Quantile Test Research Articles

Revisiting the interest rate-investment nexus in India: fresh perspective from non-parametric analysis

PurposeIt is generally believed that business spending on capital expenditure tends to decrease as interest rates rise, and vice versa, this is not always the case. The previous literature produces inconclusive results vis-à-vis the interest rate and investment nexus. This study analyzes the responsiveness of investment to changes in high and low levels of interest rates in India through a quantile-based, non-parametric method utilizing annual data from 1980 to 2022.Design/methodology/approachThis study uses Quantile-on-quantile (QQ) technique proposed by Sim and Zhou (2015) to examine the impact of interest rate quantiles on quantiles of investment. In addition, long-term association and the direction of causality are estimated through the Cho et al. (2015) test of quantile cointegration and the Jeong et al. (2012) Granger causality in quantile (GCQ) test, respectively.FindingsThe empirical evidence validates that the linkage between investments and interest rate is not consistently negative and varies from quantile to quantile. The study finds a negative impact at median quantiles and a positive impact at extreme higher quantiles. Conversely, the impact at lower quantiles is negligible, which is also observed from quantile cointegration, indicating the presence of a statistically significant association above the median quantiles. Additionally, the study finds one interesting finding that there exists unidirectional causality from investment to interest rates in India rather than other way around.Research limitations/implicationsThe study provides significant implications for policymakers as it suggests that during extreme economic conditions, the effectiveness of traditional monetary policy tools to boost capital formation is restricted. Policymakers may consider alternative measures to stimulate investment during these time periods. The study additionally posits that the neoclassical theory of investment may not be readily applicable in emerging economies in its unaltered state, mostly due to the lack of well-developed financial markets.Originality/valueThere is a limited literature available on non-linear linkage between interest rates and investment. The present study adds to the existing knowledge by investigating how investment responds differently to fluctuations in interest rates, while incorporating the complete distribution of both the variables.

Greening wallets or worsening landscapes: Exploring carbon footprints of renewable energy, tourism, and financial development indices

AbstractSustainable development goals (SDGs) 7 and 13 of the United Nation's 2030 Agenda for Sustainable Development emphasize cheap and clean energy and climate action, respectively. The relentless pursuit of sustainable development has spurred a growing interest in understanding the intricate relationships between carbon footprints, renewable energy practices, tourism, and financial development indices. This research embarks on a comprehensive exploration of the interplay among these critical factors, aiming to unravel the nuanced dynamics that shape our environmental and economic landscape of the top 10 tourist countries from 1991 to 2021. This investigation was conducted through quantile‐based modeling, where the long‐run estimates are achieved through lower, middle, and higher quantiles. Nevertheless, findings suggest that a 1% increase in tourism development will approximately result in a 0.109% to 0.298% increase in carbon footprint in the lower quantile quantiles, that is, the 10th to 30th quantile. In the middle and higher quantiles (40th to 60th and 70th to 90th), 0.313% to 0.565% and 0.721% to 1.369%, respectively. However, renewable energy and financial development index are the significant sources of reducing carbon footprints from the 10th to the 90th quantiles. Still, the intensity of their impacts is heterogeneous among different quantiles. Empirical findings demonstrate that financial development stimulates a growing demand for environmentally sustainable energy sources. Utilizing renewable energy decreases the presence of greenhouse gases in the environment in contrast to the use of fossil fuels. However, renewable energy, tourism, and financial development indices are concluded to be the cornerstones concerning carbon footprints through their distinct impacts. This study's quantile slope equality and symmetric quantile tests further corroborated the findings. Upon the conclusion of the current study, this research has offered policy implications for regulatory bodies and has deliberated on potential avenues for future investigation.

Quantile modeling for environmental risk: SAARC's journey with green finance, policies, and regulations

