Ordinary Least Squares Research Articles

Allometric equations for estimating above and belowground biomass of Colophospermum mopane in Mozambique

Seasonally dry tropical woodlands are vital for climate change mitigation, yet their full potential in carbon storage remains poorly understood. This is largely due to the lack of species-specific allometric models tailored to these ecosystems. To address this knowledge gap, this study aimed to develop species-specific biomass allometric equations (BAEs) for accurately estimating both above- and below-ground biomass of Colophospermum mopane (J.Kirk ex Benth.) J.Kirk ex J. Léonard, and to assess the feasibility of incorporating total height, estimated using height-diameter (H-D) equations, to improve the accuracy of biomass estimation in Mozambique. We applied a destructive method and felled 120 C. mopane trees in Mabalane and Tambara Districts. We measured breast height diameter (D), total height (H) and biomass of each component (roots, stem, branches and leaves). We fitted three BAE models using Ordinary Least Squares (OLS) regression and fifteen H-D models using nonlinear regression. A validation procedure checked the applicability of all models. We conducted a forest inventory with 78 temporary clusters, each consisting of four 100 m x 20 m plots, to estimate the average AGB and BGB of C. mopane using the best-fitting BAE and H-D model. We also compared the best BAE of C. mopane with existing locally developed species-specific BAEs. The study found that the model including the interaction of D2 and H, performed better than the model with separate D and H. However, models with D and H performed similarly to models with D alone. The Power model with two parameters and the HossfeldIV model with three parameters exhibited the best performance among the H-D models. Integrating the H from the H-D model into the BAE for AGB estimation can improve the efficiency and reliability of biomass estimation from forest inventory data. This research is timely as there is an urgent need to improve the accuracy of carbon counting to support climate change goals and sustainable management of Mopane woodland given their spatial extent in southern Africa.

Exploring the impact of urban spatial morphology on land surface temperature: A case study in Linyi City, China.

The increasing population density and impervious surface area have exacerbated the urban heat island effect, posing significant challenges to urban environments and sustainable development. Urban spatial morphology is crucial in mitigating the urban heat island effect. This study investigated the impact of urban spatial morphology on land surface temperature (LST) at the township scale. We proposed a six-dimensional factor system to describe urban spatial morphology, comprising Atmospheric Quality, Remote Sensing Indicators, Terrain, Land Use/Land Cover, Building Scale, and Socioeconomic Factors. Spatial autocorrelation and spatial regression methods were used to analyze the impact. To this end, the township-scale data of Linyi City from 2013 to 2022 were collected. The results showed that LST are significantly influenced by urban spatial morphology, with the strongest correlations found in the factors of land use types, landscape metrics, and remote sensing indices. The global Moran's I value of LST exceeds 0.7, indicating a strong positive spatial correlation. The High-High LISA values are distributed in the central and western areas, and the Low-Low LISA values are found in the northern regions and some scattered counties. The Geographically Weighted Regression (GWR) model outperforms the Spatial Error Model (SEM) and Ordinary Least Squares (OLS) model, making it more suitable for exploring these relationships. The findings aim to provide valuable references for town planning, resource allocation, and sustainable development.

Enhancing individuals’ engagement in marine recreational sport activities: from an institutional perspective

IntroductionEncouraging consumer participation in marine recreational sport activities is recognized as a key strategy for boosting both local and regional economies. However, compared to other traditional outdoor activities, participation rates in marine recreation remain relatively low. Two major barriers to participation are consumers' concerns about whether marine recreational sport activities are interesting and suitable for themselves, which can be summarized into product quality uncertainty and product fit uncertainty.MethodsTo address this issue, this paper, grounded in institutional theory, investigates how different institutional environments influence consumers' product certainty and their behavioral engagement in marine recreational sport activities—an area previously underexplored in the literature.Results and discussionsBy collecting 292 survey responses and utilizing ordinary least squares (OLS) regression analysis, we found that both product quality certainty and product fit certainty have a significant positive effect on consumers' behavioral engagement. Additionally, both the regulatory-normative and cognitive institutional environments were shown to significantly enhance consumers' product quality and fit certainty. Moreover, age was found to moderate these effects, with a positive influence on the relationship between the regulatory-normative environment and product certainty, while only affecting the relationship between the cognitive institutional environment and product fit certainty.

