Panel Data Unit Root Tests Research Articles

Intra-Regional and Global Competitive Dynamics of African Sugar Industries

Recent dynamics in the sugar industry, including price fluctuations in the global market, reforms in the European sugar sector, and changes in intra-regional trade patterns, underscore the need to understand changes in the competitiveness of African sugar exports. This paper, therefore, uses the Normalized Revealed Comparative Advantage (NRCA) index and the Harris-Tzavalis panel-data unit-root test to conduct a comprehensive analysis of the dynamics in both inter and intra-regional competitiveness of sugar exports across 34 African countries using panel data that spans from 2001-2021. The NRCA indices reveal notable shifts and patterns in the competitive landscape of African sugar exporters. As of 2021, half of the countries under scrutiny demonstrated a competitive edge in sugar exports, representing a slight uptick from the fourteen (14) observed in 2021. Nonetheless, only eight (8) African countries, predominantly from southern Africa, have sustained their competitiveness both globally and intra-regionally over the entire analysis period. The majority of African sugar exports have struggled to maintain competitiveness on the global market, with some alternating between periods of comparative advantage and comparative disadvantage. However, three North African countries, particularly Algeria, Egypt and Morrocco gained comparative advantage during this timeframe. The sustained competitiveness of Southern African countries and the gain in competitiveness of some North African countries highlights the importance and growing influence of Foreign Direct Investment (FDI) in shaping the developmental trajectory of African sugar industries.

Trade and competitiveness of African sugar exports

IntroductionSugar ranks among the most widely consumed, traded, sensitive, and protected commodities on the global and intra-regional stages. Recent developments in the sugar industry, inclusive of price distortions in the global sugar market, the liberalization of the European sugar sector, and the globalization of international agricultural trade, have amplified the need to comprehend the evolution of competitiveness in African sugar exports. Consequently, this study aims to provide a comprehensive analysis of the patterns, trends, and shifts in the inter- and intra-regional competitiveness of African sugar exports.MethodsThis paper employed the Normalized Revealed Comparative Advantage (NRCA) index and the Harris-Tzavalis panel-data unit-root test to assess the stability and structural changes in the competitive patterns of sugar exports for 34 African countries. The analysis is based on panel data spanning the period from 2001 to 2021.Results and discussionThe NRCA indices unveil certain dynamics and shifts in the competitiveness of country-specific sugar exports. Overall, the number of countries exhibiting competitive sugar exports has marginally increased, rising from 14 in 2001 to 17 in 2021. However, only eight African countries, predominantly from the southern region, have consistently maintained competitiveness in both the global and intra-regional markets throughout the entire analysis period. A significant portion of sugar exports from African countries has remained non-competitive on the global market, with a select few oscillating between periods of comparative advantage and disadvantage. Notably, the North African nations of Morocco, Algeria, and Egypt have transitioned from a position of comparative disadvantage to one of comparative advantage. At the intra-regional level, the presence of tariff and non-tariff trade barriers, including tariff escalations and trade embargoes, has rendered sugar exports non-competitive. These barriers augment the challenges faced by producers in other African nations seeking to exploit economies of scale.ConclusionThe sustained competitiveness of sugar exports from the Southern African region to other African regions underscores the significance and increasing impact of Foreign Direct Investment (FDI) in bolstering the competitiveness and development of the sugar industry.

The impact of economic growth, tourism, natural resources, technological innovation on carbon dioxide emission: evidence from BRICS countries.

The main objective of this manuscript was to investigate the relationships among economic development, tourism, the use of natural resources, technical advancement, and carbon dioxide emissions in the BRICS group of nations. Data from the panel was gathered from 1995 to 2018. Modern methodology tools including the CS-ARDL tests, Westerlund cointegration tests, and panel data unit root tests have been used in this study. Results of the models show that all the variables were transformed to the first difference to make it stationary. The Westerlund model test results suggest that dependent and independent variables have robust cointegration. Results of the CS-ARDL models reveal that all the variables signed, and significance are aligned with the economic theory. It indicates that except for tourism, the rest of the variables like technical innovation, natural resources, and economic growth have positive and significant effects on carbon dioxide emissions both in the short and long runs. Additionally, a 1% rise in economic growth, technical innovation, and natural resources over the long term would raise carbon dioxide emissions in the BRICS economies by 1.79%, 0.15%, and 0.10%, respectively. However, a 1% increase in tourism would result in a 0.39% decrease in carbon dioxide emissions among the nations in the panel data set. Therefore, the promotion of sustainable tourism and advancement in technological innovation is highly important in these countries, so the high impact of environmental degradation pressure may reduce to some extent. An in-addition comprehensive set of policies should be made on encouraging low-carbon transportation, promoting sustainable tourism certification, boosting local produce, reducing waste management, and provide education and awareness campaigns to tourists.