Environmental risk assessment and management have become critical issues facing global climate change and its multifaceted consequences. The 2030 United Nations Sustainable Development Goal (SDG) 13 prioritizes a sustainable environment and urgent climate change mitigation. The present study aimed to make accountability of environmental risk through green finance, financial development, policies, and regulations in SAARC countries. Using data from 2005 to 2022, the panel quantile regression (PQR) approach is applied to estimate the long-run coefficients at lower, middle, and upper quantiles. Overall, the study results indicate heterogeneity in the parameters impacting the environmental risk in SAARC. The findings from the PQR unveiled that green finance contributes to mitigating environmental risk in higher quantiles. Financial development contributes to environmental risk in the middle (40th to 60th) and higher quantiles (70th to 90th). It is concluded that the appropriate business regulatory framework reduces environmental risk in higher quantiles, and poor and low-rated policies increase it in the middle, and higher quantiles. Nevertheless, foreign direct investments increase environmental risk in lower and middle quantiles. Overall, there is a heterogeneity in the results; however, the amplitude of their parameters varied substantially. The quantile slope equality (QSE), symmetric quantile (SQ) tests, and fully modified ordinary least square (FMOLS), also confirmed the robustness of the results. Finally, the empirical findings of this study have prudent policy implications for the stakeholders concerning environmental risk.

Forecasting risk of European carbon emissions trading market with DySco-SKST model

Influenced by energy prices, macroeconomic factors and policy factors, the price of the European carbon emissions trading market has changed significantly. Effective measurement of price risk of the European carbon emissions trading market is of practical importance for market participants. Two measures Value at Risk (VaR) and Expected shortfall (ES) are used to assess price risk. Based on the dynamic score (DySco) model and skewed Student-t (SKST) distribution, the DySco-SKST model is constructed and used to predict the price risk. The unconditional/conditional coverage tests, dynamic quantile test, Actual over Expected ratio, mean and maximum Absolute Deviation, quantile loss and FZ loss are used to evaluate the VaR and ES prediction performance. The daily spot closing prices of EUAs from January 3, 2013 to November 23, 2018 are used. The empirical results show that the VaR and ES prediction performance of the DySco-SKST model is better than that of the DySco-N and DySco-ST models. The VaR and ES prediction performance is affected by the parameter re-estimation scheme, but not by the parameter re-estimation frequency. The DySco-SKST model is better at predicting VaR and ES under the rolling window than under the expanding window.

Hypothesis testing on high dimensional quantile regression

Quantile regression has been an important analytical tool in econometrics since it was proposed in 1970s. Many advantages make it still popular in the era of big data. This paper focuses on the testing problems of high-dimensional quantile regression, supplementing to robust methods in the literature of high-dimensional hypothesis testing. We first construct a new test statistic based on the quantile regression score function. The new test statistic avoids the inverse operation of the covariance matrix, and hence becomes applicable to high-dimensional or even ultrahigh-dimensional settings. The proposed method retains robustness for non-Gaussian and heavy-tailed distributions. We then derive the limiting distributions of the proposed test statistic under both the null and the alternative hypotheses. We further investigate the case where the design matrix follows an elliptical distribution. We examined the finite sample performance of our proposed method through Monte Carlo simulations. The numerical comparisons exhibit that our proposed tests outperform some existing methods in terms of controlling Type I error rate and power, when the data deviate from the Gaussian assumptions or are heavy-tailed. We illustrate our proposed high-dimensional quantile testing in financial econometrics, through an empirical analysis of Chinese stock market data.

A new generalized exponentially weighted moving average quantile model and its statistical inference

The exponentially weighting scheme is a simple and pragmatic approach to compute the value at risk (VaR). However, the existing exponentially weighting methods lack a sound statistical inference procedure. To circumvent this deficiency, this paper proposes a new generalized exponentially weighted moving average (GEWMA) quantile model, which allows a much broader weighting scheme than the benchmark one used in “Risk Metrics” document. For the GEWMA quantile model, a systematic statistical inference procedure is provided, including the weighted estimators for the weighting parameters, a t-test for the stability of the conditional quantile, another t-test for the mean invariance of the conditional quantile, a unit root test for the absence of intercept term, and several dynamic quantile tests for the model checking. Under mild conditions, the asymptotics of all proposed estimators and tests are established. Simulations show that all proposed estimators and tests have good finite-sample performances. Applications to four major exchange rates demonstrate that the weighting scheme suggested by “Risk Metrics” document is inappropriate, and the GEWMA quantile model delivers better VaR predictions than its many competitive methods. As an extension, the asymmetric GEWMA quantile model is also studied.

