David N. DeJong

The power problems of unit root test in time series with autoregressive errors

Abstract Monte Carlo methods are used to study the size and power of serial-correlation-corrected versions of the Dickey-Fuller (1979,1981) unit root tests appropriate when the time series has unknown mean. The modifications do not cause serious size distortions or power deterioration in the white noise case. While studies in the literature have investigated the operating characteristics of these tests in the presence of moving average errors, of particular concern in this paper is the performance of these procedures in the presence of autoregressive errors. The Philips and Perron (1988) and Choi and Philips (1991) procedures are found to suffer from serious size distortions and have very low power when errors are autoregressively correlated. We conclude that even in the most favorable cases, these tests perform poorly against trend-stationary alternatives which are plausible for annual, quarterly, and monthly macroeconomic time series. The augmented Dickey-Fuller procedure, on the other hand, is reasonably well-behaved.

A Bayesian approach to dynamic macroeconomics

Abstract We propose and implement a coherent statistical framework for combining theoretical and empirical models of macroeconomic activity. The framework is Bayesian, and enables the formal yet probabilistic incorporation of uncertainty regarding the parameterization of theoretical models. The approach is illustrated using a neoclassical business-cycle model that builds on the Greenwood et al. (1988, American Economic Review 78, 402–417) variable-utilization framework to study out-of-sample forecasting of output and investment. The forecasts so produced are comparable with those from a Bayesian vector autoregression.

Reconsidering 'Trends and random walks in macroeconomic time series' *

Abstract We employ a Bayesian perspective to identify the type of prior needed to support the inference that most macroeconomic time series follow random walks. For many of the series considered by Nelson and Plosser (1982) the required prior involves assigning very low probability to trendstationary alternatives. When this prior is relaxed trend-stationarity is generally supported, thus the unit root inference seems inappropriate for these series: despite Nelson and Plossers results indicating that macroeconomic time series are not inconsistent with the random walk hypothesis, our results indicate that for most series the trend-stationarity hypothesis is much more likely.

Population growth in U.S. counties, 1840-1990

Abstract We examine the location and growth of the U.S. population using county-level census data from 1840 and 1990. Natural characteristics (e.g., access to water transportation) heavily influenced where populations located in 1840, and produced characteristics in existence in 1840 (e.g., educational infrastructure) had a significant influence on subsequent growth. Evidence of population convergence appears only when the most-heavily-populated counties in 1840 are excluded from the sample. Moreover, when counties located on the western frontier are excluded from the full sample, on the assumption that they were relatively far from their steady-state populations, there is evidence of population divergence.

Russia's Internal Border

In integrated economies, inter-city-price differences can be explained largely by transportation costs. This is not the case in Russia. Here, we argue that this is due to an internal border that separates a region we denote as the Red Belt from the rest of Russia. Regions within the Red Belt exhibit high degrees of price dispersion and thus seem isolated. Moreover, these regions have been relatively slow to adopt economic reforms, and have suffered relatively low growth rates. The impact of the border on price dispersion is shown to be comparable to the impact of the U.S.-Canadian border.

Tariffs and Growth: An Empirical Exploration of Contingent Relationships

A large body of empirical research indicates that countries with low policy-induced trade barriers tend to enjoy rapid growth, ceteris paribus. In contrast, alternative theoretical models suggest that the relationship between trade barriers and growth may be contingent on the level of development. Employing a direct trade-barrier measuread valorem tariff rateswe find evidence of such a contingency: the marginal effect of tariffs on growth is declining in the level of per capita income. Moreover, evidence of a negative relationship between tariffs and growth is apparent only among the worlds rich countries.

Policy reform and growth in post-Soviet Russia

In pursuit of its transition from a command to a market economy, Russia has witnessed enormous regional differences in economic growth rates. Moreover, the implementation of economic reforms has also differed markedly across regions. We analyze whether regional differences in reform policies can account for regional differences in growth rates, and conclude that to a considerable degree, they can. Most notably, we find that regional differences in price liberalization policies exhibit a positive direct correspondence with growth. We also find that regional differences in large-scale privatization exhibit a positive correspondence with the regional formation of new legal enterprises, which in turn exhibits a strong positive correspondence with growth.

Co-integration and trend-stationarity in macroeconomic time series: Evidence from the likelihood function

Abstract A Bayesian approach to analyzing the co-integration inference is developed and applied to data deemed to be co-integrated by Engle and Granger (1987) and Campbell and Shiller (1987); the approach explicity considers trend-stationary alternatives. It is shown that when trend-stationarity is given zero prior probability the data often appear to be co-integrated. When this prior is relaxed the data support trend-stationary representations.

Keynesian Impulses Versus Solow Residuals: Identifying Sources of Business Cycle Fluctuations

We employ a neoclassical business-cycle model to study two sources of business-cycle fluctuations: marginal efficiency of investment shocks, and total factor productivity shocks. The parameters of the model are estimated using a Bayesian procedure that accommodates prior uncertainty about their magnitudes; from these estimates, posterior distributions of the two shocks are obtained. The postwar US experience suggests that both shocks are important in understanding fluctuations, but that total factor productivity shocks are primarily responsible for beginning and ending recessions. Copyright

Regional integration: an empirical assessment of Russia

Abstract Using a statistical model of commodity trade, we quantify the evolution of regional economic integration within Russia during 1995–1999, and explore potential determinants of this evolution. Our integration measure exhibits rich regional variation that, when aggregated to the national level, fluctuates substantially over time. In accounting for this behavior, we draw in part on theoretical models that emphasize the potential role of openness to international trade and regional disparities in income in threatening economic integration. Controlling for a host of additional regional- and national-level variables, we find a strong negative correspondence between openness to international trade and internal economic integration.