Jeremy Piger

• University of Oregon

We analyze the propagation of recessions across countries using a model with multiple qualitative state variables in a vector autoregression (VAR). The VAR may include country‐level variables to determine whether policy also propagates across countries. We consider versions of the model with observed discrete states or unobserved discrete states, w...

We investigate the evidence for structural breaks in autoregressive models of U.S. macroeconomic time series. There is substantial model uncertainty associated with such models, including uncertainty related to lag selection, the number of structural breaks, and the specific parameters that break. We develop a feasible approach to Bayesian model av...

Economic time-series data is commonly categorized into a discrete number of persistent regimes. I survey a variety of approaches for real-time prediction of these regimes and the turning points between them, where these predictions are formed in a data-rich environment. I place particular emphasis on supervised machine learning classification techn...

We develop an N -regime Markov-switching model in which the latent state variable driving the regime switching is endogenously determined with the model disturbance term. The model’s structure captures a wide variety of patterns of endogeneity and yields a simple test of the null hypothesis of exogenous switching. We derive an iterative filter that...

Empirical studies of bilateral foreign direct investment (FDI) activity show substantial differences in specifications with little agreement on the set of included covariates. We use Bayesian statistical techniques that allow one to select from a large set of candidates those variables most likely to be determinants of FDI activity. The variables w...

We propose a simple machine-learning algorithm known as Learning Vector Quantization (LVQ) for the purpose of identifying new U.S. business cycle turning points quickly in real time. LVQ is used widely for real-time statistical classification in many other fields, but has not previously been applied to the classification of economic variables, to t...

The Great Recession of 2007-2009 has not only caused a large wealth loss, it was also followed by a sluggish subsequent recovery. Two years after officially emerging from the recession, the economy was still growing at a low pace and payroll employment was far from reaching its previous peak. However, assessment of the employment situation was mark...

Time series analysis of macroeconomic and financial variables requires a deep understanding of many econometric pitfalls if an empirical researcher hopes to avoid making spurious inferences. This understanding is the hallmark of Charles Nelson's research over four decades and it develops out of a healthy skepticism about “conventional wisdom,” yet...

Earnings press releases are the primary mechanism by which managers announce quarterly earnings and make other concurrent disclosures to investors and other stakeholders. A largely unexplored element of earnings press releases is the language that managers use throughout the press release, which we argue provides a unifying framework for these disc...

It has long been recognized that business cycle comovement is greater between countries that trade intensively with one another. Surprisingly, no one has previously examined the relationship between trade intensity and comovement of shocks to the trend level of output. Contrary to the result for cyclical fluctuations, we find that comovement of sho...

A large literature studies the information contained in national-level economic indicators, such as nancial and aggregate economic activity variables, for forecasting U.S. business cycle phases (expansions and recessions.) In this paper, we investigate whether there is additional information regarding business cycle phases contained in subnational...

We consider the extent to which different time-series models can generate simulated data with the same business cycle features that are evident in U.S. real GDP. We focus our analysis on whether multivariate linear models can improve on the previously documented failure of univariate linear models to replicate certain key business cycle features. W...

Earnings press releases are the primary mechanism by which managers announce quarterly earnings and make other concurrent disclosures to investors and other stakeholders. A largely unexplored element of earnings press releases is the language that managers use throughout the press release, which we argue provides a unifying framework for these disc...

We investigate the importance of trend inflation and the real-activity gap for explaining observed inflation variation in G7 countries since 1960. Our results are based on a bivariate unobserved-components model of inflation and unemployment in which inflation is decomposed into a stochastic trend and transitory component. As in recent implementati...

Empirical studies of bilateral foreign direct investment (FDI) activity show substantial differences in specifications with little agreement on the set of covariates that are (or should be) included. We use Bayesian statistical techniques that allow one to select from a large set of candidates those variables most likely to be determinants of FDI a...

The national economy is often described as having a business cycle over which aggregate output enters and exits distinct expansion and recession phases. Analogously, national employment cycles in and out of its own expansion and contraction phases, which are closely related to the business cycle. This paper estimates city-level employment cycles fo...

