No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Spurious Regressions in Economics
Abstract
There occurs on some occasions a difficulty in deciding the direction of causality between two related variables and also whether or not feedback is occurring. Testable definitions of causality and feedback are proposed and illustrated by use of simple ...
... If the spatial series are first-order non-stationary, a correlation between the global spatial trends of many variables would tend to produce similar regression results. This problem is similar to that of a spurious regression in time series (Granger & Newbold, 1974). It also affects instrumental variables estimation. ...
... For time series, Granger and Newbold (1974) showed that regressions on variables with time trends tend to produce spurious results with high fit indicators, unreliable t-ratios and locally autocorrelated residuals. As in time series, spatial non-stationarity is associated with the presence of unit roots in the data and unreliable statistical tests designed for stationary variables. ...
... 13 3.2. Spatial trends and other spatial estimation issues Granger and Newbold (1974) demonstrated that the presence of time trends in the data was related to the presence of autocorrelated regression residuals. The same happens in a spatial setting. ...
Previous literature on European regions has shown that structural estimation of New Economic Geography (NEG) wage-type equations obtains results similar to those obtained using old regional economics techniques. I show that this similarity is due to the presence of global spatial trends in the variables (first-order non-stationarity), which produce spurious regressions. Formal tests and graphical models confirm that any variable displaying a core–periphery spatial pattern produces similar predictions for European regional per capita income. Empirical tests of spatial theories should thus pay attention to the geographical features of the administrative units and the global spatial trends of the variables analysed.
Access to preprint: https://www.tandfonline.com/eprint/IIU5GEKTEI6ZUFAR3UVQ/full?target=10.1080/17421772.2024.2325517
... Since the crossing trend is highly non-stationary, a naïve regression can misidentify the model due to the problem of spurious regressions [71]. To address this concern, we adopt a timeseries error correction model to analyze the long-and short-term effects of rescue probability on the number of crossings [72]. ...
... In this section we provide a brief overview of the ECM, following the exposition in [72,Section 6]. The development of the ECM was motivated by the observation that when running Ordinary Least Squares (OLS) regressions using non-stationary dependent and independent variables (in our case, N t,cross and P t,rescue , respectively), there is an elevated risk of finding a significant relationship between the two even when none exists (i.e., a spurious regression [71]). One solution in this case is to take first differences in order to obtain stationary variables, and then to fit a regression on the first differences. ...
The sea crossing from Libya to Italy is one of the world’s most dangerous and politically contentious migration routes, and yet over half a million people have attempted the crossing since 2014. Leveraging data on aggregate migration flows and individual migration incidents, we estimate how migrants and smugglers have reacted to changes in the border enforcement regime, namely the rise in interceptions by the Libyan Coast Guard starting in 2017 and the corresponding decrease in the probability of rescue to Europe. We find support for a deterrence effect in which attempted crossings along the Central Mediterranean route declined, and a diversion effect in which some migrants substituted to the Western Mediterranean route. At the same time, smugglers adapted their tactics. Using a strategic model of the smuggler’s choice of boat size, we estimate how smugglers trade off between the short-run payoffs to launching overcrowded boats and the long-run costs of making less successful crossing attempts under different levels of enforcement. Taken together, these analyses shed light on how the integration of incident- and flow-level datasets can inform ongoing migration policy debates and identify potential consequences of changing enforcement regimes.
... Although RCTs have gained preference over other methodologies, this is not the first time that such a preference for methodological sophistication is witnessed in economics. Similar developments took place in Macroeconomics in the 1970s and 1980s with the emergence of non-stationarity and VAR (Granger & Newbold, 1974;Sims, 1980). Macroeconometric structural modelling originated in the work of the Cowles Commission at the University of Chicago (Pandit, 2001). ...
... The predictive ability of SEM was first called into question by the Box-Jenkins ARIMA modelling (Naylor et al., 1972;Nelson, 1972). The important critiques of SEM are that the regression equations involving nonstationary time series would yield 'spurious' results and that the usual diagnostics are not valid (Granger, 1969;Granger & Newbold, 1974). Although it was shown that any univariate ARMA model can be integrated within the final form of SEM if the latter has enough dynamic structure (Zellner, 1979;Zellner & Palm, 1974), it was not always possible due to the constraints imposed by economic theory. ...
Randomized control trials (RCTs) are recognized as the preferred tool of analysis in modern development economics literature/research and policy evaluation. This may lead to methodologies, including case studies, tabular analysis, simple regressions, taking a back seat. This survey explores the implications of such a methodological hierarchy and the implications of preoccupation with a particular evidence/ methodology for research and policy. Similar developments in macroeconomic modelling are also discussed. Major advantages and limitations of RCTs and the attempts to address them are highlighted.
The article argues that preoccupation with a methodology can
sometimes lead to important inquiries for research and policy getting side-lined on methodological considerations. This leads to inferences favouring a particular technique/methodology or issue. Focusing solely on methodologies that emphasize quantifying the ‘effect’ may not be appropriate to address all questions relevant to development. As policies involve multiple and conflicting social concerns, methodological pluralism may be preferable.
... The Granger causality test (Granger & Newbold, 1974) was used in both versions of the time series data range before and until the COVID-19 pandemic to see if there was a significant difference between the two time series data ranges. ...
The COVID-19 pandemic outbreak has caused disruptions in various aspects of life and the economy, including the movement of stock indexes. The objective of this study is to examine the influence of macroeconomic factors on the volatility of the Jakarta Composite Index both before and after the COVID-19 pandemic. Monthly secondary data from June 2007 to December 2019 were analyzed to identify pre-COVID trends, while data from June 2007 to December 2021 were used to identify post-COVID-19 patterns. The analysis incorporated the Granger causality test, Cointegration test, Vector Error Correction Model, and Augmented Dickey-Fuller. The results of the causality analysis revealed variations in the impact of interest rates, global oil prices, inflation, and exchange rates on the Jakarta Composite Index before and following the COVID-19 pandemic. These findings hold significance for investors as they enable the identification of potential risks associated with investments during global crises.
... To test for endogeneity, we utilized the Durbin-Wu-Hausman test which helps in identifying the correlation between endogenous regressors and the error terms, indicating that estimates from Ordinary Least Squares (OLS) may be inconsistent. Upon confirming endogeneity with this test, we used lagged variables (X t−1 ) based on recommendations in the literature [16,53,59]. This approach enhances the robustness of our causal inference by assuming that past values of the predictors are less likely to be correlated with the current error term. ...
