Structural Break Tests Research Articles

Quantifying the data-dredging bias in structural break tests

Structural break tests are often applied as a pre-step to ensure the validity of subsequent statistical analyses. Without any a priori knowledge of the type of breaks to expect, eye-balling the data can indicate changes in some parameter, e.g., the mean. This, however, can distort the result of a structural break test for that parameter, because the data themselves suggested the hypothesis. In this paper, we formalize the eye-balling procedure and theoretically derive the implied size distortion of the structural break test. We also show that eye-balling a stretch of historical data for possible changes in a parameter does not invalidate the subsequent procedure that monitors for structural change in new incoming observations. An empirical application to Bitcoin returns shows that taking into account the data-dredging bias, which is incurred by looking at the data, can lead to different test decisions.

EXPLORING ASYMMETRIC NEXUS BETWEEN TOURISM, ECONOMIC GROWTH AND CO2 EMISSIONS IN THE CONTEXT OF PAKISTAN

This study aims to examine the nexus between tourism, economic growth, and CO2 emissions in Pakistan. We examined the asymmetric relationship between tourism, economic growth, and CO2 emissions for the period 1991 to 2019. We applied NARDL technique, and Granger Causality to predict results. Moreover, we also employed ADF, PP unit root test, Zivot and Andrews test for structural breaks. The nonlinear autoregressive distributed lag is the most appropriate econometric estimator in the case if asymmetric association exists among the variables. The NARDL technique is capable to discover the dynamic association between economic growth, tourism, and CO2 emissions. Our results confirmed the asymmetric nexus between tourism, GDP and CO2 emissions in the context of Pakistan. The results reported that in the short run as well as long run positive and negative shocks of tourism and GDP affect CO2 emissions. The outcomes also revealed unidirectional causality between tourism and CO2 emission, while bi-directional causality between economic growth and CO2 emissions. Likewise, a bi-directional causality has also been reported between tourism and economic growth. The results are very useful for the macro level policy makers in Pakistan, and hopefully will provide significant insight to the relevant stakeholders.

On the long-run dynamics of income and wealth inequality

We analyse top income and wealth shares data, by conducting a robust estimation of trends, tests for structural breaks, and tests for determining persistence. We include Anglo-Saxon countries, continental Europe and Asian countries, grouped under different percentiles and deciles, spanning a period that is at least close to a century. We find that the top income shares for almost all countries are characterised by broken trends, or level shifts. The preponderance of trend breaks appears in the 1970s and 1980s where after a negative trend changes in magnitude or direction. Finally, shocks to the top income share data are not transitory, which have consequences for policy such as advocating redistributive measures.

Collaboration between research institutes and large and small publishers for publishing open access journals

Research institutes frequently collaborate with for-profit publishers for the publication of open access journals. This study uses a structural break test to examine the effects of the collaboration between research institutes and large and small for-profit publishers for the publication of 15 gold open access journals on the journals’ internationality and academic influence. The results reveal an improvement in the internationality and academic influence for most of the journals following the collaboration. Additionally, the scale and persistence of the effects are not dependent on the size of the publisher. The findings indicate that large publishers do not have any advantage over small publishers in publishing journals for research institutes. This implies that small publishers can compete with large ones in publishing official journals on behalf of research institutes. However, as collaboration with research institutes strengthens the large publishers’ presence in the open access journal market, it is necessary to monitor their activities, including large publishers’ acquisitions of small ones.

BİST-100 Endeksinde Doğrusal Ve Doğrusal Olmayan Yöntemlerle Zayıf Formda Piyasa Etkinliğinin Testi

Piyasa etkinliği, haber akışlarının pay senedi fiyatlarına ne ölçüde yansıdığını ifade etmektedir. Bu bağlamda zayıf, yarı güçlü ve güçlü formda piyasa etkinliğinden söz edilebilmektedir. Literatürde zayıf formda etkinlik genellikle birim kök testleriyle incelenmektedir. Bu çalışmada 2000-2020 döneminde Borsa İstanbul BİST-100 endeksinin yükseliş ve düşüş dönemlerinde zayıf formda etkin olup olmadığı test edilmek istenmiştir. Bu amaçla önce doğrusallık testi yapılmış; ardından doğrusal olmayan Kapetanios, Shin Snell ve doğrusal nitelikte olup yapısal kırılmayı dikkate alan Zivot Andrews birim kök testi uygulanmıştır. Elde edilen sonuçlar BİST-100 endeksinin zayıf formda etkin olduğunu göstermektedir.