Do artificial neural networks provide improved volatility forecasts: Evidence from Asian markets

This paper enters the ongoing volatility forecasting debate by examining the ability of a wide range of Machine Learning methods (ML), and specifically Artificial Neural Network (ANN) models. The ANN models are compared against traditional econometric models for ten Asian markets using daily data for the time period from 12 September 1994 to 05 March 2018. The empirical results indicate that ML algorithms, across the range of countries, can better approximate dependencies compared to traditional benchmark models. Notably, the predictive performance of such deep learning models is superior perhaps due to its ability in capturing long-range dependencies. For example, the Neuro Fuzzy models of ANFIS and CANFIS, which outperform the EGARCH model, are more flexible in modelling both asymmetry and long memory properties. This offers new insights for Asian markets. In addition to standard statistics forecast metrics, we also consider risk management measures including the value-at-risk (VaR) average failure rate, the Kupiec LR test, the Christoffersen independence test, the expected shortfall (ES) and the dynamic quantile test. The study concludes that ML algorithms provide improving volatility forecasts in the stock markets of Asia and suggest that this may be a fruitful approach for risk management.

Effect of Landlockedness on Receiving Tourism Income in SAARC Countries

This study looks into the economic-driven tourism growth hypothesis in the context of SAARC countries. It also investigates the effect of landlockedness on tourism income receipt. It is based on secondary data gathered from several World Bank Reports and economic surveys of respective countries. It made use of 169 data points from SAARC's eight member countries. The data from an unbalanced panel was used. It makes use of an exploratory and analytical research design. For the impact study of independent variables on dependent variables, descriptive statistics, panel unit root testing, panel quantile regression analysis, quantile process estimates, quantile slope equality test, and symmetric quantile test are used. The GDP has a positive impact on tourism income in SAARC countries. It is found that one percent increase in the median value of GDP, the tourism income is increased by 0.219 percent. The evidence has proved the economic-driven tourism growth hypothesis, particularly regarding SAARC countries. This highlights the need for tailored tourism initiatives aimed specifically at landlocked nations.

Comparison of value-at-risk forecast using regime-dependent models for the S&P 200 Energy Index

This study investigates the regimes developed in the S&P 200 Energy Index using the Markov regime-switching GARCH model with the asymmetry feature. We also undertake to compare the Markov regime-switching GJR-GARCH model with its single regime counterpart for the Value-at-Risk one-step ahead forecast with the Backtest settings. The results indicate two regimes for the S&P 200 Energy Index with different volatility characteristics. The MS-GJR-GARCH model performs better than the GJR-GARCH model in out-of-sample Value-at-Risk analysis as per the dynamic quantile test. The results are significant for the investors forming their trading strategy based on historical data.

Research on the Economic Growth Effect and Heterogeneity of County Digital Financial Inclusion in Guizhou Province—Based on Panel Smooth Transformation Model and Quantile Model

In 2016, China first proposed the concept of "digital inclusive finance", which effectively solved the problem of difficult and expensive loans for small investors, activated economic growth from all sides, and has become the trend of financial industry development. This article is based on data from 72 counties in Guizhou Province from 2014 to 2021, using the PSTR model and quantile model for empirical analysis, exploring the relationship between economic growth and digital inclusive finance in Guizhou Province. The research results show that the development of digital inclusive finance can promote economic growth in Guizhou Province. After crossing a certain threshold value, it will further promote the economy; the breadth and digitization of the second-level indicators of digital inclusive finance have a nonlinear impact on the economy of Guizhou Province. The depth of digital inclusive finance has a linear relationship with the economy of Guizhou Province; The results of the quantile test show that the effect of digital inclusive finance promoting the economy is more significant in underdeveloped areas.

Research on the Impact of Digital Finance on China's Urban-Rural Income Gap

<p>The integration of digital technology and traditional finance has further achieved the goal of low-cost and sustainable financial services and contributed to high-quality economic development. Based on the data from 31 provinces in China from 2011 to 2021, this paper empirically analyzes the impact of digital finance on the urban-rural income gap. The results show that digital finance can significantly narrow the income gap between urban and rural residents. The quantile test shows that the greater the urban-rural income gap, the stronger the role of digital finance in narrowing the urban-rural income gap. The threshold effect test shows that the narrowing effect of digital finance on the urban-rural income gap will first increase and then weaken with the continuous improvement of the development level. Heterogeneity analysis shows that the secondary indicators of digital finance can significantly narrow the urban-rural income gap, and the effect of depth of usage is the most obvious. Moreover, digital finance has a significantly stronger effect on narrowing the urban-rural income gap in the eastern region than in other regions. Therefore, we should vigorously promote the development of digital finance and give full play to its effectiveness in narrowing the urban-rural income gap.</p>

