This paper develops a novel and effective bootstrap method for simulating asymptotic critical values for tests of equal forecast accuracy and encompassing among many nested models. The bootstrap, which combines elements of fixed regressor and wild bootstrap methods, is simple to use.
This chapter provides an overview of pseudo-out-of-sample tests of unconditional predictive ability. We begin by providing an overview of the literature, including both empirical applications and theoretical contributions.
Smooth-transition autoregressive (STAR) models have proven to be worthy competitors of Markov-switching models of regime shifts, but the assumption of a time-invariant threshold level does not seem realistic and it holds back this class of models from reaching their potential usefulness.
We use a simple partial adjustment econometric framework to investigate the effects of the crisis on the dynamic properties of a number of yield spreads. We find that the crisis has caused substantial disruptions revealed by changes in the persistence of the shocks to spreads as much as by in their unconditional mean levels.
Since Galí , long-run restricted VARs have become the standard for identifying the effects of technology shocks. In a recent paper, Francis et al.  proposed an alternative to identify technology as the shock that maximizes the forecast-error variance share of labor productivity at long horizons.
Using formal statistical tests, we detect (i) significant volatility increases for various types of capital flows for a period of changes in business cycle comovement among the G7 countries, and (ii) mixed evidence of changes in covariances and correlations with a set of macroeconomic variables.
Oil prices rose sharply prior to the onset of the 2007-2009 recession. Hamilton (2005) noted that nine of the last ten recessions in the United States were preceded by a substantial increase in the price of oil.
Recent research [e.g., DeMiguel, Garlappi and Uppal, (2009), Rev. Fin. Studies] has cast doubts on the out-of-sample performance of optimizing portfolio strategies relative to naive, equally weighted ones. However, existing results concern the simple case in which an investor has a one-month horizon and meanvariance preferences.
We examine whether simple VARs can produce empirical portfolio rules similar to those obtained under a range of multivariate Markov switching models, by studying the effects of expanding both the order of the VAR and the number/selection of predictor variables included.
The number of commercial banks in the United States has fallen by more than 50 percent since 1984. This consolidation of the U.S. banking industry and the accompanying large increase in average (and median) bank size have prompted concerns about the effects of consolidation and increasing bank size on market competition and on the number of banks that regulators deem “too–big–to–fail.”
Many studies have documented disparities in the regional responses to monetary policy shocks. However, because of computational issues, the literature has often neglected the richest level of disaggregation: the city. In this paper, we estimate the city-level responses to monetary policy shocks in a Bayesian VAR.
It has become common practice to estimate the response of asset prices to monetary policy actions using market-based measures such as the unexpected change in the federal funds futures rate as proxies for monetary policy shocks.
Nearly all journal rankings in economics use some weighted average of citations to calculate a journal’s impact. These rankings are often used, formally or informally, to help assess the publication success of individual economists or institutions.
This paper develops a framework for inferring common Markov-switching components in a panel data set with large cross-section and time-series dimensions. We apply the framework to studying similarities and differences across U.S. states in the timing of business cycles.
Advances in information-processing technology have significantly eroded the advantages of small scale and proximity to customers that traditionally enabled community banks and other small-scale lenders to thrive.
Welfare gains to long-horizon investors may derive from time diversification that exploits non-zero intertemporal return correlations associated with predictable returns. Real estate may thus become more desirable if its returns are negatively serially correlated.
Using a self-exciting threshold autoregressive model, we confirm the presence of nonlinearities in sectoral real exchange rate (SRER) dynamics across Mexico, Canada and the US in the pre-NAFTA and post-NAFTA periods.
We study the cross-section correlations of net, total, and disaggregated capital flows for the major source and recipient European Union countries. We seek evidence of changes in these correlations since the introduction of the euro to understand whether the European Union can be considered a unique entity with regard to its international capital flows.
We analyze the second-moment properties of the components of international capital flows and their relationship to business cycle variables (output, investment, and real interest rate) in 22 industrial and emerging countries.
Motivated by the common finding that linear autoregressive models often forecast better than models that incorporate additional information, this paper presents analytical, Monte Carlo, and empirical evidence on the effectiveness of combining forecasts from nested models. In our analytics, the unrestricted model is true, but a subset of the coefficients are treated as being local-to-zero. This approach captures the practical reality that the predictive content of variables of interest is often low. We derive MSE-minimizing weights for combining the restricted and unrestricted forecasts. Monte Carlo and empirical analyses verify the practical effectiveness of our combination approach.