Quantile Regression Estimation Research Articles

How do technology convergence and expansibility affect information technology diffusion? Evidence from the internet of things technology in China

Information technology diffusion (ITD) is essential for promoting the sustainable development of technologies and helping technology owners gain a competitive advantage. The web-based development of technology and the digital transformation needs of multidisciplinary markets simultaneously drive the increasing convergence and expansibility of information technology (IT). However, whether these two technological characteristics can contribute to the diffusion of early-stage IT and how they influence the further diffusion of IT that has already diffused on a large scale are yet to be thoroughly investigated. We argue that the impact of technology convergence on ITD is heterogeneous when distinguishing between low- and high-ITD scenarios, as is technology expansibility. Our quantile regression estimates use a dataset about Internet of Things (IoT) patents authorized by the Chinese Patent Office from 2009 to 2019. The results show that increased technology convergence benefits ITD in high-ITD scenarios but does not affect ITD in low-ITD scenarios. Technology expansibility negatively impacts ITD in high-ITD scenarios and positively impacts ITD in low-ITD scenarios. This study broadens the theoretical paradigm of “technological characteristics and ITD” from the domain perspective. It inspires information technology owners to formulate sustainable strategies related to ITD according to technology convergence and expansibility.

Benchmarking asset pricing models in emerging markets: evidence from Borsa Istanbul

PurposeInvestors who can transfer their savings to investments in a well-regulated market benefit not only themselves but also economic development. Hence, it is crucial for fund owners to evaluate their stock market investment decisions. The goal of the study is to understand which model determines the asset returns most efficiently. In this regard, the validity of single and multi-index asset pricing models (capital asset pricing model-CAPM and Fama–French models) has been examined in the Turkish Stock Exchange for 2009–2020, with the quantile regression (QR) approach.Design/methodology/approachOn 18 portfolios comprised of quoted stocks in the Istanbul Stock Exchange 100 (ISE-100/BIST-100), we test the CAPM, the Fama and French three factor model (FF3) and the Fama and French five factor model (FF5). Empirical analyses have been carried out via QR approach regressing the portfolios' average weekly excess returns on risk premium/market factor (Rm-Rf), firm size, book value/market value (B/M), profitability and investments factors. QR estimation has been employed since QR is more effective and provides a better definition of the distribution’s tails.FindingsOur empirical findings have revealed that the average excess weekly returns can be explained more strongly via CAPM. Moreover, Fama and French models are expected to give more reliable result with more data, whereas the market premium would give robust results for the Turkish Capital Market.Practical implicationsIndividuals investing in financial assets must find the price model that best fits the market. The return can be approximated in the most appropriate manner using the right variables.Originality/valueThe study differs from other research by comparing the asset pricing models via examining the assets' weekly returns with QR in the Istanbul Stock Exchange 100 (ISE-100).

Exploring the determinants of methane emissions from a worldwide perspective using panel data and machine learning analyses

This article contributes to the scant literature exploring the determinants of methane emissions. A lot is explored considering CO2 emissions, but fewer studies concentrate on the other most long-lived greenhouse gas (GHG), methane which contributes largely to climate change. For the empirical analysis, a large dataset is used considering 192 countries with data ranging from 1960 up to 2022 and considering a wide set of determinants (total central government debt, domestic credit to the private sector, exports of goods and services, GDP per capita, total unemployment, renewable energy consumption, urban population, Gini Index, and Voice and Accountability). Panel Quantile Regression (PQR) estimates show a non-negligible statistical effect of all the selected variables (except for the Gini Index) over the distribution's quantiles. Moreover, the Simple Regression Tree (SRT) model allows us to observe that the losing countries, located in the poorest world regions, abundant in natural resources, are those expected to curb methane emissions. For that, public interventions like digitalization, green education, green financing, ensuring the increase in Voice and Accountability, and green jobs, would lead losers to be positioned in the winner's rankings and would ensure an effective fight against climate change.