The "business cycle" is a fundamental, yet elusive concept in macroeconomics. In this paper, we consider the problem of measuring the business cycle. First, we argue for the 'output-gap' view that the business cycle corresponds to transitory deviations in economic activity from a permanent or "trend" level. Then, we investigate the extent to which...

Studies of the predictive ability of the Federal Reserve's Beige Book for aggregate output and employment have proven inconclusive. This might be attributed, in part, to its irregular release schedule. We use a model that allows for data sampling at mixed frequencies to analyze the predictive power of the Beige Book. We find that the Beige Book's n...

We present a new approach to trend/cycle decomposition of time series that follow regime-switching processes. The proposed approach, which we label the "regime-dependent steady-state" (RDSS) decomposition, is motivated as the appropriate generalization of the Beveridge and Nelson decomposition [Beveridge, S., Nelson, C.R., 1981. A new approach to d...

We take a Bayesian approach to model selection in regression models with structural breaks in conditional mean and residual variance parameters. A novel feature of our approach is that it does not assume knowledge of the parameter subset that undergoes structural breaks, but instead conducts model selection jointly over the number of structural bre...

Following Hamilton [1989. A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica 57, 357-384], estimation of Markov regime-switching regressions typically relies on the assumption that the latent state variable controlling regime change is exogenous. We relax this assumption and develop a parsimoni...

We use counterfactual experiments to investigate the sources of the large volatility reduction in US real GDP growth in the 1980s. Contrary to an existing literature that conducts counterfactual experiments based on classical estimation and point estimates, we consider Bayesian analysis that provides a straightforward measure of estimation uncertai...

A number of studies have documented a reduction in aggregate macroeconomic volatility beginning in the early 1980s, i.e., the "Great Moderation." This paper documents the Great Moderation at the state level, finding significant heterogeneity in the timing and magnitude of states' structural breaks. For example, we find that 14 states had breaks tha...

This paper evaluates the ability of formal rules to establish U.S. business cycle turning point dates in real time. We consider two approaches, a nonparametric algorithm and a parametric Markov-switching dynamic-factor model. In order to accurately assess the real-time performance of these rules, we construct a new unrevised "real-time" data set of...

Glossary Definition of the Subject Introduction Threshold and Markov-Switching Models of Regime Change Estimation of a Basic Markov-Switching Model Extensions of the Basic Markov-Switching Model Specification Testing for Markov-Switching Models Empirical Example: Identifying Business Cycle Turning Points Future Directions Bibliography

Studies of the predictive ability of the Federal Reserve's Beige Book, an anecdotal measure of regional economic conditions, for aggregate output and employment have proven inconclusive. This might be attributed, in part, to the irregular release schedule of the Beige Book. In this paper, we use a model that allows for data sampling at mixed freque...

This paper investigates the dynamic relationship between permanent and transitory components of post-war U.S. business cycles. We specify a time-series model for real GNP and consumption in which the two share a common stochastic trend and transitory component, and Markov-regime switching is used to model business cycle phases in these components....

This paper examines the determinants of employment growth in metro areas. To obtain growth rates, we use a Markov-switching model that separates a city's growth path into two distinct phases (high and low), each with its own growth rate. The simple average growth rate over some period is, therefore, the weighted average of the high-phase and low-ph...

In this paper, we develop a Bayesian approach to counterfactual analysis of structural change. Contrary to previous analysis based on classical point estimates, this approach provides a straightforward measure of estimation uncertainty for the counterfactual quantity of interest. We apply the Bayesian counterfactual analysis to examine the sources...

In this paper, we examine whether managers use optimistic and pessimistic language in earnings press releases to provide information about expected future firm performance to the market, and whether the market responds to optimistic and pessimistic language usage in earnings press releases after controlling for the earnings surprise and other facto...

We measure the relative contribution of the deviation of real activity from its equilibrium (the gap), “supply shock” variables, and long-horizon inflation forecasts for explaining the U.S. inflation rate in the post-war period. For alternative specifications for the inflation driving process and measures of inflation and the gap we reach a similar...

This paper examines and compares the recent business cycle experiences of the seven states that lie partly or wholly within the Eighth Federal Reserve District (Arkansas, Illinois, Indiana, Kentucky, Mississippi, Missouri, and Tennessee). For the period surrounding the 1990-91 NBER recession, six of the seven states had recessions that were much sh...