Do the electricity price shocks influence the Sectoral Production and KSE100 Index in Pakistan? An ARDL structural breaks approach

This research investigates the long-term cointegration of electricity price with sectoral production and equity market in Pakistan. Fourteen major industrial sectors and the KSE100 index is taken into consideration to determine the relationship. Literature in this regard is available but this research is distinct from previous literature for it tests the sectoral production and equity market relationship with electricity price change in Pakistan. Monthly data from 1st Jan 2011 till 31st Dec 2019 is taken for fourteen sectors from the sources of Quantum Index Pakistan Bureau of Statistics (PBS) and for KSE100 index from (www.investing.com). An Auto Regressive Distributed Lag (ARDL) model and bound test for multiple structural breaks has been applied. It is found that almost the production of all industrial sectors and KSE100 index stock prices are adversely affected by the electricity price shocks both in long-term and short-term. The study suggests that management should implement a moderate monitory policy that is neither more expansionary nor contractionary. The government should provide incentives to those who successfully control energy wastage. A mixed kind of energy policy is recommended with higher weightage to the development of renewable energies to reduce foreign exchange outflow with imported furnace oil. This study is limited to the sectoral production and equity market of Pakistan. A cross-sectional research is encouraged to compare the connection between major energy costs and macroeconomic variables in different countries.

COVID-19 pandemic and cryptocurrency markets: an empirical analysis from a linear and nonlinear causal relationship

PurposeThis paper aims to empirically examine the effect of Coronavirus disease 2019 (COVID-19) pandemic on cryptocurrency market returns with particular attention to top five cryptocurrencies and COVID-19 confirmed and death cases.Design/methodology/approachThe study applies the linear Toda and Yamamoto and nonlinear Diks and Panchenko Granger causality test to know the causal relationship of cryptocurrencies with COVID-19 pandemic. The study also uses the Narayan and Popp endogenous two structural break tests to capture the break period of the sample.FindingsThe findings of the study confirm the existence of unidirectional causal relation from COVID-19 confirmed and death cases to cryptocurrency price returns. While examining the break periods, the post-break period result indicates the presence of unidirectional linear causality from COVID-19 confirmed cases to Bitcoin and Ethereum price returns. This shows that prior knowledge of COVID-19 pandemic growth helps to predict the return of cryptocurrencies.Originality/valueThe study suggests the investors or crypto lovers to observe the growth of COVID-19 situations during their investment in cryptocurrency markets.

From Black Wednesday to Brexit: Macroeconomic shocks and correlations of equity returns in France, Germany, Italy, Spain, and the United Kingdom

AbstractThis paper investigates whether macroeconomic shocks, such as the UK's referendum decision to leave the European Union (“Brexit”), the 2008 Financial Crisis, the 1992 ERM Crisis (“Black Wednesday”), and the 1987 stock market crash (“Black Monday”), had a positive impact on portfolio risk diversification. We estimate weekly dynamic conditional correlations and then optimal sectoral portfolio allocations between 1973 and 2019. Our results show that correlations of equity returns increased as a consequence of economic integration among European countries from the mid‐1980s until the late 2000s, and decreased in the United Kingdom after Black Wednesday and the Brexit referendum. We tested the existence of a correlation change‐point on June 27, 2016 by applying Wied et al. (2012)'s [Econometric Theory, 28(3), 570–589] correlation structural break test, which we modified to account for dynamic conditional correlations. Application of this test confirms that the referendum date was a break‐point in nearly all UK manufacturing industries. The failure of Lehman Brothers and the 1987 stock market crash were also identified as structural breaks in equity correlations. Moreover, our findings suggest that the Brexit vote may constitute a long‐term trend reversal of the convergence of equity return correlations in European markets, akin to Black Wednesday, rather than a shock like the 1987 and 2008 financial crises, which merely intensified a historical upward trend in correlations of European equity returns.