This study investigates the impact of the Energy-related Uncertainty Index (EUI) on corporate investment among Chinese non-financial listed companies, focusing on two aspects: the effect of EUI fluctuations on investment behavior, and its differential impact on energy versus non-energy sectors. Utilizing a dataset of 2487 firms from 2007 to 2022, encompassing 22,346 firm-year observations, our analysis reveals that a 1% increase in the EUI leads to a 0.045% decrease in overall corporate investment. Notably, this effect is more pronounced in energy-related firms, where a 1% increase in EUI leads to a 0.057% reduction in investment. In comparison, non-energy-related firms exhibit a milder response, with a 1% increase in EUI resulting in a 0.026% decrease in investment. Given the average annual change in EUI over the sample period [2007–2022] of 27.710%, a 0.045% decrease in investment implies a substantial 1.246% per annum change in investment. This highlights the economically significant impact of EUI fluctuations on corporate investment decisions, particularly during periods of heightened uncertainty. These findings, validated through alternative EUI measures and investment metrics, provide crucial insights for understanding investment behavior under energy uncertainty. Conclusively, our study contributes to the literature by highlighting how energy uncertainty uniquely impacts corporate investment, taking into account the specific financial and operational conditions within different sectors. The findings highlight the importance of incorporating energy policy considerations into corporate strategic planning, particularly for energy-intensive industries within transitional economies like China.
... When two-time series data are non-stationary, the regression between these two time-series data may give a high R-Squared even if these time-series data are entirely unrelated. The regression between the unrelated time series is called spurious regression (Granger and Newbold 1974). So, checking whether each financial time-series are stationary or contain a unit root (non-stationary) is required before regression between two financial time series data is undertaken. ...
This paper evaluates the stock market cointegration as a result of COVID-19 and the investment implications, among six countries representing four major continents. We use the Gregory and Hansen cointegration test, to avoid any structural change issue within the time series, to test if one stock market cointegrates with another and the multivariate Dynamic Conditional Correlation model to estimate time-varying conditional correlation relationships among these stock markets. Using daily stock market data between January 2011 and December 2022 which we further divided into three sub-samples of pre, during and post COVID-19, the Gregory and Hansen results show a long-run relationship among sixty percent of the stock markets investigated before COVID-19. However, we find that there are no stable long-run relationships among eighty percent of the same stock markets after COVID-19, indicating potential portfolio diversification benefits for investors. Our findings using the Dynamic Conditional Correlation model show that stock market correlations are low before and after COVID-19 but find a © Author(s) Licensed under Creative Common Page 2 dramatic increase in correlation during the COVID-19 period and that the correlation starts to decrease after the crisis. Therefore, active investors should understand how markets cointegrate at normal times, during economic crises and after such crises as well as how they correlate and apply such in the design of investment portfolios to fully leverage on the inherent benefit of international diversifications.
... Yule's claims remained unnoticed until 1974 when computer simulations provided further proof to the observations he had made by drawing playing cards from previously shuffled packs. 6 Since then, the analysis of these correlations has constituted an important topic in econometric and economic modeling, where it receives the names of "spurious regressions" or "spurious correlations". 7,8 Recent research was able to determine the analytical expression for the second moment of the correlation coefficient for a pair of independent variables carrying out long random walks; and even for short walks, a characterization of the expected correlations has been presented. ...
Nonsense correlations frequently develop between independent random variables that evolve with time. Therefore, it is not surprising that they appear between the components of vectors carrying out multidimensional random walks, such as those describing the trajectories of biomolecules in molecular dynamics simulations. The existence of these correlations does not imply in itself a problem. Still, it can present a problem when the trajectories are analyzed with an algorithm such as the Principal Component Analysis (PCA) because it seeks to maximize correlations without discriminating whether they have physical origin or not. In this Article, we employ random walks occurring on multidimensional harmonic potentials to evaluate the influence of fortuitous correlations in PCA. We demonstrate that, because of them, this algorithm affords misleading results when applied to a single trajectory. The errors do not only affect the directions of the first eigenvectors and their eigenvalues, but the very definition of the molecule’s “essential space” may be wrong. Additionally, the main principal component’s probability distributions present artificial structures which do not correspond with the shape of the potential energy surface. Finally, we show that the PCA of two realistic protein models, human serum albumin and lysozyme, behave similarly to the simple harmonic models. In all cases, the problems can be mitigated and eventually eliminated by doing PCA on concatenated trajectories formed from a large enough number of individual simulations.
... Although two variables may appear to be strongly associated, they may not actually be if a spurious regression error is committed. Granger and Newbold (1974) demonstrated that two random walk series that have no meaningful association can be strongly correlated, generating a regression model with good fit. The problem can be addressed by determining the degree of stationarity for each variable using a unit root test. ...
Canada’s universities each receive an annual operating grant from their provincial gov-
ernment to partially finance operating expenses. This paper estimates the sensitivity of provincial operating grants to the business cycle by disentangling the effects of procyclical income on government revenue and the countercyclical effect on student demand by utilizing an economic regression model composed of three equations. Our panel data include the total real operating grant paid to all universities within a province, total student enrolment, real per capita government revenue, and real per capita gross domestic product for Canada’s ten provinces over the 1992–2019 sample
period. The results confirm that real per capita government revenues are procyclical and that full-time equivalent student enrolments are counter-cyclical. The total real operating grant is only weakly associated with cyclical changes in provincial government revenue. Instead, the total real operating grant is mainly determined by counter-cyclical changes in student demand. This partially offsets the potential reduction in funding to universities during an economic downturn. Provincial governments in Canada can smooth the total allocation over the business cycle by adjusting other expenditures and using debt financing. Our results suggest they do this to some extent, but not enough to avoid a net reduction in real operating grants during an economic downturn.
... Within a VAR model, the Granger causality concept is based on the idea that if past values of one variable aid in the prediction of another variable, then the first variable is deemed "Granger's cause" for the second variable. See the authors' papers, Granger (1969) and Granger and Newbold (1974) for a deeper understanding. Figure 1 shows the evolution, in returns, of the Brent Crude Spot, Euro Stoxx Oil & Gas, Nasdaq Clean Edge Green Energy, WilderHill Clean Energy, and Clean Energy Fuels stock indexes from May 3, 2018, to May 2, 2023. ...