Do natural resource rents aid renewable energy transition in resource‐rich African countries? The roles of institutional quality and its threshold

AbstractTransitioning to a carbon‐neutral renewable energy (REN) option to decarbonize ecosystems and mitigate carbon dioxide (CO2) emissions and the negative impacts of climate change is consistent with United Nations Sustainable Development Goals 7 and 13. Scholars have identified natural resource wealth and institutions as critical factors in the REN transition in resource‐rich countries. Financial barriers are arguably the most significant impediments to transitioning to REN, as it is more capital‐intensive and costly to produce, invest in, and use than traditional fossil fuel‐based energy. Meanwhile, weak institutions and corruption in most resource‐rich countries culminate in the resource curse phenomenon and the mismanagement of natural resource wealth. It implies that institutions (weak or strong) modify the natural resource rent contribution to the REN transition. Previous research has paid little attention to the impact of the interplay between natural resources and institutional quality on the REN transition in resource‐rich African countries. This study examines how institutions moderate the contribution of natural resource wealth to accelerating or inhibiting the REN switch in resource‐rich African countries for the period 2000–2021, using fully modified ordinary least squares, a Driscoll–Kraay nonparametric covariance matrix, and moments‐based quantile regression estimators. This study departs from earlier studies by determining the institutional quality threshold above which institutions significantly stimulate natural resource rents to accelerate Africa's REN transition. The findings indicate that institutions in resource‐rich African countries breed inefficient bureaucracies and corruption in natural resource rent administration. These undermine the ability of natural resource incomes to facilitate a shift to renewable energy sources. The threshold analyses indicate that most resource‐rich African countries operate below the institutional quality threshold. This finding corroborates that inefficient institutions abet natural resource rent mismanagement and hinder the channeling of resource income toward the REN transition. The findings' policy implications are robustly articulated and outlined.

Self-weighted quantile regression estimation for diffusion parameter in jump-diffusion models

The self-weighted quantile regression estimator for the diffusion parameter in diffusion models with jumps is proposed. The consistency of the underlying estimator is obtained. Moreover, the better finite-sample properties are verified through the Monte-Carlo simulation study and empirical analysis.

Photovoltaic Power Prediction Based on Hybrid Deep Learning Networks and Meteorological Data.

Conventional point prediction methods encounter challenges in accurately capturing the inherent uncertainty associated with photovoltaic power due to its stochastic and volatile nature. To address this challenge, we developed a robust prediction model called QRKDDN (quantile regression and kernel density estimation deep learning network) by leveraging historical meteorological data in conjunction with photovoltaic power data. Our aim is to enhance the accuracy of deterministic predictions, interval predictions, and probabilistic predictions by incorporating quantile regression (QR) and kernel density estimation (KDE) techniques. The proposed method utilizes the Pearson correlation coefficient for selecting relevant meteorological factors, employs a Gaussian Mixture Model (GMM) for clustering similar days, and constructs a deep learning prediction model based on a convolutional neural network (CNN) combined with a bidirectional gated recurrent unit (BiGRU) and attention mechanism. The experimental results obtained using the dataset from the Australian DKASC Research Centre unequivocally demonstrate the exceptional performance of QRKDDN in deterministic, interval, and probabilistic predictions for photovoltaic (PV) power generation. The effectiveness of QRKDDN was further validated through ablation experiments and comparisons with classical machine learning models.

Truncated composite quantile regression with covariates measurement errors

Truncated data and measurement error data are often encountered in practice. In this paper, we study two classes of truncated composite quantile regression with covariates measured with errors. We propose weighted composite quantile regression estimators of the slope parameters based on weights which are random quantities and determined by the product-limit estimates of the distribution function of truncated variable. However, the estimators are often biased when one treats mismeasured covariates as error-free. To eliminate the bias and obtain consistent estimators, a debiasing technique is proposed. The resulting estimates are proved to be asymptotically normal and root n consistent under some mild conditions. Simulation studies and a real data example show that the proposed methods work promisingly.