This paper presents a new nonlinear time series model that captures a post-recession 'bounce-back' in the level of aggregate output. While a number of studies have examined this type of business cycle asymmetry using recession-based dummy variables and threshold models, we relate the 'bounce-back' effect to an endogenously estimated unobservable Ma...

The U.S. aggregate business cycle is often characterized as a series of distinct recession and expansion phases. We apply a regime-switching model to state-level coincident indices to characterize state business cycles in this way. We find that states differ a great deal in the levels of growth that they experience in the two phases: Recession grow...

This paper examines and compares the recent business cycle experiences of the seven states that lie partly or wholly within the Eighth Federal Reserve District (Arkansas, Illinois, Indiana, Kentucky, Mississippi, Missouri, and Tennessee). For the period surrounding the 1990-91 NBER recession, six of the seven states had recessions that were much sh...

In this paper, we present a new approach to trend/cycle decomposition under the assumption that the trend is the permanent component and the cycle is the transitory component of an integrated time series. The permanent component is defined as the steady-state level of the series, a definition that has exploitable forecasting implications useful for...

This paper considers the ability of simulated data from linear and nonlinear time-series models to reproduce features in U.S. real GDP data related to business cycle phases. We focus our analysis on a number of linear ARIMA models and nonlinear Markov-switching models. To determine the timing of business cycle phases for the simulated data, we pres...

This paper investigates regime switching in the response of U.S. output to a monetary policy action. We find substantial, statistically significant, time variation in this response that corresponds to "high response" and "low response" regimes. We then investigate whether the timing of the regime shifts are consistent with three particular manifest...

We find evidence that adopting an explicit inflation objective plays a role in anchoring long-run inflation expectations and in reducing the intrinsic persistence of inflation. For the period 1994-2003, private-sector long-run inflation forecasts exhibit significant correlation with lagged inflation for a number of industrial economies, including t...

Using a Bayesian model comparison strategy, we search for a volatility reduction in U.S. real gross domestic product (GDP) growth within the postwar sample. We find that aggregate real GDP growth has been less volatile since the early 1980s, and that this volatility reduction is concentrated in the cyclical component of real GDP. Sales and producti...

We find evidence that inflation targeting (IT) plays a role in anchoring long-run inflation expectations and in reducing the intrinsic persistence of inflation. Over the period since 1994, private-sector long-run inflation forecasts for the United States and the euro area exhibit significant correlation with lagged inflation, whereas this correlati...

This paper presents a new approach to trend/cycle decomposition. The trend of an integrated time series is measured as the conditional expectation of the steady-state level of the series, where steady state is determined by simulation from an appropriate forecasting model. By explicitly linking the trend component to the concept of steady state, ou...

Using a Bayesian model comparison strategy, we search for a volatility reduction in U.S. real gross domestic product (GDP) growth within the postwar sample. We find that aggregate real GDP growth has been less volatile since the early 1980s, and that this volatility reduction is concentrated in the cyclical component of real GDP.Sales and productio...

this paper are as follows: First, because the NBER's decisions represent the consensus of individuals who bring differing techniques to bear on the question of when turning points occur, the dating methodology is neither transparent nor reproducible. Second, the NBER business cycle peaks and troughs are often determined well after the fact. This pr...

This paper investigates the relationship between permanent and transitory components of U.S. recessions in an empirical model allowing for business cycle asymmetry. Using a common stochastic trend representation for real GDP and consumption, we divide real GDP into permanent and transitory components, the dynamics of which are different in booms vs...

We apply both classical and Bayesian econometric methods to characterize the dynamic behavior of inflation for twelve industrial countries over the period 1984-2003, using four different price indices for each country. In particular, we estimate a univariate autoregressive (AR) model for each series, and consider the possibility of a structural bre...

this paper where the two cycle components are plotted, and has been widely noted; see Watson (1986), Stock and Watson (1988) among others. It should surprise us that the unobserved component (UC) and Beveridge-Nelson (BN) methods produce very different trend-cycle decompositions since both are modelbased. Each implies an ARIMA representation. Neith...