Urban growth in the long term: Belgium, 1880–1970

We take advantage of a new data set on Belgian cities to test random growth, that is, Gibrat’s law. This unique data set provides annual population estimates for all Belgian municipalities (2680 cities) from 1880 to 1970. The use of panel data methodology and unit root tests can provide a precise test of Gibrat’s law (a unit root is equivalent to random growth). We run both time series and panel data unit root tests, thus obtaining strong support for random growth in the long term. Results hold when allowing for the presence of one and two structural breaks in the mean, with the timing of the breaks coinciding with some major historical events, such as the World Wars and the economic crisis of 1929–1933.

Panel unit-root tests with structural breaks

In this article, we introduce a new community-contributed command called xtbunitroot, which implements the panel-data unit-root tests developed by Karavias and Tzavalis (2014, Computational Statistics and Data Analysis 76: 391–407). These tests allow for one or two structural breaks in deterministic components of the series and can be seen as panel-data counterparts of the tests by Zivot and Andrews (1992, Journal of Business and Economic Statistics 10: 251–270) and Lumsdaine and Papell (1997, Review of Economics and Statistics 79: 212–218). The dates of the breaks can be known or unknown. The tests allow for intercepts and linear trends, nonnormal errors, and cross-section heteroskedasticity and dependence. They have power against homogeneous and heterogeneous alternatives and can be applied to panels with small or large time-series dimensions.

Convergence of testing and positivity rates for the COVID-19 pandemic: evidence from Germany and Italy

PurposeThis paper aims to analyze the convergence of the testing and positivity rates for the COVID-19 pandemic focusing on Germany and Italy.Design/methodology/approachThe authors employ the two-regime threshold autoregressive (TAR) panel unit root test by using the weekly data in the period of 2020:03-2021:04.FindingsFollowing finding out that the testing and positivity rates are nonlinear, the authors determine that the transition country between the two regimes is Italy for the testing rates and Germany for the positivity rates. Their findings support the partial convergence for the testing rates for Germany and Italy. On the other hand, the authors could not find any convergence for the positivity rates of these two countries.Originality/valueThis paper contributes to academic literature in several ways. Firstly, to the best of their knowledge, this paper is the first study that analyzes the convergence of testing and positivity data. This paper further focuses on two Euro-Area countries which have suffered significantly from the COVID-19 pandemic. In addition, the authors employ the two-regime threshold autoregressive (TAR) panel unit root proposed by Beyaert and Camacho (2008) in their empirical analysis. This recent panel data methodology aims to test real convergence in a nonlinear framework by incorporating the threshold model, panel data unit root test and the calculation of critical values by bootstrap simulation.

Missing Values in Panel Data Unit Root Tests

Missing data or missing values are a common phenomenon in applied panel data research and of great interest for panel data unit root testing. The standard approach in the literature is to balance the panel by removing units and/or trimming a common time period for all units. However, this approach can be costly in terms of lost information. Instead, existing panel unit root tests could be extended to the case of unbalanced panels, but this is often difficult because the missing observations affect the bias correction which is usually involved. This paper contributes to the literature in two ways; it extends two popular panel unit root tests to allow for missing values, and secondly, it employs asymptotic local power functions to analytically study the impact of various missing-value methods on power. We find that zeroing-out the missing observations is the method that results in the greater test power, and that this result holds for all deterministic component specifications, such as intercepts, trends and structural breaks.

Do foreign direct investments influence environmental degradation? Evidence from a panel autoregressive distributed lag model approach to low-, lower-middle-, upper-middle-, and high-income countries.