Does innovation facilitate meeting the CO2 emission reduction targets of China: A non-linear approach

China has been implementing energy efficiency and CO2 emission reduction schemes at the provincial level that have been embedded in the National Five Year Plans of the country. We set out to investigate the relationship between R&D expenditures and CO2 emissions in China at the province level in the context of the planned emissions reduction targets. We explore the possibility of the existence of a non-linear relationship between R&D expenditures and CO2 emissions with a non-parametric methodology, a fixed effect panel data quantile (FEQR) regression estimator applied to a panel of 30 provinces. We stratify the sample according to the five emissions reduction target tiers of the 12th Five-Year National Plan of China and we investigate the role of R&D expenditures in emissions reduction within each of the tiers. We find an inverse U relationship with different turning points for the three middle tiers and a U-shaped relationship for the tier under the most stringent environmental regulation. We find no effect in the tier with the least stringent emissions reduction targets. A further investigation shows that the above results are attributed to sectors with relatively low energy intensity and not to the sectors of heavy industry. The results allow us to draw broad conclusions about the effectiveness of investment in new technologies as a means of meeting the CO2 targets in China.

Quasi-maximum Likelihood Inference for Linear Double Autoregressive Models

This paper investigates the quasi-maximum likelihood inference including estimation, model selection and diagnostic checking for linear double autoregressive (DAR) models, where all asymptotic properties are established under only fractional moment of the observed process. We propose a Gaussian quasi-maximum likelihood estimator (G-QMLE) and an exponential quasi-maximum likelihood estimator (E-QMLE) for the linear DAR model, and establish the consistency and asymptotic normality for both estimators. Based on the G-QMLE and E-QMLE, two Bayesian information criteria are proposed for model selection, and two mixed portmanteau tests are constructed to check the adequacy of fitted models. Moreover, we compare the proposed G-QMLE and E-QMLE with the existing doubly weighted quantile regression estimator in terms of the asymptotic efficiency and numerical performance. Simulation studies illustrate the finite-sample performance of the proposed inference tools, and a real example on the Bitcoin return series shows the usefulness of the proposed inference tools.

Sales performance of direct food marketers: African American‐led operations

AbstractThis paper examines the impact of participation in direct marketing on the entire distribution of farm sales for African American (AA) operations using the unconditional quantile regression (UQR) estimator. Our analysis yields unbiased estimates of the unconditional impact of direct marketing on farm sales and reveals the heterogeneous effects that occur across the distribution of farm sales. The sales gap for AA‐led operations is about 11% across all quantiles when we control for farming and marketing experience along with key features of the farm operation such as crop choice and geographic location. The relative sales gap for AA operations declines across the distribution of farm sales and actually disappears for the largest operations. The network effect that we identify is associated with a sales premium for AA‐led operations relative to other operations engaged in direct marketing. Marketing experts and extension professionals can use this information to guide farmers who are considering initiating or expanding direct marketing activities.

The second-order bias and mean squared error of quantile regression estimators

The second-order bias and mean squared error of quantile regression estimators

Sampling Importance Resampling Algorithm with Nonignorable Missing Response Variable Based on Smoothed Quantile Regression

The presence of nonignorable missing response variables often leads to complex conditional distribution patterns that cannot be effectively captured through mean regression. In contrast, quantile regression offers valuable insights into the conditional distribution. Consequently, this article places emphasis on the quantile regression approach to address nonrandom missing data. Taking inspiration from fractional imputation, this paper proposes a novel smoothed quantile regression estimation equation based on a sampling importance resampling (SIR) algorithm instead of nonparametric kernel regression methods. Additionally, we present an augmented inverse probability weighting (AIPW) smoothed quantile regression estimation equation to reduce the influence of potential misspecification in a working model. The consistency and asymptotic normality of the empirical likelihood estimators corresponding to the above estimating equations are proven under the assumption of a correctly specified parameter working model. Furthermore, we demonstrate that the AIPW estimation equation converges to an IPW estimation equation when a parameter working model is misspecified, thus illustrating the robustness of the AIPW estimation approach. Through numerical simulations, we examine the finite sample properties of the proposed method when the working models are both correctly specified and misspecified. Furthermore, we apply the proposed method to analyze HIV—CD4 data, thereby exploring variations in treatment effects and the influence of other covariates across different quantiles.