The recent worldwide pandemic of 2020 and Russia's invasion of Ukraine in 2022 have sparked interest in understanding the links between clean and dirty energy markets. This research investigates the co-movements of clean energy and dirty energy stock indexes before and during the 2020 and 2022 events. The study focuses on the Brent Crude Spot, Euro Stoxx Oil & Gas, NASDAQ Clean Edge Green Energy, WilderHill Clean Energy, and Clean Energy Fuels stock indexes from May 3, 2018, to May 2, 2023. The goal is to determine if the events of 2020 and 2022 have increased co-movements between clean and dirty energy stock indexes, potentially challenging portfolio diversification. The results show that co-movements have increased, but portfolio diversification was no longer efficient during the tranquil period in international markets. These findings hold relevance for investors, policymakers, and other players in the energy financial market.
... For example, Auto regressive distributed lag is more flexible than Vector Auto regressive or Vector error correction Model (VecM) in terms of stationarity for i(0) and i (1). however, stationarity is a necessary condition for estimating cointegration and error correction methods and is important for checking the accuracy and adequacy of the data. in addition, the regression of non-stationary variables often leads to problems with spurious regressions, and variables only have contemporaneous relationships rather than full causality (Granger & Newbold, 1974;harris & Sollis, 2003). therefore, taking stationarity with the Ardl model does not guarantee data quality and assurance, so this flexibility leads to incorrect inferences and wrong conclusions, and undermine the overall robustness of the findings. ...
Most of the previous economic theories and empirical studies revealed that the relationship between population and economic growth is controversial and inconclusive in different parts of the world. However, previous studies have attempted to examine the relationship between population and economic growth, but their results have been vague or not even sufficiently realistic to address the issue practically. Thus, cognizant of this fact, this study investigates the dynamic effect of population and economic growth in Ethiopia. This study used a Vector Error Correction Model (VECM) and estimated using annual data for the period 1991-2022. The study found that, in the short run, high population growth was associated with increases in real gross domestic product. However, in the long run, population expansion hurts economic growth. Furthermore, the analysis shows that there is no causal relationship between population growth and economic growth by using block exogenity test. In conclusion, population growth has a greater short term positive impact on economic growth than it does in the long term. This study suggests that the government should adopt a pro-natal strategy that uses incentives for agricultural output in the short term to encourage individuals to have more families; the government should promote anti-natal policies to sustain economic growth that encourages individuals to have fewer children in the long run. Additionally, instead of solely focusing on population growth, the study suggests that the government prioritize and sustain economic growth by centralizing and improving the real money supply.
... Finally, the VAR Residual Serial Correlation LM test is used to determine whether the residuals are temporally autocorrelated. For more in-depth knowledge, reading the articles by Granger (1969) and Granger and Newbold (1974) is suggested. the volatility these markets were exposed to, especially in the first few months of 2022, coinciding with the Russian invasion of Ukraine. Figure 2 shows the mean returns of the Clean Energy Fuels, Nasdaq Clean Edge Green Energy, S&P Global Clean Energy, WilderHill Clean Energy stock indices and the precious metals Gold, Handy & Harman, Silver, Handy & Harman, and London Platinum over the period from January 1, 2021 to November 23, 2023. ...
This study contributes to the literature by examining the links between clean energy stocks and commodities such as gold, silver, and platinum. The purpose was to examine the clean energy stock indices, namely Clean Energy Fuels, Nasdaq Clean Edge Green Energy, S&P Global Clean Energy, WilderHill Clean Energy, and the precious metals Gold, Handy & Harman; Silver, Handy & Harman; and London Platinum over the period from January 1, 2021 to November 23, 2023. The results revealed significant changes in hedging asset characteristics related to the sustainable energy and precious metals indices. The movements that impact price formation increased from 11 to 18 in the conflict sub-period, indicating greater complexity and interdependence between the assets analyzed. These results have important implications in the context of enormous growth in investments in clean energy stocks and the repeated occurrence of periods of uncertainty.
... Granger and Newbold (1974) [63] proposed that conducting a regression analysis with non-stationary parameters could result in misleading regression. As a result, it became vital for a time series regression that the variables be stationarized. ...
This study investigates the key factors that influence household water usage in Amman, Jordan, with the aim of improving water management practices in a region facing significant scarcity. The research focuses on factors such as temperature, water pricing, system input, and family size. The Vector Error Correction Model with Exogenous Variables (VECMX) is applied to data from 1980 to 2015 to provide insights into consumption patterns, both in the short-term and long-term. The results show that family size and marginal costs significantly impact long-term water demand, while system input and family size influence short-term water demand. The study also finds that water pricing has a limited impact on consumer behavior, indicating inelasticity. Temperature and income, however, did not emerge as significant determinants. These findings highlight the need for water management policies in arid areas like Amman to prioritize factors other than price, such as household size and water infrastructure, to establish more effective strategies for conserving water.
... Previous studies have shown that spurious regression can occur between stationary and nonstationary time series [21,22]. For example, Kim et al. [23] found that when the sample size approaches infinity, the ordinary least square (OLS) estimator of regression coefficient for two series with trends convergence in probability to the ratio of the corresponding trend component, rather than the true correlation coefficient value between two series. ...
The regression of mutually independent time series, whether stationary or non-stationary, will result in autocorrelation in the random error term. This leads to the over-rejection of the null hypothesis in the conventional t-test, causing spurious regression. We propose a new method to reduce spurious regression by applying the Cochrane-Orutt feasible generalized least squares method based on a bias-corrected method for a first-order autoregressive model in finite samples. This method eliminates the requirements for a kernel function and bandwidth selection, making it simpler to implement than the traditional heteroskedasticity and autocorrelation consistent method. A series of Monte Carlo simulations indicate that our method can decrease the probability of spurious regression among stationary, non-stationary, or trend-stationary series within a sample size of 10–50. We applied this proposed method to the actual data studied by Yule in 1926, and found that it can significantly minimize spurious regression. Thus, we deduce that there is no significant regressive relationship between the proportion of marriages in the Church of England and the mortality rate in England and Wales.
