Nonparametric rank tests for non-stationary panels

We develop a set of nonparametric rank tests for non-stationary panels based on multivariate variance ratios which use untruncated kernels. As such, the tests do not require the choice of tuning parameters associated with bandwidth or lag length and also do not require choices with respect to numbers of common factors. The tests allow for unrestricted cross-sectional dependence and dynamic heterogeneity among the units of the panel, provided simply that a joint functional central limit theorem holds for the panel of differenced series. We provide a discussion of the relationships between our setting and the settings for which first- and second generation panel unit root tests are designed. In Monte Carlo simulations we illustrate the small-sample performance of our tests when they are used as panel unit root tests under the more restrictive DGPs for which panel unit root tests are typically designed, and for more general DGPs we also compare the small-sample performance of our nonparametric tests to parametric rank tests. Finally, we provide an empirical illustration by testing for income convergence among countries.

A panel bootstrap cointegration test

This paper proposes a bootstrap test for the null hypothesis of cointegration in panel data. The test is general enough to allow for dependence both within and between the cross-sectional units, and is shown to work well in small samples. © 2007 Elsevier B.V. All rights reserved.

A note on the pooling of individual panic unit root tests

One of the most cited studies in recent years within the field of nonstationary panel data analysis is that of Bai and Ng (2004), in which the authors propose PANIC, a new framework for analyzing the nonstationarity of panels with idiosyncratic and common components. The problem is that the asymptotic validity of PANIC as a platform for constructing pooled panel unit root tests based on averaging is not fully proven. This paper provides the required results, whose usefulness is verified through simulations. © 2009 Cambridge University Press.

A simple test for cointegration in dependent panels with structural breaks

This paper develops a very simple test for the null hypothesis of no cointegration in panel data. The test is general enough to allow for heteroskedastic and serially correlated errors, unit-specific time trends, cross-sectional dependence and unknown structural breaks in both the intercept and slope of the cointegrated regression, which may be located at different dates for different units. The limiting distribution of the test is derived, and is found to be normal and free of nuisance parameters under the null. A small simulation study is also conducted to investigate the small-sample properties of the test. In our empirical application, we provide new evidence concerning the purchasing power parity hypothesis. © Blackwell Publishing Ltd and the Department of Economics, University of Oxford, 2008.

New simple tests for panel cointegration

In this paper, two new simple residual-based panel data tests are proposed for the null of no cointegration. The tests are simple because they do not require any correction for the temporal dependencies of the data. Yet they are able to accommodate individual specific short-run dynamics, individual specific intercept and trend terms, and individual specific slope parameters. The limiting distributions of the tests are derived and are shown to be free of nuisance parameters. The Monte Carlo results in this paper suggest that the asymptotic results are borne out well even in very small samples. Copyright © Taylor & Francis, Inc.

Pooled unit root tests in panels with a common factor

This paper proposes new pooled panel unit root tests that are appropriate when the data exhibit cross-sectional dependence that is generated by a single common factor. Using sequential limit arguments, we show that the tests have a limiting normal distribution that is free of nuisance parameters and that they are unbiased against heterogenous local alternatives. Our Monte Carlo results indicate that the tests perform well in comparison to other popular tests that also presumes a common factor structure for the cross-sectional dependence.

Panel cointegration and the monetary exchange rate model

This paper re-examines the validity of the monetary exchange rate model during the post-Bretton Woods era for 18 OECD countries. Our analysis simultaneously considers the presence of both cross-sectional dependence and multiple structural breaks, which have not received much attention in previous studies of the monetary model. The empirical results indicate that the monetary model emerges only when the presence of structural breaks and cross-country dependence has been taken into account. Evidence is also provided suggesting that the breaks in the monetary model can be derived from the underlying purchasing power parity relation. © 2008 Elsevier B.V. All rights reserved.

Error-correction-based cointegration tests for panel data

This article describes a new Stata command called xtwest, which implements the four error-correction-based panel cointegration tests developed by Westerlund (2007). The tests are general enough to allow for a large degree of heterogeneity, both in the long-run cointegrating relationship and in the short-run dynamics, and dependence within as well as across the cross-sectional units.

Is there really a unit root in the inflation rate? More evidence from panel data models

Time series unit root evidence suggests that inflation is nonstationary. By contrast, when using more powerful panel unit root tests, Culver and Papell (1997) find that inflation is stationary. In this article, we test the robustness of this result by applying a battery of recent panel unit root tests. The results suggest that the stationarity of inflation holds even after controlling for cross-sectional dependence and structural change.

Agriculture, trade openness and emissions: an empirical analysis and policy options

This article investigates the impact of sectoral production allocation, energy usage patterns and trade openness on pollutant emissions in a panel consisting of high-, medium- and low-income countries. Extended STIRPAT (Stochastic Impact by Regression on Population, Affluence and Technology) and EKC (Environmental Kuznets Curve) models are conducted to systematically identify these factors driving CO2 emissions in these countries during the period 1980–2010. To this end, the studyemploys three different heterogeneous, dynamic mean group-type linear panel modelsand one nonlinear panel data estimation procedure that allows for cross-sectionaldependence. While affluence, nonrenewable energy consumption and energy intensity variables are found to drive pollutant emissions in linear models, population is also found to be a significant driver in the nonlinear model. Both service sector and agricultural value-added levels play a significant role in reducing pollution levels, whereas industrialisation increases pollution levels. Although the linear model fails totrack any significant impact of trade openness, the nonlinear model finds trade liberalisation to significantly affect emission reduction levels. All of these results suggest that economic development, and especially industrialisation strategies and environmental policies, need to be coordinated to play a greater role in emission reduction due to trade liberalisation.