The main aim of the present study is to examine the possible nonlinear relations between foreign direct investments and environmental deterioration for subpanels separated according to the income levels of countries by using the classification made by the World Bank. Total energy consumption, economic growth, and renewable energy share are also considered as determinants of environmental deterioration in the model. Cross-sectional dependence is observed; hence, appropriate panel data unit root and cointegration tests are utilized for which results pointed out mixed integration order. Pooled mean group (PMG) estimator panel auto-regressive distributed lag (ARDL, hereafter) approach is adapted to observe short- and long-run relationships between the variables. Long-run results supported the pollution haven hypothesis as foreign direct investments caused an increase in ecological footprint. Findings are sensitive to different income levels of the subpanels of countries. This empirical study suggests tailored policymaking for every income level subpanel to ensure sustainable development.

Examination of impact of COVID-19 on stock market: evidence from American peninsula

PurposeThe rapid spread of COVID-19 has dramatic effects on financial market across the globe. This study analyzes the relationship between the COVID-19 cases, age and stock market indexes in Central America, North America, and South America.Design/methodology/approachThe panel regression analysis on three regions from March 10, 2020 to April 9, 2020 was conducted to test the hypothesized model. The authors used Levin et al.’s (2002) panel data unit root test to check the stationarity, and Hausman (1978) test was applied to determine the random and fixed effects.FindingsThe authors’ panel regression results indicate that the COVID-19 cases have a negative impact on stock indexes, whereas the age has a positive impact on the stock indexes. The region-wise analysis supports the panel finding except for South America, which shows an insignificant association between stock indexes and COVID-19 cases.Originality/valueThe study supplements the literature by examining the impact of pandemics on stock indexes and focus on three multicultural regions, comprising developed, developing and emerging countries, which are hitherto unaddressed.

EXTERNAL SHOCKS, STRUCTURAL BREAKS AND UNEMPLOYMENT HYSTERESIS IN SELECTED ASIAN COUNTRIES

This paper re-examines the hypothesis of unemployment hysteresis using panel data for 11 Asian countries for the period from 1980 to 2008. This study employs a variety of panel data unit root tests recently advanced by Bai and Ng (2004), Pesaran (2007) and Chang and Song (2009). The advantage of these tests is that they are able to exploit the cross-section variations of the series. In addition to these tests, a new powerful panel stationarity test proposed by Carrión-i-Silvestre et al. (2005) is applied which exploits the cross-section variations of the series and also allows for different numbers of endogenous breakpoints in the series. Our findings stress the importance of accounting exogenous shocks in the series and provide stronger evidence against the hypothesis of unemployment hysteresis for the countries analyzed. We also discover critical economic affairs which may cause the unemployment rates to fluctuate significantly. Policy implications are proposed through our observations.

The greenhouse effect of the agriculture-economic growth-renewable energy nexus: Evidence from G20 countries

Agriculture is the world's second largest greenhouse gas (GHG) emitter due to the use of fossil fuel-based fertilizers, agricultural machinery, and the burning of biomass. Meanwhile, the Group of Twenty (G20) countries, which include the world's top three agricultural markets, have a significant impact on world agricultural development. This study is the first attempt to examine the effects of the agriculture-economic growth-renewable energy nexus on carbon dioxide (CO2) emissions within the framework of the environmental Kuznets curve (EKC) in a panel of 19 nations of the G20 countries from 1990 to 2014. To do so, panel data unit root tests, cointegration tests, and the panel fully modified ordinary least squares (FMOLS) estimator are used. The main findings are as follows: (1) Panel data unit root and cointegration tests confirm the existence of a long-run relationship among the selected variables, (2) agriculture significantly increases CO2 emissions in the full sample and the developing economies of the G20, while renewable energy consumption reduces the CO2 emissions in the full sample and the developed economies of the G20, (3) the EKC indeed exists in the full sample and developed economies, while economic growth only exerts a positive impact on CO2 emissions for developing economies, indicating that the peak of CO2 emissions for developing economies has not yet been reached, and (4) varied causality links exist among the variables across the different income levels of the G20 countries. Based on the above findings, to suppress the greenhouse effect, the G20 countries' policymakers should not only promote the development of sustainable agriculture, but also stimulate renewable energy consumption, especially in developing economies.

