Ricerca
Risultati della ricerca

Creator: Martin, Vance, 1955 and Pagan, Adrian R. Series: Simulationbased inference in econometrics Abstract: Procedures for computing the parameters of a broad class of multifactor continuous time models of the term structure based on indirect estimation methods are proposed. The approach consists of simulating the unknown factors from a set of stochastic differential equations which are used to compute synthetic bond yields. The bond yields are calibrated with actual bond yields via an auxiliary model. The approach circumvents many of the difficulties associated with direct estimation of this class of models using maximum likelihood. In particular, the paper addresses the identification issues arising from singularities in the yields and spreads which tend not to be recognised in existing estimation procedures and thereby overcome potential misspecification problems inherrent in direct methods. Indirect estimates of single and multifactor models are computed and compared with the estimates based on existing estimation procedures.
Parola chiave: Continous time models, Indirect estimation, Multifactor models, Term structure, Testing factor models, Stochastic differential equations, and Singularities Soggetto: C30  Multiple or simultaneous equation models  General, C51  Econometric modeling  Model construction and estimation, and G12  General financial markets  Asset pricing ; Trading volume ; Bond interest rates 
Creator: Wallace, Neil Series: Working paper (Federal Reserve Bank of Minneapolis. Research Department) Number: 024 Abstract: In "Liquidity Preference as Behavior Towards Risk," Tobin suggests that risk aversion and expected utility maximization can provide a rigorous foundation for an equilibrium demand for money. In Tobin's model, money plays a risk reducing role in individual portfolios. This note considers whether a general equilibrium stochastic model can produce equilibrium yield distributions that allow money to play that role if money does not appear directly as an argument in the utility or production functions of the economy. The model examined, a stochastic production variant of Samuelson's model of overlapping generations, cannot produce such yield distributions.
Parola chiave: Risk aversion, Stochastic, and Monetary economy Soggetto: E41  Demand for Money, C51  Model Construction and Estimation, and G11  Portfolio Choice; Investment Decisions 
Creator: Roberds, William Series: Working paper (Federal Reserve Bank of Minneapolis. Research Department) Number: 261 Abstract: A method is presented for solving a certain class of hierarchical rational expectations models, principally models that arise from Stackelberg dynamic games. The method allows for numerical solution using spectral factorization algorithms, and estimation of these models using standard maximum likelihood techniques.
Parola chiave: Rational expectations theory, Stackelberg dynamic game, and Oligopoly model Soggetto: C13  Estimation: General and C73  Stochastic and Dynamic Games; Evolutionary Games; Repeated Games 
Creator: FernandezVillaverde, Jesus. and RubioRamírez, Juan Francisco. Series: Joint committee on business and financial analysis Abstract: This paper presents a method to perform likelihoodbased inference in nonlinear dynamic equilibrium economies. This type of models has become a standard tool in quantitative economics. However, existing literature has been forced so far to use moment procedures or linearization techniques to estimate these models. This situation is unsatisfactory: moment procedures suffer from strong small samples biases and linearization depends crucially on the shape of the true policy functions, possibly leading to erroneous answers. We propose the use of Sequential Monte Carlo methods to evaluate the likelihood function implied by the model. Then we can perform likelihoodbased inference, either searching for a maximum (QuasiMaximum Likelihood Estimation) or simulating the posterior using a Markov Chain Monte Carlo algorithm (Bayesian Estimation). We can also compare different models even if they are nonnested and misspecified. To perform classical model selection, we follow Vuong (1989) and use the KullbackLeibler distance to build Likelihood Ratio Tests. To perform Bayesian model comparison, we build Bayes factors. As an application, we estimate the stochastic neoclassical growth model.
Parola chiave: Likelihoodbased inference, Dynamic equilibrium economies, Sequential Monte Carlo methods, and Nonlinear filtering Soggetto: C15  Statistical Simulation Methods: General, C13  Estimation: General, C10  Econometric and Statistical Methods and Methodology: General, and C11  Bayesian Analysis: General 
Creator: Gourieroux, Christian, 1949, Renault, Eric., and Touzi, Nizar. Series: Simulationbased inference in econometrics Abstract: This paper is interested in the small sample properties of the indirect inference procedure which has been previously studied only from an asymptotic point of view. First, we highlight the fact that the Andrews (1993) medianbias correction procedure for the autoregressive parameter of an AR(1) process is closely related to indirect inference; we prove that the counterpart of the medianbias correction for indirect inference estimator is an exact bias correction in the sense of a generalized mean. Next, assuming that the auxiliary estimator admits an Edgeworth expansion, we prove that indirect inference operates automatically a second order bias correction. The latter is a well known property of the Bootstrap estimator; we therefore provide a precise comparison between these two simulation based estimators.
Parola chiave: Edgeworth correction, Econometrics, Bootstrap, Bias correction, Economic models, Indirect inference, and Simulation Soggetto: C13  Econometric and statistical methods : General  Estimation, C15  Econometric and statistical methods : General  Simulation methods, C32  Multiple or simultaneous equation models  Timeseries models ; Dynamic quantile regressions, and C22  Single equation models ; Single variables  Timeseries models ; Dynamic quantile regressions 