... To examine the relationship between variables using F-statistics, the value must fall between the ranges of 0.01 to 0.05. According to Granger and Newbold (1974), the Durbin-Watson test value must be between the ranges of 1.5 to 2.5 in order to be recognized as acceptable. As showed in Table 3, the model utilizing DPA_avg and PTM_Avg as predictors accounts for approximately 31.4% of the variability observed in APS_avg.The variables DPA_avg and PTM_Avg have a moderate association (0.560) with the variable APS_avg. ...
The study examined the relationship between teachers' teaching methods and the academic performance of 150 undergraduate and Master's students from various fields of study. It contains a structural sample strategy to ensure the inclusion of individuals from various fields. A quantitative research methodology was used to administer a structured survey questionnaire, which was designed through a systematic literature review, in order to analyze students' diverse perspectives on teaching methods, academic performance, and demographic information. The independent variables consisted of perceptions of Teaching Methodologies and different pedagogical approaches, whereas the academic performance of students was the dependent variable. The statistical studies performed using SPSS software encompassed descriptive, regression, and factor analyses, revealing the connections between teaching approaches and academic success. The results emphasized the crucial significance of interactive, learner-focused instructional approaches in promoting enhanced academic performance. The active participation of students and the use of diverse teaching methods had a substantial impact on student achievement, emphasizing the importance of flexible instructional strategies. Nevertheless, traditional teacher-centered approaches demonstrated restricted influence. Although this study has limitations in terms of sample size and reliance on self-reported data, it highlights the need for an adaptable educational approach that incorporates evolving teaching methods to improve student outcomes. The research provides useful insights into effective pedagogical methods, advocating for a versatile and learner-centered educational environment. The study highlights the need for a better understanding of teaching methods' impact on academic performance to improve educational outcomes, resource allocation, curriculum development, and policy formulation.
... Time series are exposed to impacts that can create regular fluctuations, leading to biases. Granger and Newbold [48] claimed that a non-stationary time series could yield an incorrect outcome. Therefore, a series is said to be stationary if its second and first moments are constant and its relationship between its periods is constant regardless of the passing of time or the distance separating them. ...
This paper explores the asymmetric and symmetric influence of the human development index (HDI), economic growth, CO2 emissions and inflation on crude oil production (COP) in Cameroon from 1977 to 2019. The ZivotAndrews and Augmented Dickey-Fuller tests verified stationarity, the ARDL and NARDL models were applied to assess asymmetric and symmetric effects and finally, causality was established by the Toda-Yamamoto test. The results conclude that economic growth and CO2 emissions have a negative impact on COP in the long term, while in the short term the HDI and inflation have a positive impact. The presence of an asymmetric influence of HDI and economic growth in the short term, and an asymmetric influence of CO2 emissions and inflation on COP in the long term. A two way connection between economic growth and COP. A unidirectional link between the HDI, CO2 emissions and inflation on COP. As a result of these findings, policies have been formulated to help Cameroon achieve crude oil production that is beneficial to social and economic development while respecting environmental standards.
... The assumption of the classical regression model necessitates that both the dependent and independent variables be stationary and the errors have a zero mean and finite variance. According to Granger and Newbold (1974), the effects of non-stationarity include spurious regression, high R 2 and low Durbin-Watson (DW) statistic. Below are basic reasons why data must be tested for non-stationarity. ...
This paper examined the relationship between trade liberalization and poverty reduction in Nigeria using quarterly data from 2000 to 2022. The Augmented Dickey-Fuller test and Johansen co-integration test were used to determine the stationarity of the time series data. The research used the Error Correction Model (ECM) due to the stationarity status of the data. The findings show that important variables (capital importation, trade openness, foreign portfolio investment, foreign direct investment and poverty index) converge over the long term, demonstrating the presence of a long-term link between them. ECM is within the acceptable range of less than unity and has the anticipated negative sign. Specifically, trade openness, capital importation and foreign portfolio investment have positive impact on poverty level. The impact is significant for capital importation and foreign portfolio investment while trade openness has insignificant impact on poverty level. Foreign direct investment has negative and insignificant impact on poverty level while exchange rate has positive and significant impact on poverty level. It is therefore recommended that government should enact trade policies that will make international trade favourable to Nigeria and beneficial to the citizenry. The Government should ensure that values are added to primary products being exported in order to gain more from trade liberalization. The Government should improve on the ease of doing business to attract and sustain more foreign investors in critical sectors of the economy that have capacity to increase output, income and reduce poverty.
... The concept of Granger causality within a SVAR model is based on the idea that if the past values of one variable help to improve the prediction of another variable, then the first variable is considered a "Granger cause" of the second variable. For a better understanding of the model, the papers by Granger (1969) and Granger and Newbold (1974) are helpful. Based on the results, it was found that all the indices had positive mean returns, with the exception being the MASI (-2.074e-05) and the Platinum market (-2.10e-05), while concerning the index with the greatest risk, it was found that the MOEX (0.0175) had the most significant deviation from the mean. ...
In the context of the global pandemic of 2020 and the Russian invasion of Ukraine in 2022, a newfound interest is emerging in understanding the interconnections between the Dow Jones (United States), Amman SE General (Jordan), BLSI (Lebanon), EGX 30 (Egypt), ISRAEL TA 125 (Israel), MASI (Morocco), and MOEX (Russia) indices and the precious metals markets Gold Bullion LBM, Silver, Handy & Harman, London Platinum, from January 1, 2018 to November 23, 2023. The study aimed to determine whether precious metals such as Gold, Silver, and Platinum can be considered hedging assets to the stock markets of the Middle East and North Africa (MENA) countries, i.e., whether investors operating in these regional markets can rebalance their portfolios with these precious metals. The structural vector autoregressive (SVAR) methodology allowed assessing the influence of the analyzed markets on each other regarding price formation. The results show that the markets interacted very significantly during the stress period. Platinum was the market that most influenced its peers (1 to 8 comove-ments), the MOEX, 1 to 7, MASI, 2 to 6, the Dow Jones went from 4 to 7 comove-ments, the Amman SE General and EGX 30 markets went from 1 to 4, the Israeli market (ISRAEL TA 125) and Silver went from 2 to 4 comovements, and finally the Gold Bullion LBM from 3 to 4.
