. Using this new series representation, the paper augments the usual solution strategy with an additional set of constraints thereby enhancing algorithm reliability. The paper also provides general formulas for evaluating the accuracy of proposed solutions. The technique can readily accommodate models with occasionally binding constraints and regime switching. The algorithm uses Smolyak polynomial function approximation in a way which makes it possible to exploit a high degree of ...
A reliable and computationally efficient algorithm for imposing the saddle point property in dynamic models
This paper describes a set of algorithms for quickly and reliably solving linear rational expectations models. The utility, reliability and speed of these algorithms are a consequence of 1) the algorithm for computing the minimal dimension state space transition matrix for models with arbitrary numbers of lags or leads, 2) the availability of a simple modeling language for characterizing a linear model and 3) the use of the QR Decomposition and Arnoldi type eigenspace calculations. The paper also presents new formulae for computing and manipulating solutions for arbitrary exogenous processes.
A Coherent Framework for Predicting Emerging Market Credit Spreads with Support Vector Regression
We propose a coherent framework using support vector regression (SRV) for generating and ranking a set of high quality models for predicting emerging market sovereign credit spreads. Our framework adapts a global optimization algorithm employing an hv-block cross-validation metric, pertinent for models with serially correlated economic variables, to produce robust sets of tuning parameters for SRV kernel functions. In contrast to previous approaches identifying a single "best" tuning parameter setting, a task that is pragmatically improbable to achieve in many applications, we proceed with ...
Higher-order perturbation solutions to dynamic, discrete-time rational expectations models
We present an algorithm and software routines for computing nth order Taylor series approximate solutions to dynamic, discrete-time rational expectations models around a nonstochastic steady state. The primary advantage of higher-order (as opposed to first- or second-order) approximations is that they are valid not just locally, but often globally (i.e., over nonlocal, possibly very large compact sets) in a rigorous sense that we specify. We apply our routines to compute first- through seventh-order approximate solutions to two standard macroeconomic models, a stochastic growth model and a ...