Environmental Kuznets curve in the presence of structural breaks: new evidence for individual European Countries.

This study explores the relationships between carbon emissions and their main determinants such as energy consumption, real income and international trade, in 15 European countries, employing data for the period 1960-2015, and in Germany, for that of 1970-2015. The purpose of this paper is to examine the environmental Kuznets curve in subregimes in the presence of structural shifts. Two complementary unit root tests are employed to examine the stationarity of employed variables. The Ng and Perron Econometrica 69: 1519-1554 (2001) and the Zivot and Andrews J Bus Econ Stat, 10(3), 251-270 (1992) unit root tests, both allow for a structural break. To estimate the parameters of the regression model and to detect structural breaks in the model, the Kejriwal and Perron J Econ, 146(1), 59-73, (2008), J Bus Econ Stat, 28(4), 503-522, (2010a), J Time Ser Anal, 31, 305-328, (2010b)) structural break test is employed. When structural breaks are allowed in estimations, the empirical results provide strong evidence of fluctuating relationships between CO2 emissions and income expressed by the U-shape in every subregime, which contradicts early findings in the literature of inverse U-shape environmental Kuznets curve.

Comparing the performances of symmetric and asymmetric generalized autoregressive conditionally heteroscedasticity models based on long-memory models under different distributions

This research compares the symmetric and asymmetric effects of generalized autoregressive conditional heteroscedasticity (GARCH)-type models to investigate the volatility of the autoregressive fractionally integrated moving average (ARFIMA) model using the monthly Brent crude oil price series for the period of January 1979–July 2019. The best model of volatility is determined by comparing 13 hybrid models of GARCH (sGARCH, fGARCH, EGARCH, TGARCH, IGARCH, AVGARCH, NGARCH, NAGARCH, APARCH, apARCH, GJRGARCH, gjrGARCH, and csGARCH) in terms of symmetric and asymmetric effects at the level of (1,1). R/S analysis is used to achieve this target. The aggregated variance method, the Higuchi method, and the structural break test are performed to determine the presence of long memory in the dataset. Furthermore, the Hurst exponent method and the Geweke and Porter–Hudak method are used to estimate the fractional difference values. The ARFIMA(2,0.3589648,2)–IGARCH(1,1) model under normal distribution is selected as the best model based on the Akaike information criterion, Schwartz Bayesian information criterion, and by the smallest value for root-mean-squared error, in which this model can be used to predict more accurately than other models.

Entropy analysis and pattern recognition in rainfall data, north Algeria

Algerian climate is characterized by the transition between the subtropical climate in the north and the hot Saharan climate in the south. Understanding the spatiotemporal variability of rainfall patterns in such areas has significant implications for water resources management. To account for the spatial variation in the rainfall pattern of north Algeria, Tsallis entropy analysis, pattern recognition, and Precipitation Concentration Index (PCI) have been analyzed over a period of 33 years (1980–2013). The rainfall trend is identified by analyzing the results of the structural break test and Mann-Kendall (MK) trend tests. The Tsallis entropy produced spatial patterns for a better understanding of rainfall characteristics and the results show that entropy values were higher for higher rainfall values. The magnitude of rainfall change indicates that a large amount of rainfall occurs over the northern country boundary compared with the central part of Algeria. The rainfall record shows a structural break in the year 1992 during the selected time period. The MK trend analysis revealed a significant decreasing trend over the central and no trend in north and south of the study area. The PCI indicates a moderate rainfall concentration across the northern border region compared with a significant irregular rainfall distribution over the central region. The Wavelet Coherence Analysis (WCA) between El Nino Modoki (EMI) and Southern Oscillation Index (SOI) events on monthly rainfall data were also investigated to find a possible influence of global climatic indicators on the rainfall events. The results show a significant correlation of EMI and SOI with the rainfall pattern of north Algeria.