A condição de não estaticidade dos seguros em geral se dá por se tratar de uma ciência que depende de fatores sociais e econômicos para se sustentar. O Seguro de Vida, em especial, é impactado por diversos agentes, desde políticas econômicas e culturais, até o desempenho das seguradoras quanto a oferta e demanda do seu produto e aspectos sociodemográficos que influenciam no comportamento do próprio segurado. O conhecimento sobre o risco identificado é fundamental para que a avaliação seja realista e precisa. Para garantir a solvência dessas empresas e assegurar os compromissos futuros, diversas premissas atuariais estão envolvidas no gerenciamento e precificação de riscos, como análise de frequência de sinistros, severidade, risco biométrico, análises de sensibilidade e subscrição, acompanhamento de sinistralidade, entre outras, cabendo ao atuário responsável adequar tais medidas a realidade da instituição de risco. Portanto, este trabalho tem como objetivo avaliar modelos de previsão para uma das premissas atuariais mencionadas, a saber, a sinistralidade, por meio de métodos de regressão e Box-Jenkins. Foram analisados os dados mensais disponíveis no Sistema de Estatísticas (SES) da Superintendência de Seguros Privados (SUSEP), entre os anos de 2011 e 2021, das oito seguradoras com maior volume de prêmio. A capacidade de previsão dos modelos foi avaliada comparando os valores previstos com os dados reais do 1° semestre de 2022. O modelo de regressão foi o mais adequado para a previsão da sinistralidade, embora ambos os métodos tenham apresentado desempenho satisfatório.
Ekonomik büyümeyi artıran nedenlerin başında beşeri sermaye stoğuna yapılan yatırımlar gelmektedir. Bu yatırımlardan biri de sağlık harcamalarıdır. Bir ülkedeki sağlık harcamalarının artması, eğitimin etkisiyle bilinçli toplumun sağlık hizmetlerinden daha verimli yararlanmasına ve dolayısıyla o toplumun gelişmesine ve refah seviyesinin artmasına pozitif katkı sağlayacaktır. Çalışmada Türkiye’de 2000-2018 dönemlerine ait ekonomik büyüme ve sağlık harcamaları değişkenleri arasındaki uzun dönem ilişki Auto Regressive Distributed Lag, (ARDL, Gecikmesi Dağıtılmış Otoregresif Model) testi ile incelenmiştir. Yapılan analizler sonucunda ekonomik büyüme ile sağlık harcamaları arasında pozitif ve anlamlı uzun dönemli bir ilişki olduğu gözlemlenmiştir.
The paper examines the causality between the German current account and financial account. It contrasts with past research which assumes the current account and financial account to be jointly determined by a saving-investment imbalance. Our analysis decomposes the current account into exports and imports (real resource flows) and the financial account into domestic capital outflows and foreign capital inflows (gross capital flows). Evidence from the Toda-Yamamoto causality test shows that for Germany from Q1.1980 to Q2.2023, the causality runs from the financial account to the current account. It is not real resource flows but gross capital flows which exert significant impacts on the German real exchange rate. The finding implies that over the long run, strong German capital outflows and weak foreign capital inflows contributed to weak wage growth and stagnant investment in Germany, sustaining the persistent German current account surpluses. A reduction of the German current account surpluses requires a policy mix of fiscal expansion and monetary tightening which would expand the absorption of German and foreign capital in the German economy.
The Mediterranean region is an important agricultural center and is expected to be most affected by climate change due to its location. In this study, the role of climate change on agriculture is examined for eight South European countries on the Mediterranean coast for the period of 1996–2016. Carbon dioxide emissions, temperature and precipitation values are used as the indicators of climate change while cereal production is taken as a proxy for agricultural production. Results of the panel vector autoregression approach reveal that an increase in the carbon dioxide emissions and temperature have a negative impact on the cereal production. However, this effect is statistically significant only in the initial periods. On the other hand, an increase in rainfall has a statistically significant positive effect on crop production only in one period. However, eventually this effect turns to negative as expected, since excessive rainfall has a negative effect on agriculture as much as drought. In conclusion, the importance of bringing the policies and strategies to the forefront in ensuring the sustainability of agriculture and minimizing the negative effects of climate change in the region are discussed.
Using the Environmental Kuznets curve (EKC) framework, this study aimed to quantify the effects of agricultural innovation, the use of renewable energy, and economic growth on CO2 emissions in Nepal from 1990 to 2018. To examine the empirical findings, the current study used fully modified ordinary least squares and canonical cointegration estimators to derive the long-run associations between the variables. Similarly, the study used the Toda–Yamamoto causal test to determine the causal relationships. The empirical findings disproved the existence of an EKC with an inverted U form. Furthermore, agricultural innovations were shown to lead to long-term improvements in environmental quality. Similarly, the findings indicated that urbanization and renewable energy significantly lower Nepal’s CO2 emissions. The causal test explored the unilateral linkages from agricultural innovations to CO2 emissions and renewable energy to CO2 emissions. In contrast, the results indicated bidirectional causal associations between income and CO2 emissions and agricultural innovations and CO2 emissions. These results are unique and have substantial policy implications discussed in the study.
The present research aimed to investigate the effects of monetary policy on the US stock market between December 2008 and December 2021. This period had a significant absolute return advantage for growth stocks over value stocks, in contrast to research that has historically shown an advantage for value stocks over growth stocks. For this reason, we sought to examine whether the monetary policy of the period would have benefited growth stocks through the application of a vector autoregressive (VAR) model with an error correction vector (VEC model), using as variables four exchange-traded funds (ETFs) that passively follow indices, two of which are value and two growth. The total assets on the Federal Reserve (Fed) balance sheet were utilized to analyze the effects of monetary policy in this period. The results demonstrated, by the generalized impulse-response functions, the greater long-term elasticity of growth ETFs to shocks in the value of Fed assets, confirming the hypothesis that monetary stimuli positively influenced the absolute returns of stock price growth and value in the demarcated period, with greater benefits for growth stocks.