Economic forecasters rely on monthly consumer confidence surveys to help them determine the current and future states of the economy. But how reliable are these surveys?

This paper evaluates the ability of a statistical regime-switching model to identify turning points in U.S. economic activity in real time. The authors work with Markov-switching models of real GDP and employment that, when estimated on the entire post-war sample, provide a chronology of business cycle peak and trough dates very close to that produ...

We distinguish between three different ways of using real-time data to estimate forecasting equations and argue that the most popular approach should generally be avoided. The point is illustrated with a model that uses monthly industrial production, employment, and retail sales data to predict real GDP growth. When the model is estimated using our...

We investigate the power and size performance of unit-root tests when the data undergo Markov regime switching. All tests, including those robust to a single break in trend growth rate, have low power against a process with a Markov-switching trend. Under the null hypothesis, we find that previously documented size distortions in Dickey–Fuller-type...

Using Bayesian tests for a structural break at an unknown break date, we search for a volatility reduction within the post-war sample for the growth rates of U.S. aggregate and disaggregate real GDP. We find that the growth rate of aggregate real GDP has been less volatile since the early 1980's, and that this volatility reduction is concentrated i...

This paper investigates the relationship between permanent and transitory components of U.S. recessions in an empirical model allowing for business cycle asymmetry. Using a common stochastic trend representation for real GNP and consumption, we divide real GNP into permanent and transitory components, the dynamics of which are different in booms vs...

This paper investigates the nature of U.S. business cycle asymmetry using a dynamic factor model of output, investment, and consumption. We identify a common stochastic trend and common transitory component by embedding the permanent income hypothesis within a simple growth model. Markov-switching in each component captures two types of asymmetry:...

This paper investigates the relationship between permanent and transitory components of U.S. recessions in an empirical model allowing for business cycle asymmetry. Using a common stochastic trend representation for real GNP and consumption, we divide real GNP into permanent and transitory components, the dynamics of which are different in booms vs...

: We distinguish between three different ways of using real-time data to estimate forecasting equations and argue that the most frequently used approach should generally be avoided. The point is illustrated with a model that uses monthly observations of industrial production, employment, and retail sales to predict real GDP growth. When the model i...

: We investigate the power and size performance of unit root tests when the true data generating process undergoes Markov regime-switching. All tests, including those robust to a single break in trend growth rate, have very low power against a process with a Markov-switching trend growth rate as in Lam (1990). However, for the case of business cycl...

We investigate the power and size performance of unit root tests when the true data generating process undergoes Markov regime-switching. All tests, including those robust to a single break in trend growth rate, have very low power against a process with a Markov-switching trend growth rate as in Lam (1990). However, for the case of business cycle...

This paper investigates the nature of business cycle asymmetry using a dynamic factor model of output, investment, and consumption. We first identify a common stochastic trend and a common transitory component by embedding the permanent income hypothesis within a simple growth model. We then investigate two types of asymmetry commonly identified in...

We investigate the performance of a battery of standard unit root tests when the true data generating process has a Markov-switching trend growth rate and variance. Regime switching under both the null hypothesis of a unit root and the alternative hypothesis of trend stationarity is considered. In contrast to the case of a single break in trend gro...

We consider the extent to which different time-series models can generate simulated data with the same business cycle features that are evident in U.S. real GDP. We focus our analysis on whether omitted variables might explain the previously documented support for nonlinear dynamics when considering the abilities of univariate models to reproduce b...

In this paper, we consider the ability of time-series models to generate simulated data that display the same business cycle features found in U.S. real GDP. Our analysis of a range of popular time-series models allows us to investigate the extent to which multivariate information can account for the apparent univariate evidence of nonlinear dynami...

I consider the problem of accounting for model uncertainty in linear models with multiple struc- tural changes of unknown timing in intercept, slope, and residual variance parameters. A feasible approach to Bayesian Model Averaging (BMA) is developed, where the model space encompasses variable selection, the number of structural changes, and the ty...

Thesis (Ph. D.)--University of Washington, 2000 The dissertation is comprised of three chapters, each investigating Markov-switching models of U.S. business cycle asymmetry. In the first essay, I investigate the performance of a battery of unit root tests in the presence of Markov-switching in trend growth rate and variance, a model commonly used t...