Abstract Bayesian priors are often used to restrain the otherwise highly over‐parametrized vector autoregressive (VAR) models. The currently available VAR methodology does not allow user specify prior beliefs about unconditional mean, or steady state, of system. This is unfortunate as state something that economists usually claim know relatively well. paper develops easily implemented methods for analyzing both stationary and cointegrated VARs, in reduced structural form, with an informative...

This paper analyzes the forecasting performance of an open economy dynamic stochastic general equilibrium (DSGE) model, estimated with Bayesian methods, for Euro area during 1994Q1–2002Q4. We compare DSGE model and a few variants this to various reduced-form models such as vector autoregressions (VARs) error correction (VECM), both by maximum likelihood two different approaches, traditional benchmark models, e.g., random walk. The accuracy point forecasts, interval forecasts predictive...

We propose Subsampling MCMC, a Markov Chain Monte Carlo (MCMC) framework where the likelihood function for $n$ observations is estimated from random subset of $m$ observations. introduce highly efficient unbiased estimator log-likelihood based on control variates, such that computing cost much smaller than full in standard MCMC. The estimate bias-corrected and used two dependent pseudo-marginal algorithms to sample perturbed posterior, which we derive asymptotic error with respect $m$,...

Analysis of functional magnetic resonance imaging (fMRI) data is becoming ever more computationally demanding as temporal and spatial resolutions improve, large, publicly available sets proliferate. Moreover, methodological improvements in the neuroimaging pipeline, such non-linear normalization, non-parametric permutation tests Bayesian Markov Chain Monte Carlo approaches, can dramatically increase computational burden. Despite these challenges, there do not yet exist any fMRI software...

This paper estimates and tests a new Keynesian small open economy model in the tradition of Christiano, Eichenbaum, Evans (2005) Smets Wouters (2003) using Bayesian estimation techniques on Swedish data. To account for switch to an inflation targeting regime 1993 we allow discrete break central bank's instrument rule. A key equation - uncovered interest rate parity (UIP) condition is well known be rejected empirically. Therefore explore consequences modifying UIP negative correlation between...

In this paper we develop a dynamic stochastic general equilibrium (DSGE) model for an open economy, and estimate it on Euro area data using Bayesian estimation techniques. The incorporates several economy features, as well number of nominal real frictions that have proven to be important the empirical fit closed models. offers: i) theoretical development standard DSGE into setting, ii) model, including assesments relative importance various shocks explaining iii) evaluation model's...

There are many indications that formal methods not used to their full potential by central banks today. In this paper we demonstrate how BVAR and DSGE models can be shed light on questions policy makers deal with in practice using data from Sweden. We compare the forecast performance of Riksbank's official, more subjective forecasts, both terms actual forecasts root mean square errors. also discuss combine model- judgment-based show combined performs well out-of-sample. addition, advantages...

Abstract We demonstrate improvements in predictive power when introducing spline functions to take account of highly nonlinear relationships between firm failure and leverage, earnings, liquidity a logistic bankruptcy model. Our results show that modeling excessive nonlinearities yields substantially improved predictions, on the order 70%–90%, compared with standard The model provides several important surprising insights into nonmonotonic relationships. find low-leveraged as well profitable...

A Bayesian reference analysis of the cointegrated vector autoregression is presented based on a new prior distribution. Among other properties, it shown that this distribution distributes its probability mass uniformly over all cointegration spaces for given rank and invariant to choice normalizing variables vectors. Several methods computing posterior number cointegrating relations model parameters are proposed, including an efficient Gibbs sampling approach where inferences determined from...

In this paper we use a Dynamic Stochastic General Equilibrium (DSGE) model for an open economy to examine the role of sticky prices in explaining joint behaviour inflation and fairly large set macroeconomic variables. We find that price stickiness is important feature firms active domestic, export import sectors, even though embodies variable capital utilisation, working-capital channel time-varying target. also document all sectors if markup shocks are allowed be autocorrelated, although...

Regression density estimation is the problem of flexibly estimating a response distribution as function covariates. An important approach to regression uses finite mixture models and our article considers flexible mixtures heteroscedastic (MHR) where normal mixture, with component means, variances, weights all varying Our develops fast variational approximation (VA) methods for inference. motivation that alternative computationally intensive Markov chain Monte Carlo (MCMC) fitting are...

The complexity of the Metropolis-Hastings (MH) algorithm arises from requirement a likelihood evaluation for full data set in each iteration. Payne and Mallick (2015) propose to speed up by delayed acceptance approach where decision proceeds two stages. In first stage, an estimate based on random subsample determines if it is likely that draw will be accepted and, so, second stage uses decide upon final acceptance. Evaluating thus avoided draws are unlikely accepted. We more precise...

In this paper, we compare the empirical properties of closed- and open-economy DSGE models estimated on Euro area data. The comparison is made along several dimensions; examine in terms their marginal likelihoods, forecasting performance, variance decompositions, transmission mechanisms monetary policy.