Bankalar, türev ürünlerin en büyük kullanıcılarıdır ve bankaların türev ürün kullanım kararlarını etkileyen karmaşık faktörlerin incelenmesi önemlidir. Ancak mevcut literatürde gelişmiş ve gelişmekte olan ülkelerdeki bankaların döviz türevi kullanımını etkileyen faktörlerin karşılaştırmalı analizlerine rastlanmamıştır. Bu alandaki boşluğu doldurmak amacıyla gelişmekte olan ve gelişmiş ülkelerde faaliyet gösteren bankaların döviz türevi kullanımını inceleyen bir çalışma yapılmıştır. Çalışmada, 21 gelişmiş ülkedeki 104 banka ve 12 gelişmekte olan ülkedeki 41 bankanın, 2010-2020 yılları arasındaki bankacılık ve makroekonomik verileri panel veri analiziyle incelenmiştir. Analiz dönemi, veriye ulaşımın kısıtlı olması nedeniyle 2010-2020 arasında sınırlı kalmıştır. Sonuçlar, gelişmiş ve gelişmekte olan ülkelerde, faiz oranları ve banka büyüklüğünün döviz türevi kullanımı ile pozitif ilişkili olduğunu göstermektedir. Gelişmekte olan ülkelerde kur ve krediler, döviz türevi kullanımıyla pozitif ilişkilidir. Ancak, gelişmiş ülkelerde mevduat büyüklüğünün artması döviz türevi kullanımını artırırken, gelişmekte olan ülkelerde azaltmaktadır. Öz kaynakların artması gelişmiş ülkelerde döviz türevi kullanımını azaltırken, finansal kurumlar endeksinin yükselmesi döviz türevi kullanımını artırmaktadır.
Son yirmi otuz yıl içerisinde artan yaşlı nüfus ve yükselen refah beklentileri ülkelerin sosyal güvenlik sistemlerinin finansal sürdürülebilirliğini risk altına sokmuştur. Bu riskten korunmak için bireysel emeklilik sitemleri genel kabul gören bir çözüm yolu olarak ortaya çıkmış ve birçok ülke tarafından benimsenmiştir. Günümüze kadar geçen süre içerisinde bireysel emeklilik sistemleri, devasa fonların birikmesi sonucunda alternatif bir emeklilik imkânı sunmanın ötesine geçerek kurumsal yatırımcı kimliği kazanmıştır. Bu açıdan ekonomik bir unsur olarak değerlendirilen özel emeklilik fonları sermaye piyasalarının derinleşmesine çok önemli katkılarda bulunmaktadır. Türkiye’de, idari yapılanma tarafından çeşitli yöntemlerle teşvik edilen Bireysel Emeklilik Sistemi ile toplanan katkı payları, emeklilik fonları aracılığı ile yatırıma yönlendirilmektedir. Bu çalışmada, söz konusu katkı paylarının finansal piyasalara olan etkisi kurulan regresyon modelleri ile test edilmiştir. Ulaşılan bulgulara göre, pay piyasalarında anlamlı bir nedensellik ilişkisi tespit edilememiştir. Borç piyasalarında ise toplanan katkı payları ile gösterge faiz arasında negatif katsayılı(ters yönlü) anlamlı bir nedensellik ilişkisi tespit edilmiştir. Bu duruma, fonların varlık dağılımlarında borçlanma araçlarına ayrılan payın diğer yatırım araçlarına nazaran yüksek olmasının neden olduğu düşünülmektedir.
“MINT Ülkeleri” tanımlaması Meksika, Endonezya, Nijerya ve Türkiye ekonomilerini ifade etmektedir. MINT ülkelerinin ekonomisi, gençlerin yoğun olduğu kalabalık bir nüfus, hızlı ekonomik büyüme ve yüksek girişimcilik özellikleri göstermektedir. Bu çalışma MINT ülkelerinin borsa endeksleri için getiri oynaklığı ile işlem hacmi arasındaki ilişkiyi incelenmektedir. Çalışmanın veri seti Haziran 2019 – Mart 2023 dönemini kapsamakta ve günlük frekanslı verilerden oluşmaktadır. Endeks getiri serilerine ilişkin asimetrik etkinin tespiti için E-GARCH(1,1) modeli tahmin edilmiştir. Model sonuçları, Nijerya hariç olmak üzere, Meksika, Endonezya ve Türkiye pay senedi piyasaları için getiri oynaklığına etki eden şokların etkilerinin asimetrik olduğuna işaret etmektedir. Getiri oynaklığı-işlem hacmi ilişkisinin tespiti için oluşturulan modellere eş zamanlı işlem hacmi ve ardından işlem hacminin gecikmeli değeri dâhil edilerek yeni modeller oluşturulmuştur. Elde edilen bulgular Meksika, Endonezya ve Türkiye pay senedi piyasaları için Ardışık Bilgi Akışı Hipotezinin geçerli olduğunu göstermektedir. İlgili ülke borsa endeksi getiri oynaklığı dinamiklerini açıklama noktasında hacim verisi ve gecikmeli değerleri önemli bir değişkendir. Nijerya pay senedi piyasası için ise Karışık dağılımlar Hipotezinin geçerli olduğu yönünde bulgulara ulaşılmıştır. Nijerya borsa endeksi getiri oynaklığını açıklamada işlem hacmi verisinin anlamlı bir katsayıya sahip olduğu tespit edilmiş olup, getiri oynaklığı ile işlem hacminin gecikmeli verisi arasında benzer ilişkinin mevcut olmadığı, ilişkinin devam etmediği sonucuna ulaşılmıştır.
There is a wide variety of non-seasonal and seasonal unit root tests. However, it is not always obvious which tests can be relied upon due to uncertainties in identifying the data generating process, often with respect to the presence of deterministic terms and the initial conditions. We evaluate the size and power of a large set of unit root tests on time series that are simulated to be representative of economic time series in the M4 competition data. Furthermore, using a conditional random forest-based elimination algorithm, we assess which tests should be combined to improve the performance of each individual test.
The impact of technological progress on employment is a highly controversial topic in the theoretical and empirical literature. They are theoretically called optimistic, pessimistic and balancing views, respectively, that technological development increases, reduces and does not affect employment. Nevertheless, there is no common opinion in the empirical literature regarding the effect of technological development on employment. Employment destabilization, which started after the "2008 global crisis", still maintain.