Panel data unit root test with structural break: A Bayesian approach

The idea about structural break in unit root hypothesis under time series model had received great amount of attention over many last decades. The importance of structural break in the mean had been comprehensively studied by Perron [15], Perron and Vogelsang [17], Zivot and Andrews [25] etc. This had also studied in considering of break in variance by Kim et al. [9], Cook [6], Kumar et al. [11] etc. There is sufficient contribution regarding break in mean and variance individually but both are equally important and this was little explored by Bai [1] for panel data and Meligkotsidou et al. [14] for univariate time series. In present paper, we are extending this on panel dataAR(1) time series model under Bayesian framework. Posterior odds ratio has been derived for various models with and without break in mean, variance and both in consideration of unit root hypothesis. A simulation as well as an empirical analysis is also carried out to get more generalized view on the model under study.

DOES MIDDLE INCOME TRAP EXIST?: EVIDENCE FROM EMERGING ECONOMIES: E7 COUNTRIES FOR 1969-2015

The E7 countries (China, India, Brazil, Russia, Mexico, Indonesia and Turkey)that have been growing fast since 1990s have been under the middle income countrycategory according to the income category classification of the World Bank for a longperiod of time. Researchers have been interested especially in emerging economies thathave not been able to move up from the middle income category to the high incomecategory and this has led to the initiation of what’s called the ‘middle income trap’ (MIT)discussions in literature. The MIT is generally defined as the countries under the middleincome category failing to move up to the high income category. Therefore, the purpose ofthis study is to identify the presence of MIT in E7 countries that hold an importantposition in global economy. The unit root tests were used in the empirical phase of thestudy. This study’s difference from other studies is the fact that both the time series andthe panel data unit root tests were used both in linear and nonlinear forms, thuspreventing the misleading results created by choosing the wrong model specification.The USA was taken as the reference country in the study and the GNI per capitaaccording to the Atlas method (current US$) data of the World Bank was used for the E7countries for the period 1969-2015. To achieve consistency in the analysis results, Russiawas not included in the model as there were no data available for the same period forRussia given the fact that the same timeframe should be taken as the basis for allcountries. The empirical analysis showed that the E7 countries do not fall into the MIT.

Effect of Trading Volume on Market Returns of Equity Securities Market in Kenya

The study aimed to establish the effect of trading volume on market returns of securities traded in Kenyan securities exchange market. The study used secondary data from all the firms listed in NSE during the period 2004 to 2016. The target population of the study consisted of the sixty 62 companies listed in Nairobi securities exchange market that is, both financial and non-financial companies. The study was a census study of all the sixty 2 companies listed in the Nairobi security exchange market for 13 years starting the year 2004 to the year 2016. The study started with descriptive and then diagnostic tests. The measures of central tendency used to test normality were mean, median, maximum and minimum value, standard deviation, skewness, kurtosis and Jarque-Bera (JB) test. The results from these tests showed that the variables were fairly normally distributed. The study further sought to investigate the stationality properties of market returns, trading volume. The study used five panel data unit root tests. Particularly the test were, Levin, Lin and Chu t, Breitung t-stat, Im, Pesaran and Shin W-stat developed, Fisher-type tests using augmented dickey fuller ADF and (Phillip and Peron) PP tests. The all these tests revealed that the variables were stationary on average. The study also sought to test the granger causality among the variable. The results from granger causality showed that some of the variables granger caused one another. The cointegration results showed that there was long-run equilibrium. The regression techniques used was Cross-section fixed (dummy variables) and Period fixed (dummy variables). The regression results revealed that the variables were statistically significant effect on market returns trading volume had a positive effect on the market returns. It is therefore in this light that the future research should consider other variables which would increase the predictive power of the model. The other relevant variables would be variables such as the size of the firm, market value of the firm and the macroeconomic variables such as exchange rate, inflation, money supply among others.

Environment and economic growth in the Russian Arctic

The purpose of this study is to examine the hypothesis of the inverted U-shaped interdependence between environmental damage from air pollutant emissions and economic growth measured by gross regional product (GRP) per capita in the Arctic regions of Russia. Using the panel data for the period of 2000-2014, we apply FM-OLS panel long-run estimates proposed by Pedroni to investigate the existence of environmental Kuznets curve. Various panel data unit root and co-integration tests are also applied. We examine the stationary properties of individual series in panel datasets using different panel unit root tests. According to the concept of the environmental Kuznets curve all regions of the Russian Arctic are on the increasing branch of the curve. The economic growth is found to have no beneficial effect on the environment in the Arctic. We actualise the need of concentrated policies and incentives to reduce air pollutant emissions in the Russian Arctic.