Assessment of Minimal Clinically Important Difference in Patient-Reported Myelofibrosis-Associated Symptoms Using an Anchor-Based Analysis Based on MANIFEST Arm 3 Data

Background Myelofibrosis (MF) is a life-threatening hematologic neoplasm that can arise as a primary condition or as a progression from polycythemia vera or essential thrombocythemia. The MF Symptom Assessment Form (MFSAF) v4.0 is a seven-item questionnaire that assesses symptom severity from the patients' (pts) perspective. Each item is rated on a scale from 0 (Absent) to 10 (Worst Imaginable). The MFSAF Total Symptom Score (TSS) ranges from 0 to 70, with higher scores indicating worse symptoms. A ≥50% reduction in TSS (TSS50) is a commonly used binary endpoint in clinical trials. However, the clinical meaningfulness of the dichotomization of response at 50% cutoff across the spectrum of responses remains uncertain. The relevance of considering TSS as a continuous endpoint in MF studies is assessed here to capture the full spectrum of symptom changes, enabling a potentially more accurate assessment of treatment effects. Pelabresib (CPI-0610) is an investigational oral small-molecule BET inhibitor, while the Janus kinase inhibitors (JAKis) ruxolitinib or fedratinib are the current standard of care for intermediate- or high-risk pts with MF.InArm 3 of the Phase 2 MANIFEST trial of JAKi treatment-naïve pts with MF treated with pelabresib and ruxolitinib, 56% achieved TSS50 response at Week (Wk) 24. Aims This anchor-based analysis aims to determine the minimal clinically important difference (MCID) of change in TSS as a continuous endpoint, based on data from JAKi treatment-naïve pts with MF treated with pelabresib and ruxolitinib, to better evaluate the incremental clinical benefit of treatment effects. Methods Data from Arm 3 of the MANIFEST Phase 2 study of treatment-naïve pts with MF treated with pelabresib combined with ruxolitinib were used (July 29, 2022 data cut). Anchor-based methods compare the change in a scale-based outcome measure with that of an established patient-reported outcome (PRO). These methods are commonly used to establish the MCID, defined as the smallest difference in score that pts consider beneficial. In this analysis, the Patient Global Impression of Change (PGIC), a seven-point scale reflecting overall improvement compared with baseline (BL), was used as the anchor PRO. On the PGIC, pts rated their change from ‘very much improved’ to ‘very much worse’ (Table 1). The relationship between TSS changes (percentage and absolute) at Wk 24 and PGIC categories was examined using correlation and graphical analyses. Linear and quantile regressions were applied to assess the impact of a one-point difference in PGIC score on TSS change at Wk 24, adjusting for BL TSS score. Only pts with available TSS and PGIC data at Wk 24 were included, with no imputation for missing values. Results In Arm 3 of the MANIFEST trial, 78 of 84 pts treated with pelabresib and ruxolitinib had complete TSS data and PGIC at Wk 24. At BL, mean TSS was 16.4 (SD=8.4), and median TSS was 15.5 (range 2.0-38.3). A -58.8% and -7.7 median percentage and absolute reduction in TSS at Wk 24 was observed, respectively. For PGIC at Wk 24 (Table 1), only six pts (7.7%) scored in the three worsening PGIC categories. Percentage and absolute changes in TSS, and the percentage TSS50 responders for each PGIC category are shown in Table 1. Linear regression demonstrated that a one-category increase in PGIC (indicating worsening) corresponded to an 11.89% increase (95% CI 3.12-20.65) in TSS (indicating worsening) at Wk 24. The quantile regression estimate for this relationship was 11.36% (3.53-19.19). For absolute change at Wk 24, a one-category increase in PGIC resulted in a 1.67 (range 0.74-2.60) increase in mean TSS, with a 1.87 (range 0.62-3.12) increase in median TSS. Conclusion Assuming a one-category change in the seven-category PGIC represents a clinically meaningful difference, the analyses suggest that the MCID in TSS for JAKi treatment-naïve pts with MF could be approximately 11-12% for percentage change from BL and approximately 1.5-2 points for absolute change from BL. These findings provide valuable guidance for assessing treatment outcomes and evaluating symptom improvements' clinical significance in this patient population. Further exploration of these findings requires larger data sets, which will be addressed in the forthcoming Phase 3 MANIFEST-2 study evaluating pelabresib and ruxolitinib versus placebo and ruxolitinib in JAKi treatment-naïve pts with MF.