The Asymmetric Effect of the Extreme Changes in the Economic Policy Uncertainty on the Exchange Rates: Evidence from Emerging Seven Countries

This research has focused on examining the connection between uncertainties in economic policies and exchange rates. This research extends the literature to this field by analyzing the impact of small to large negative along with small to large positive variations in the economic policy uncertainty on the currency rates. For this purpose, this research uses the Granger causality in the quantile test and a newly constructed multiple asymmetric threshold nonlinear ARDL (MATNARDL) model. When a nonlinear ARDL model is utilized, our results confirmed the nonlinear impact in three nations only. In contrast, when the MATNARDL technique is utilized, these findings do confirm the nonlinear effect for all nations. Furthermore, when the Granger causality in the quantile test is applied, the impact differs over various quantiles. In general, the enhanced framework encourages us to analyze better how EPU affects the exchange rate in the emerging seven (E7) nations. The findings of our research may be useful for state banks to design policies to make interventions in the foreign currency market.

Exchange rate and energy demand in G7 countries: Fresh insights from Quantile ARDL model

The empirical literature examines the effect of exchange rate on energy demand. However, the existing literature fails to investigate the effect during different states of energy demand, that is, when energy demand is relatively high and when it is quite low. We extend the prior literature by examining the effect of exchange rates on various states of energy demand in G7 countries. We use the Quantile ARDL (QARDL) model and compare its results with standard ARDL and nonlinear ARDL models. In addition, we use the Granger causality in Quantile (GCQ) test for robustness purposes. The standard ARDL and nonlinear ARDL estimates show that cointegration exists in the context of France only. In contrast, QARDL estimates support cointegration in all sample countries. Moreover, the QARDL estimates indicate that the short-run and long-run effect varies across various quantiles of the energy demand, suggesting different policy implications during different states of the energy demand. Finally, GCQ estimates suggest that the exchange rate causes energy demand across various quantiles of the exchange rate and energy demand. In contrast, energy demand does not cause exchange rate at most quantiles. These findings indicate that devising policies without considering the different states of energy demand may lead to unfavourable consequences.

Research on extreme risk measurement in the international carbon emission futures market, based on a two-component Beta-Skew-t-EGARCH-POT model

ABSTRACT The European Union Allowance (EUA)-driven carbon emissions trading market is selected as a research object. First, the one-component and two-component Beta-Skew-t-EGARCH models are used to depict the characteristics of the return series, considering return series features such as volatility clustering and asymmetry. Moreover, the extreme VaR risk value is directly estimated. Then, the POT method of extreme value theory is applied to describe the extreme tail characteristics of the return series, and the one-component and two-component Beta-Skew-t-EGARCH-POT models constructed, to estimate the extreme VaR risk value, once again. Finally, the performance of each model in extreme VaR risk measurement is tested using six indicators that include the relative error rate, independence test, and dynamic quantile test. The empirical results show that the two-component Beta-Skew-t-EGARCH-POT model performs better in extreme risk measurement, inferring that this model is better suited to describing risk in the carbon market.

Persistence of shocks on sectoral non-methane volatile organic compound from 1820 to 2019: Insights from a fourier quantile unit root test

Despite being directly related to anthropogenic consumption and production, researchers have paid less attention to understanding the dynamics of non-methane volatile organic compounds. The primary objective of this research is to investigate the persistence of potential shocks to non-methane volatile organic compounds in 20 developed from 1820 to 2019 performing traditional unit root approaches and a newly developed Fourier quantile unit root test. Great portion of the empirical results obtained by traditional unit root tests reveal that the sectoral non-methane volatile organic compounds follow a non-stationary process, while the Fourier quantile unit root test indicate quite different results. The Fourier quantile test shows that non-methane volatile organic compounds are stationary in the United Kingdom, Ireland, Germany, France and Austria. In the other 15 countries, government interventions to reduce non-methane volatile organic compounds can have lasting effects and success. The inferences and policy outcomes of the empirical results are discussed in the main body of the paper.