Dynamics of Wood Pulp Production: Evidence from OECD Countries

This paper investigates whether shocks to pulp for paper production for 17 Organisation for Economic Co-Operation and Development (OECD) members over the period 1980–2012 are transitory or permanent. A variety of univariate and panel data unit root tests are employed. The presence of structural breaks is taken into account when performing those tests. Based on the Narayan-Popp univariate unit root test, wood production series for approximately 64.71% of countries is found to follow a non-stationary process. However, univariate unit root tests tend to have low power when the time span is relatively short. Consequently, three generations of panel unit root tests are considered. Cross-sectional dependence is detected. The first generation of unit roots do not effectively control for cross-sectional dependence, while the second and third generations do. The third generation accounts mainly for cross-sectional co-integration. As a confirmatory analysis, both unit root tests that tests for the null of non-stationarity and stationarity are considered. Most of the panel unit root tests point towards a non-stationary process. Hence, while these shocks can be transmitted to other economic sectors, past behaviours of wood production cannot be used for forecasting purposes. Forest conservation policies can have a permanent impact on pulp for paper production.

Testing for regional convergence of agricultural land prices

The focus of this paper is on spatial market integration in agricultural land markets. We scrutinize the applicability of the law of one price to land markets and distinguish between absolute and relative versions of this “law”. Panel data unit root and stationarity tests are applied to land sale prices in the German state Lower Saxony. Three main clusters with different price developments are detected. Our results indicate that the law of one price holds only locally due to structural differences among regions.

Addressing the effect of workers’ remittance on economic growth: evidence from MENA countries

Purpose– The purpose of this paper is to study the effect of remittances on economic growth in MENA region. More precisely this study tries first to explore the short-run and the long-run relationship between remittances and economic growth. Second, the authors address how the local financial development and institutional environment influence a country’s capacity to take advantage from remittances.Design/methodology/approach– The panel data unit-root test as well as the panel data co-integration is used for the purpose of the long-run remittances growth relationship and the IV technique with GMM option is adopted to study the short-run link.Findings– This paper provides empirical evidence that remittances have a positive effect on economic growth in the long run and a negative effect in short run. The short-run effect of remittances on economic growth is conditional. In fact, it depends in the levels of financial development and institutional quality, respectively.Practical implications– As practical implications, policy interventions, to improve the functioning of governance institutions, enforcing regulation and political stability, enhancing financial system and socio-economic environment are also crucial for increasing the benefit effects of remittances.Originality/value– The research is an extension of previous evidence in two ways; the authors have examined the long-run and short-run remittances-growth relationship in the first time. In the second time, the authors have explored the conditional remittances-growth relationship in MENA countries. Specifically, the authors have examined whether the remittances-growth nexus is affected by financial development and institutional quality levels in MENA countries.

Testing for unit roots in nonlinear heterogeneous panels with smoothly changing trends: an application to Scandinavian unemployment rates

This paper derives panel unit root tests, based on the unit root tests in single time series by He and Sandberg (Oxf Bull Econ Stat 68:835–861, 2006), in a nonlinear dynamic heterogeneous panel accommodating smooth structural changes in the intercepts, in the dynamics, and in the trends. The finite sample size properties of the tests are satisfactory, and the tests are conspicuously more powerful than the panel data unit root tests by Im et al. (J Econom 115:53–74, 2003; Bull Econ Stat 67:393–419, 2005), and Pesaran (J Appl Econom 22:265–312, 2007) in panels subject to structural changes. To accommodate panels with cross-section-dependent idiosyncratic errors, a bootstrap version of the tests is considered. The tests are applied to unemployment rates in Scandinavia, and strong evidence against the hysteresis hypothesis is found. This is not the case if panel unit root tests based on a linear panel or a nonlinear panel with a break in the intercept are applied.

Are Shocks to Wood Fuel Production Permanent? Evidence from the EU

This paper investigates whether shocks (economic effects) to wood fuel production for 18 countries of the European Union (EU) over the period 1961–2012 are temporary or persistent. A variety of time-series and panel data unit root tests are employed. The presence of structural breaks is taken into account when performing those tests. Wood production in approximately 78% of the countries is found to follow a non-stationary process supported by the result that most of the panel unit root tests also point towards a non-stationary process. This indicates that the economic effect will tend to be persistent and suggests that policies affecting wood fuel production, implicitly or explicitly, will have enduring effects. For instance, forest conservation policies will persistently reduce the wood fuel production level.