Impact of Public Debt on Economic Growth: A Quantile Regression Approach

This study aimed at investigating the nexus between government debt and its determinants in the context of sustainable economic growth for 97 countries over the period from 2004 to 2018 by employing a panel data quantile regression and comparing it across a fixed-effects model and a generalized method of moments (GMM) model. The different touches of debt on economic growth were analysed. The quantile regression estimates revealed that government debt has various impacts on economic growth, relying on the degree of economic performance. Government debt negatively affects economic growth across all the quantiles. More interestingly, the quantile regression estimates indicated that in countries with a very low level of real GDP per capita growth, government debt has a stronger pernicious effect on economic growth compared to upper-middle and high-income countries. Hence, our results provided insightful information for policy makers in designing appropriate fiscal policies particularly for low- and lower- middle-income countries to mitigate the negative effect on economic growth, and it should be maintained at a low and reasonable level to promote sustainable economic growth. JEL Classification: E61, E62, E63, H63, O4, O40

Does financial inclusion spur CO2 emissions? The marginal effects of financial sustainability

PurposeThis study aims to examine the relationship between financial inclusion, CO2 emissions and financial sustainability across 17 African countries.Design/methodology/approachData were sourced from the World Development Indicators for the period 2004-2021. The study performs the principal component analysis, panel fixed effects model and quantile regression estimations to investigate the relationship between financial inclusion, CO2 emissions and financial sustainability.FindingsThe study finds that an increase in automated teller machine (ATM) penetration rate, savings and credits increases CO2 emissions. Findings also reveal that financial sustainability reduces financial inclusion, with significant negative effects on the conditional mean of CO2 emissions and the conditional distribution of CO2 emissions across quantiles.Originality/valueThis study is beneficial for policymakers, particularly in the age of digitalization and drive for low-carbon emissions, to develop green credits for energy players and investors to take up renewable and green energy projects characterized by high levels of carbon storage and carbon capture. Further, the banking sector’s credits and liquid assets should be used to finance alternative banking energy-related equipment and services, such as solar photovoltaic wireless ATMs, and fewer bank branches.

A Novel Daily Runoff Probability Density Prediction Model Based on Simplified Minimal Gated Memory–Non-Crossing Quantile Regression and Kernel Density Estimation

Reliable and accurate daily runoff predictions are critical to water resource management and planning. Probability density predictions of daily runoff can provide decision-makers with comprehensive information by quantifying the uncertainty of forecasting. Models based on quantile regression (QR) have been proven to achieve good probabilistic prediction performance, but the predicted quantiles may crossover with each other, seriously reducing the reliability of the prediction. This paper proposes non-crossing quantile regression (NCQR), which guarantees that the intervals between adjacent quantiles are greater than 0, which avoids the occurrence of quantile crossing. In order to apply NCQR to the prediction of nonlinear runoff series, this paper combines NCQR with recurrent neural network (RNN) models. In order to reduce the model training time and further improve the model accuracy, this paper simplifies the minimal gated memory (MGM) model and proposes a new RNN model, called the simplified minimal gated memory (SMGM) model. Kernel density estimation (KDE) is used to transform the discrete quantiles predicted using SMGM-NCQR into a continuous probability density function (PDF). This paper proposes a novel daily density prediction model that combines SMGM-NCQR and KDE. Three daily runoff datasets in the Yangtze River Basin in China are taken as examples and compared with the advanced models in current research in terms of five aspects: point prediction evaluation, interval prediction evaluation, probability density prediction evaluation, the degree of quantile crossing and training time. The experimental results show that the model can provide high-quality and highly reliable runoff probability density predictions.