The present study aims at highlighting the determinants and degree diversification of export in Pakistan. The index of export’s diversification by the United Nations Conference on Trade and Development is used to calculate the degree of export diversification. Furthermore, using time series data from 1995 to 2022, present study examines the factors that influence export diversification. There are very few studies that address estimating and determinants in the context of Pakistan. To check the unit root problem Augmented Dickey Fuller test is used. The Auto Regressive Distributive Lag method is used in this study to observe long-term relationships in the underlying variables. The regression results indicate that official exchange rates, economic globalization, and foreign direct investment negatively affect export diversification in Pakistan. While, gross fixed capital formation, world GDP per capita, term of trade, and political stability positively affect diversification of exports in the case of Pakistan.
Bu çalışmanın amacı, dijital bankacılık araçları ile bankacılık sektörü çalışan sayısı arasındaki ilişkiyi araştırmaktır. Bu amaç doğrultusunda çalışmada 2006q1-2022q4 dönemine ait veriler kullanılmıştır. Bu veriler korelasyon analizi ve Vektör Otoregresyon Modeli (VAR) yöntemleri kullanılarak analiz edilmiştir. Elde edilen korelasyon analizi sonucuna göre, dijital bankacılık (DIG) ve bankamatik (ATM) sayıları arttıkça çalışan sayısının (PN) da artması beklenmektedir. VAR analizi üzerinden elde edilen etki-tepki fonksiyonu sonuçlarına göre PN’de meydana gelen bir standart sapmalık şoka karşılık değişkenin kendisi pozitif ancak azalarak 12. dönemde sönümlenen bir tepki vermektedir. DIG ve ATM değişkenlerinde meydana gelen bir standart sapmalık şoka karşılık da PN değişkeninin pozitif tepkiler verdiği ancak 5. dönemde DIG kaynaklı şokların, 6. dönemde ise ATM kaynaklı şokların etkisinin kaybolduğu görülmektedir. Varyans ayrıştırması sonuçlarına göre ise çalışan sayısı değişkeninin varyansındaki değişimin yaklaşık %89.5’u kendisindeki, %2’si dijital bankacılık değişkenindeki ve %8.3’ü ise bankamatik değişkenindeki değişimlerden kaynaklanmaktadır. Elde edilen bu sonuçlara göre bankacılık sektöründeki dijitalleşmenin çalışan sayısını arttırması beklenmektedir.
This study presents a time series analysis of the long-term stock performance of airlines, with a focus on Turkish Airlines (THY). Stock-related variables were obtained from the Istanbul Stock Exchange, and other variables were obtained from the Turkish Statistical Institute. The research investigates various economic factors that may influence THY's stock prices over an extended period. Specifically, the study examines the relationship between global energy prices, inflation, the BIST100 index, gold prices, exchange rates, and THY stock prices. The analysis employs the Autoregressive Distributed Lag (ARDL) approach, a versatile technique capable of estimating both short-term and long-term relationships between variables. The findings of this research reveal significant and statistically meaningful connections between these economic variables and THY's stock prices. Notably, the study highlights the impact of global energy prices and other economic factors on the long-term stock performance of Turkish Airlines. These results provide valuable insights for investors and analysts seeking to understand and forecast THY's stock price movements.
Following the initiatives of the United Nations Framework Convention for Climate Change (UNFCCC) and especially since the Paris Agreement of 2015, corporate environmental performance has become a critical component of corporate financial performance. Particularly, stakeholder pressure has driven environmental and financial inclusion targeted at raising corporate performance. Hence, this paper examines the link between corporations’ environmental performance (CEP) and corporations’ financial performance (CFP) using annual panel data from 130 corporations from China and 166 corporations annually over the years from 2010 to 2018. The empirical results from the FMOLS and ARDL tests show that corporations’ good emission preventive practices translate into improved financial performance in Japan but not in China, which is a reflection of the advanced earlier development of environmental governance in the former and the latecomer status of the latter. Nevertheless, environmental disclosure raises corporate financial performance in both China and Japan in the long run but CSR strategy is negatively correlated with corporate financial performance. Also, while the Dumitrescu Hurlin causality test shows that there is significant bidirectional causality between CEP and CFP in the Japan sample, this relationship is weak in the China sample. While the results confirm actions by Japan and China to strengthen corporate environmental governance, the initiatives in China should be quickened to enhance the relationship between CEP and CFP.
Aim
The effective connectivity between the striatum and cerebral cortex has not been fully investigated in attention‐deficit/hyperactivity disorder (ADHD). Our objective was to explore the interaction effects between diagnosis and age on disrupted corticostriatal effective connectivity and to represent the modulation function of altered connectivity pathways in children and adolescents with ADHD.
Methods
We performed Granger causality analysis on 300 participants from a publicly available Attention‐Deficit/Hyperactivity Disorder‐200 dataset. By computing the correlation coefficients between causal connections between striatal subregions and other cortical regions, we estimated the striatal inflow and outflow connection to represent intermodulation mechanisms in corticostriatal pathways.
Results
Interactions between diagnosis and age were detected in the superior occipital gyrus within the visual network, medial prefrontal cortex, posterior cingulate gyrus, and inferior parietal lobule within the default mode network, which is positively correlated with hyperactivity/impulsivity severity in ADHD. Main effect of diagnosis exhibited a general higher cortico‐striatal causal connectivity involving default mode network, frontoparietal network and somatomotor network in ADHD compared with comparisons. Results from high‐order effective connectivity exhibited a disrupted information pathway involving the default mode‐striatum‐somatomotor‐striatum‐frontoparietal networks in ADHD.
Conclusion
The interactions detected in the visual‐striatum‐default mode networks pathway appears to be related to the potential distraction caused by long‐term abnormal information input from the retina in ADHD. Higher causal connectivity and weakened intermodulation may indicate the pathophysiological process that distractions lead to the impairment of motion planning function and the inhibition/control of this unplanned motion signals in ADHD.
The aim of this study is to determine the impact of technological progress on wage inequality in the context of non-standard employment. For this purpose, an econometric analysis was conducted on the data of 31 OECD countries for the years 2000-2019. In order to understand the relationship between ‘technological progress and non-standard employment' and ‘technological progress and wage inequality,' five different data sets were used. The results show that technological innovation leads to an increase in non-standard employment. However, technological progress and non-standard employment did not have a negative impact on wage inequality. The results of the study have important implications for the effects of technology on employment and wage inequality.