The local power of the CADF and CIPS panel unit root tests

Very little is known about the local power of second generation panel unit root tests that are robust to cross-section dependence. This article derives the local asymptotic power functions of the cross-section argumented Dickey–Fuller Cross-section Augmented Dickey-Fuller (CADF) and CIPS tests of Pesaran (2007), which are among the most popular tests around.

Urbanization, openness, emissions, and energy intensity: a study of increasingly urbanized emerging economies

This paper analyses the impact of urbanization and trade openness on emissions and energy intensity in twenty-two increasingly urbanized emerging economies. We employ three second-generation heterogeneous linear panel models as well as recently developed nonlinear panel estimation techniques allowing for cross-sectional dependence. The empirical results show that population density and affluence increase emissions and energy intensity while renewable energy seems to be dormant in these emerging economies, but non-renewable energy increases both CO2 emissions and energy intensity. In addition, openness significantly reduces both pollutant emissions and energy intensity whereas urbanization significantly increases energy intensity, but it is insignificant in increasing emissions. This may be, in part, due to the recent increasing trend in adopting cleaner technologies in these increasingly urbanized developing economies.

Asymmetric oil shocks and external balances of major oil exporting and importing countries

This study investigates the effects of oil price shocks on three measures of oil exporters' and oil importers' external balances: total trade balance, oil trade balance and non-oil trade balance. We employ three second-generation heterogeneous linear panel models and one recently developed non-linear panel estimation technique that allows for cross-sectional dependence. With respect to 28 major oil exporting countries, an increase in oil prices leads to an improved real oil trade balance, although it is detrimental to non-oil and total trade balances. This finding might be due to the expenditure effect arising from increases in proceeds from oil exports. A decrease in oil prices is found to be beneficial for both total and oil trade balances in these oil exporting countries. Forty major oil importers seem to be increasingly shielded from positive oil shocks over the 1970s and 1980s; however, they must worry about oil price declines. A decline in oil prices has a negative impact on both total and real oil trade balances resulting from increased oil imports in emerging economies. Hence, a decline in oil prices is beneficial to oil exporters due to the quantity effect outweighing the price effect, while for oil importers a stable oil price is more desirable than a price decline. These results are important to take into account if we are to gain a full understanding on the magnitude of the trade and macroeconomic effects of oil price changes and what the policy responses should be.

Output and labor productivity in organized manufacturing: a panel cointegration analysis for India

One of the policy puzzles faced in India during the last two and half decades has been the weak association between output and labor markets, particularly in the manufacturing sector. In this research, we investigate the long-run relationship between output, labor productivity and real wages in the case of organized manufacturing. We adjust the measure of labor productivity incorporating bottlenecks, such as lack of infrastructure, access to external finance, and labor regulations, which all may influence labor market outcomes. Using panel data from seventeen manufacturing industries, we establish long-run dynamics for the output-labor productivity-real wages series over a period of nearly three decades. We employ recently developed panel unit root and cointegration tests for cross-sectional dependence to incorporate heterogeneity across industries. Long-run elasticities are generally found to be low for labor productivity compared to real wages due to the changes in manufacturing output. There are variations across industries within the manufacturing sector for the effects of the labor market on manufacturing output. In some industries, lower wages are associated with higher output, and the reason for the positive relationship in other industries could be due to workers' bargaining power.

Can the Severity of Dependence Scale be usefully applied for 'ecstasy'?

Background/Aims: Although use of 'ecstasy' (drugs sold as containing 3,4-methylenedioxymethamphetamine) is prevalent, it is typically infrequent, and treatment presentations involving ecstasy as a principal problem drug are relatively rare. Human case reports and animal literature suggest dependence potential, although there may be some unique aspects to this syndrome for ecstasy in comparison to other substances. The Severity of Dependence Scale (SDS) was examined to determine whether this could usefully identify 'dependent' ecstasy consumers.

Methods: We conducted a cross-sectional survey of 1,658 frequent (at least monthly) ecstasy consumers across Australia, assessing drug use, associated harms and risk behaviours. Dependence was evaluated with the SDS, using a cut-off of ≥4 to identify potential 'dependence'. Results: One fifth of the participants were screened as potentially dependent. These individuals used ecstasy more frequently, in greater amounts, engaged more extensively in risk behaviours and reported greater role interference than other participants. These findings were independent of methamphetamine use or dependence. The underlying structure of the ecstasy SDS was bifactorial.

Conclusions: The SDS has demonstrated construct validity as a screening tool to identify ecstasy users at elevated risk of experiencing adverse consequences, including features of dependence. The underlying structure of dependence symptoms differs for ecstasy compared to other drug classes, and some dependent consumers use the drug infrequently. The unique neurotoxic potential and entactogenic effects of ecstasy may require a distinct nosological classification for the experience of dependence associated with the drug.