The temporal dimensions of policy responses to capital surges

The temporal dimensions of policy responses to capital surges

SUBSAMPLING INFERENCE FOR NONPARAMETRIC EXTREMAL CONDITIONAL QUANTILES

This paper proposes a subsampling inference method for extreme conditional quantiles based on a self-normalized version of a local estimator for conditional quantiles, such as the local linear quantile regression estimator. The proposed method circumvents difficulty of estimating nuisance parameters in the limiting distribution of the local estimator. A simulation study and empirical example illustrate usefulness of our subsampling inference to investigate extremal phenomena.

A hybrid carbon price prediction model based-combinational estimation strategies of quantile regression and long short-term memory

In recent years, global warming mitigation has received increasing attention. Reasonable carbon prices in stable carbon markets can reduce greenhouse gas emissions. Therefore, to accurately predict carbon prices and describe their fluctuations, a hybrid model was developed based on Complete Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), SampEn (SE), Long Short-Term Memory (LSTM), Quantile regression (QR), and Kernel density estimation (KDE). First, CEEMDAN was used to decompose the original carbon price series into several Intrinsic Mode Functions (IMFs), and the SE of each decomposed series was calculated to reconstruct a new series. The actual influencing factors determine the number of new series. The prediction model, named QRLSTM, combines QR and LSTM to achieve point and interval predictions. Finally, KDE was used to obtain a probabilistic prediction of the daily carbon price. Compared with other methods, the experimental results in Hubei, China, showed that the proposed CEEMDAN-SE-QRLSTM model had the best performance. For point prediction, the MSE, MAE, RMSE, MAPE, and R2 were 0.19, 0.33, 0.43, 0.01, and 91.7%, respectively. In interval prediction, the coverage width criterion (CWC) in the 95%, 90%, and 80% confidence intervals was small, with values of 0.37, 0.32, and 0.27, respectively. In probabilistic prediction, the continuous ranked probability score (CRPS) with 95% confidence was small, with a value of 0.25. In addition, the improvement in point prediction and stability of the hybrid model were also proved. The proposed model can provide more accurate results and valuable information for decision-makers.

Does globalization and ecological footprint in OECD lead to national happiness.

This study examines the relationship between globalization, ecological footprint, innovation, and subjective wellbeing in the form of happiness, using a comprehensive assessment of OECD countries from 2008 to 2020. The study employs FGLS, Quantile, and Bootstrap Quantile regression estimation to investigate the quadratic effects of globalization, ecological footprint, and the moderating effect of innovation while controlling for renewable energy and population density. Happiness is a multidisciplinary subject, and this study focuses on the economic dimensions of happiness. The findings reveal a nonlinear relationship between ecological footprint and globalization, with negative effects on subjective wellbeing at high levels of ecological footprint and globalization. However, the moderating effect of innovation mitigates these adverse effects, indicating that innovation can help to offset the detrimental impacts of ecological footprint and globalization on subjective wellbeing. The study's implications are significant for policymakers promoting sustainable economic growth while enhancing subjective wellbeing. The findings highlight the importance of investing in innovation and sustainable development to promote subjective wellbeing in the face of increasing ecological footprint and globalization. Additionally, this research contributes to the multidisciplinary understanding of happiness and provides valuable insights for future research in this area.