Economic Policy Uncertainty and Industrial Linkage in Japan: A Granger Causality in Quantile Test

ABSTRACT This article examines the relationship between economic policy uncertainty and industrial linkage in Japan. Using a VAR-based connectedness approach to measure the monthly industrial linkage across 15 groups of Japanese industries, we examine the Granger causality in quantile between the industrial linkage and Japan’s monthly economic policy uncertainty (EPU) and its four components including fiscal policy uncertainty, monetary policy uncertainty, trade policy uncertainty, and exchange rate uncertainty during the period from January 1987 to May 2021. We find that changes in economic policy uncertainty and all four components Granger cause changes in industrial linkage, and this result is robust and consistent across nearly all quantiles. We do not find evidence of the Granger causality running from industrial linkage to economic policy uncertainty. However, considering all quantiles, changes in industrial linkage Granger cause the change in each of the four policy uncertainty.

On the interdependence between biofuel, fossil fuel and agricultural food prices: Evidence from quantile tests

This study investigates the long- and short-run relationships between fossil fuel, biofuel and agricultural food commodity prices by applying the cointegration and causality analysis. This study employs a quantile approach to consider the non-linearity and asymmetry in the relationship of data. To reduce a possible noise contained in the data, this study uses weekly average data of biofuel (ethanol), fossil fuel (West Texas Intermediate [WTI] oil) and agricultural food commodity (corn) futures prices from April 18, 2005 to October 30, 2020. The main findings are summarised as follows. First, we discover no evidence of cointegration between the quantiles of WTI oil, ethanol and corn prices when all quantiles are considered, although the results of the linear cointegration test are inconclusive. Second, results of the Granger non-causality test in quantiles reveal a significant short-run bidirectional causality between the returns of WTI oil, ethanol and corn prices, for all or most quantiles of the distribution. This implies asymmetric and nonlinear causal linkage between these variables. Moreover, the results of our analysis have several policy implications, including energy price stability, decrease in energy dependence on fossil fuels, promotion of agricultural industry, environmental sustainability, energy conversion and reduction of greenhouse gas emissions.

Bitcoin, uncertainty and internet searches

PurposeThis paper aims to examine the predictive power of the volume of Economic Uncertainty Related Queries and the Macroeconomic Uncertainty Index on the Bitcoin returns.Design/methodology/approachData consists of 118 monthly observations from September 2010 to June 2020. Due to the departure of series from Gaussian distribution and the existence of outliers, the authors use the quantile analysis framework to investigate the persistency of the shocks, the long-run relationships and Granger causality among the variables.FindingsThis research provides several important findings. First, the substantial differences between conventional and quantile test results stress the importance of the method selection. Second, throughout the conditional distribution of the series, stochastic properties of the variables, long-run and the causal relationships between the variables might be significantly different. Third, rich information provided by the quantile framework might help the investors design better investment strategies.Originality/valueThis study differs from the previous research in terms of variable selection and econometric methodology. Therefore, it presents a more comprehensive framework that suggests implications for empirical researchers and Bitcoin investors.

Hubungan Kausalitas antara Sentimen Investor dan Pasar Keuangan Indonesia

This study aims to see the causal relationship that occurs between investor sentiment-based google search and the Indonesian stock-bond market in 2020. The test used in this study is a combined test between the quantile test to see the effect of investor sentiment on optimistic (pessimistic) conditions and the Granger causality test to detect the causal relationship that occurs between variables. The results of the study found that there was a one-way relationship between investor sentiment and the Indonesian stock market where investor sentiment affects the stock market. Interestingly, in the bond market, causal relationship between variables can’t be found. This study also found that the causal relationship between investor sentiment variables and financial markets only occurs when the optimistic and pessimistic conditions of investors aren't in extreme conditions.

Exchange rate response to economic policy uncertainty: evidence beyond asymmetry

Recent studies have examined the relationship between economic policy uncertainty and exchange rate. We contribute to this literature by considering the effect of minor positive and major positive changes as well as minor negative and major negative changes in the economic policy uncertainties on the exchange rates. In this regard, we use a recently developed multiple asymmetric threshold nonlinear ARDL model along with Granger causality in quantile test. Our estimates support the asymmetric effect in three countries only when an asymmetric ARDL model is used. However, these estimates support asymmetric effects for all the sample countries when the multiple asymmetric threshold nonlinear ARDL model is used. Moreover, the effect varies across various quantiles when Granger causality in quantile test is used. Overall, the extended model helps us to examine more minutely the impact of EPU and GEPU on the exchange rate in G7 countries. The results of this study can be useful for the central banks to devise appropriate policies to intervene in the foreign exchange market.