We consider the problem of detecting causal relationships between discrete time series, in the presence of potential confounders. A hypothesis test is introduced for identifying the temporally causal influence of (
x<sub>n</sub>
) on (
y<sub>n</sub>
), causally conditioned on a possibly confounding third time series (
z<sub>n</sub>
). Under natural Markovian modeling assumptions, it is shown that the null hypothesis, corresponding to the absence of temporally causal influence, is equivalent to the underlying ‘causal conditional directed information rate’ being equal to zero. The plug-in estimator for this functional is identified with the log-likelihood ratio test statistic for the desired test. This statistic is shown to be asymptotically normal under the alternative hypothesis and asymptotically
χ
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
distributed under the null, facilitating the computation of
p
-values when used on empirical data. The effectiveness of the resulting hypothesis test is illustrated on simulated data, validating the underlying theory. The test is also employed in the analysis of spike train data recorded from neurons in the V4 and FEF brain regions of behaving animals during a visual attention task. There, the test results are seen to identify interesting and biologically relevant information.
The planet is currently grappling with ecological upheaval as a consequence of the relentless surge in global warming. In response, the Danish government has undertaken a commitment to environmental decarbonization, setting a goal for the year 2030. This study contributes to these efforts by assessing the extent to which domestic material biomass and raw material productivity consumption impact ecological sustainability in Denmark. This assessment is based on data spanning from 1990 to 2020. Furthermore, the study takes into consideration the additional effects of economic advancement and domestic consumption of fossil fuels. These factors are addressed using a nonlinear auto-regressive distributed lag approach, which captures their respective positive and negative influences. The outcomes of the study affirm that positive (negative) shifts in domestic consumption of biomass and raw materials productivity contribute to increased (decreased) ecological sustainability in Denmark. Similarly, positive (negative) shifts in economic growth and domestic consumption of fossil fuels lead to decreased (increased) environmental sustainability. These conclusions are further substantiated by the causality results in the frequency domain. Drawing from these empirical findings, the study presents various strategies aimed at advancing diverse sustainable development goals, offering potentially beneficial avenues for Denmark's progress.
As a prominent CO 2 producer in Southeast Asia, Malaysia is taking steps to mitigate carbon emissions amid its rapid economic expansion. However, there remains a limited understanding of the complex relationships among various factors such as domestic credit (DRC), energy consumption, green technology policy (GTP), oil prices (OPs), and FDI in shaping CO 2 emissions. This study addresses this gap by examining both symmetric and asymmetric impacts of these factors-FDI, renewable and non-renewable energy consumption, OP, GTP, DRC, and gross domestic products (GDP)-on CO 2 emissions in Malaysia, considering both short and long-term effects. Our research, which combines block exogeneity causation with ARDL and non-linear ARDL cointegration approaches, spans data from 1980 to 2021 and provides several significant discoveries. This study provides support for the Environmental Kuznets curve hypothesis, highlighting the intricate balance between economic growth and environmental conservation. The symmetric findings reveal that factors such as high GDP, FDI, renewable energy
Delegation of power can of political, social and fiscal authority and all the three has been considered an important policy reform to achieve high growth, better delivery of services and stabilize the macro uncertainties in economy. Among the three types of decentralization, this study was conducted to assess the fiscal aspect of decentralization and its impacts were analyzed on public services deliveries, which is one of the core objectives of power delegation. Pakistan was taken as a sample case. Annual time series data spanning from 1974 to 2021 were sourced from both the World Bank and the economic survey of Pakistan. Fiscal decentralization was measured through fiscal transfers and vertical balances while public services were proxy through health sector. In health sector this study took infant mortality rates because of the ways availability of data. Per capita GDP, Rural-Urban ratio and health expenditures were taken as a control variable. The results were extracted through ARDL and it was found that between the two proxies of fiscal decentralization, fiscal transfers is more effective than vertical balances and therefore it was suggested that government may increase the share of provinces to further improve the delivery of public services in Pakistan.
Research examining the effects of COVID-19 on the criminal legal system—including the demand for police services—is accumulating. However, few empirical inquiries have sought to examine the pandemic’s effect on mental health and wellbeing by analyzing calls for service (CFS) involving emotionally disturbed persons (EDP). This study examines CFS received pre- and post-pandemic by Houston’s crisis intervention team (CIT). By examining visual trends and using interrupted time-series analysis (ITSA), we analyze COVID-19’s immediate and long-term effects. In the current study we examine three distinct call types: (1) Risk to others; (2) Risk to self; and (3) Welfare calls. Findings demonstrate significant increases in the overall CFS after the implementation of the initial stay-at-home order in Houston, with some differences in trends based on call type. These findings further our understanding of COVID-19’s impact on mental health and wellbeing during the pandemic through the lens of the increased demand for police services. Specific implications for the study site department are discussed, and to the extent possible, general implications for other departments with CIT programs.
As the population increases, spending on publicly provided goods must also increase if there is congestion and governments want to maintain provision of the same level of benefit to everyone. This article estimates a parameter capturing this impact of congestion for the state and local component of the general government sector in Australia. It shows the congestion parameter is likely to be between 0.51 and 0.84 implying super congestion and/or decreasing returns to scale have dominated the supply of these goods. The per person cost of congestion has been rising and differs across states. Larger jurisdictions also have relatively higher per person congestion costs.
The method of analysis used in a recent paper on economic forecasting is reviewed. Evidence is presented that what were believed to be highly significant relationships making possible the forecasting of the Financial Times share index arise because of the inflexibility of the assumed error structure.
A number of procedures for forecasting a time series from its own current and past values are surveyed. Forecasting performances of three methods--Box-Jenkins, Holt-Winters and stepwise autoregression--are compared over a large sample of economic time series. The possibility of combining individual forecasts in the production of an overall forecast is explored, and we present empirical results which indicate that such a procedure can frequently be profitable.
In recent years, a number of power spectra have been estimated from economic data and the majority have been found to be of a similar shape. A number of implications of this shape are discussed, particular attention being paid to the reality of business cycles, stability and control problems, and model building.
First Published in 2005. Routledge is an imprint of Taylor & Francis, an informa company.
Typescript (photocopy). Thesis--University of Nottingham. Includes bibliographical references (303-308).
New York stock price series are analyzed by a new statistical technique. It is found that short-run movements of the series obey the simple random walk hypothesis proposed by earlier writers, but that the long-run components are of greater importance ...