Exploring Asymmetric Nexus Between CO2 Emissions, Environmental Pollution, and Household Health Expenditure in China.

ObjectiveThis study investigates the nexus between household health expenditure, CO2 emissions and environmental pollution in China. We analyzed the asymmetric dynamic relationship between CO2 emissions, environmental pollution and household health expenditure for the period 1990 to 2019 in China.MethodsThis study adopted nonlinear autoregressive distributed lag (NARDL) and Granger causality following the diagnostic test. Furthermore, we applied Dickey–Fuller (ADF), PP unit root tests, Zivot and Andrews test for structural breaks in our analysis. The NARDL is the most suitable econometric technique for estimations, especially if the asymmetric relationship exists among the variables. NARDL technique is capable to explore the dynamic relationship between CO2 emissions, environmental pollution and household health expenditure.ResultsThe empirical results verify the asymmetric nexus between CO2 emissions, environmental pollution and household health expenditure in the context of China. The outcomes revealed that in the short run and long run positive shocks of CO2 emissions and environmental pollution positively affecting health expenditure, while negative shocks reduce health spendings. The results also demonstrate bi-directional causality among household health spendings, CO2 emissions and environmental pollution.ConclusionOur results support many previous studies, documenting that CO2 emissions positively contribute to the amount of household health expenditure, confirming the asymmetric relationship between CO2 emissions and household health expenditure. The results also confirm the statistically significant and asymmetrically positive relationship between environmental pollution and household health expenditure. This implies that Chinese residents have to bear more household health expenditure, in the case of more CO2 emissions and a greater amount of environmental pollution.

Sugar Prices vs. Financial Market Uncertainty in the Time of Crisis: Does COVID-19 Induce Structural Changes in the Relationship?

Securitization of the agricultural commodity market has accelerated since the beginning of the 21st century, particularly in the times of financial market uncertainty and crisis. Sugar belongs to the group of important agricultural commodities. The global financial crisis and the COVID-19 pandemic has caused a substantial increase in the stock market volatility. Moreover, the novel coronavirus hit both the sugar market’s supply and demand side, resulting in sugar stock changes. The paper aims to assess potential structural changes in the relationship between sugar prices and the financial market uncertainty in a crisis time. In more detail, using sequential Bai–Perron tests for structural breaks, we check whether the global financial crisis and the COVID-19 pandemic have induced structural breaks in that relationship. Sugar prices are represented by the S&P GSCI Sugar Index, while the S&P 500 option-implied volatility index (VIX) is used to show stock market uncertainty. To investigate the changes in the relationship between sugar prices and stock market uncertainty, a regression model with a sequential Bai–Perron test for structural breaks is applied for the daily data from 2000–2020. We reveal the existence of two structural breaks in the analysed relationship. The first breakpoint was linked to the global financial crisis outbreak, and the second occurred in December 2011. Surprisingly, the COVID-19 pandemic has not induced the statistically significant structural change. Based on the regression model with Bai–Perron structural changes, we show that from 2000 until the beginning of the global financial crisis, the relationship between the sugar prices and the financial market uncertainty was insignificant. The global financial crisis led to a structural change in the relationship. Since August 2008, we observe a significant and negative relationship between the S&P GSCI Sugar Index and the S&P 500 option-implied volatility index (VIX). Sensitivity analysis conducted for the different financial market uncertainty measures, i.e., the S&P 500 Realized Volatility Index confirms our findings.

Determinants of the WTI‐Brent price spread revisited

AbstractUsing autoregressive distributed lag modeling and structural break testing, we explore the drivers of the oil price spread between West Texas Intermediate and Brent in a data set from 1995 to 2019. We find a major structural break in December 2010 and minor breaks in 2005 and 2012. Important spread determinants are the convenience yield, as a proxy for crude oil inventories, the trading activity in crude oil paper markets, shipping costs, as well as the stock market development in the United States and Europe. After the break in 2010, the paper market activity, open interest, and shipping costs have become more important spread drivers.

The time-varying effects of oil prices on oil\u2013gas stock returns of the fragile five countries

This study analyzes oil price exposure of the oil–gas sector stock returns for the fragile five countries based on a multi-factor asset pricing model using daily data from 29 May 1996 to 27 January 2020. The endogenous structural break test suggests the presence of serious parameter instabilities due to fluctuations in the oil and stock markets over the period under study. Moreover, the time-varying estimates indicate that the oil–gas sectors of these countries are riskier than the overall stock market. The results further suggest that, except for Indonesia, oil prices have a positive impact on the sectoral returns of all markets, whereas the impact of the exchange rates on the oil–gas sector returns varies across time and countries.

Robust test for structural instability in dynamic factor models

In this paper, we consider a robust test for structural breaks in dynamic factor models. The proposed framework considers structural changes when the underlying high-dimensional time series is contaminated by outlying observations, which are often observed in many real applications such as fMRI, economics and finance. We propose a test based on the robust estimation of a vector autoregressive model for principal component factors using minimum density power divergence. The simulations study shows excellent finite sample performance, higher powers while achieving good sizes in all cases considered. Our method is illustrated to the resting state fMRI series to detect brain connectivity changes.

Testing for Structural Breaks – A New Self-Normalization Approach Based on the Adjusted Sample Range

In this paper, we introduce adjusted-range based Kolmogorov-Smirnov (KS) type statistics to test for structural breaks in the mean of a process and also in a more general setting. We propose a normalization based on the adjusted-range of a partial sum, which is stochastically proportional to the true long-run variance (LRV), and is nuisance parameter and distribution free. We find, through simulation studies, that the new statistic offers better performance than the self-normalized KS statistic (Shao and Zhang, 2010) and the KS statistics utilizing the small-b and fixed-b approaches (Kiefer and Vogelsang, 2005). Finally, empirical studies also illustrate the suitability of KS type tests.

Volatility spillover between stock market and currency market of Pakistan in the presence of structural breaks

This study examines the volatility transmission between the currency market and the stock market of Pakistan in the presence of structural breaks. For this purpose, daily data from the stock market and currency market is analyzed. An empirical investigation is conducted using the bivariate EGARCH model and the test for multiple structural breaks developed by Bai and Perron (2003). This study analyses these markets with the inclusion of sudden changes. Results of the EGARCH model suggest that volatility spillover is positive and bidirectional between these markets of Pakistan.

А был ли сдвиг: эмпирический анализ тестов на структурные сдвиги в волатильности доходностей

In this article, two popular tests for structural breaks are considered for return volatilities: the ICSS algorithm employing the AIT test, and the least-squares (LS) estimator. We show that the AIT test is sensitive to many features of the time series, and the use of asymptotic critical values is not always justified. The LS method was found to detect breaks more accurately, especially if there are many, in comparative simulations. Real data analysis revealed that LS estimation yields results in better accordance with general economic intuition, although its results are somewhat sensitive to the sample length. In general, we recommend the LS estimator for practical purposes.

Spatial and temporal pattern of rice yield growth in Asian countries from 1961 to 2016: An exploratory econometric analysis

The present paper attempts to find out the spatial and temporal movement of rice yield in twelve countries in Asia which is its lifeline over the period 1961 to 2016 by following Bai-Perron multiple structural break tests. The results based on endogenous multiple structural break analysis show that many of these countries passed through several phases of acceleration and deceleration in rice yield over this period The results also demonstrate that except Japan, all the twelve countries considered in our study experienced at least one structural break in rice yield at level during the period 1961 to 2016. The acceleration phases of rice yield growth observed mostly during 1970's and 1980's are resulted from improved technological innovations in agriculture whereas deceleration phases observed in the last two decades are mainly caused by environmental challenges on rice production. Cross country yield gaps have been showing declining trend since early 80's.