Spatial Economic Correlations via Geographically Weighted Neural Network Regression with A New Dataset

The GDP and unemployment rates of two geographic units are influenced by their population density and economic characteristics, as well as their distance and spatial relationship. This work aim to use Geographically Weighted Regression (GWR), a classic and widely used method for modeling spatial heterogeneity, to analyze the correlation of these multiple factors. However, GWR does not precisely express its weighting kernel, making it insufficient to estimate complex geographic processes. Therefore, the work employed the Geographically Weighted Neural Network Regression (GNNWR) model, which combines Ordinary Least Squares (OLS) and neural networks, to estimate spatial heterogeneity based on GWR. This work collected various indicators, such as population density and GDP of first-level administrative units of the top 20 countries by GDP at the end of 2022, along with the Euclidean distance and geographic topology between these units. Using GNNWR, the work analyzed the correlation of their GDP growth. The results show that GNNWR outperforms OLS and GWR in fitting accuracy and provides more accurate predictions of the economic correlation between two geographic units.

Enhancing innovation through ESG practices: the superior impact on family businesses

PurposeThis work contributes to the debate on the link between environmental, social and governance (ESG) criteria and firm innovation, incorporating ownership structure as a moderating variable.Design/methodology/approachThis research uses ordinary least squares (OLS) regression to analyse the impact of ESG criteria on innovation, considering firm ownership as a catalyst that strengthens the effect of environmental and social practices on innovative performance.FindingsFamily-owned firms, with their unique characteristics like long-term orientation and commitment to family values, strengthen the relationship between environmental and social practices and innovation performance. This suggests that such firms are better positioned to leverage their corporate social responsibility (CSR) commitments and activities.Practical implicationsThe findings offer valuable insights for decision-making in organizations, particularly family firms focused on innovation and sustainability. The research shows that investing in sustainability practices not only ensures ESG compliance but also significantly fosters innovation.Originality/valueThis study contributes to the debate regarding the relationship between ESG criteria and firm innovative performance. It highlights how the implementation of ESG practices influences innovation, and particularly how firm ownership further enhances the relationship between environmental and social practices and firm innovative performance.

Do Uncertainties in US Affect Bitcoin Returns? Evidence from Time Series Analysis

Abstract The study attempts to add to the existing literature on the relationship between uncertainties and Bitcoin by determining the direction of the relationship between Economic Policy Uncertainty (EPU), Geopolitical Risk (GPR), Political Risk (PR) and Bitcoin returns. This is to ascertain if Bitcoin hedges and is a safe haven asset against uncertainties. We employed the use of Ordinary Least Square (OLS), Autoregressive Distributive Lag (ARDL) and Quantile Regression (QR) to achieve the research objective. Having discovered the existence of structural breaks after conducting the Zivot-Andrews unit root for structural breaks, the analysis was divided into full sample period, first sub-period and the second sub-period. Findings show that EPU, GPR and PR hedge and play the role of safe haven against uncertainties in the United States (US). We found that EPU exerts positive influence against Bitcoin returns while GPR and PR negatively influence Bitcoin returns. The result further shows that Bitcoin returns hedges against EPU in the lower and middle quantiles while Bitcoin returns hedges against PR only in the lower quantile. The study therefore concludes that uncertainty and risk in the US influence bitcoin returns. It supports the hedging ability and safe haven properties of bitcoin, emphasising that bitcoin returns react more to EPU US than GPR US and PR US, therefore recommending investment experts and financial analysts focus more on EPU US than GPR US and PR US.

Real-world trends and future projections of the prevalence of cirrhosis and hepatic encephalopathy among commercially and Medicare-insured adults in the United States.

Describing cirrhosis and hepatic encephalopathy (HE) burden over time can inform clinical management and resource allocation. Using health care claims data, this observational study examined recent trends in the prevalence of cirrhosis and HE and associated health care resource utilization among commercially and Medicare-insured adults in the United States (US). Data from the MarketScan Commercial Claims and Encounters Database and 100% Medicare Research Identifiable Files were analyzed (2007-2020). Annual prevalence of cirrhosis, HE, overt HE (OHE) hospitalizations, and rifaximin ± lactulose use, and costs per hospitalization per year were calculated. Average year-over-year (YOY) changes in prevalence of cirrhosis and HE were estimated. Trends were extrapolated to 2030 using ordinary least-squares regression. From 2007 to 2020, the prevalence of cirrhosis increased by an average of 4.6% YOY in the Commercial population and 8.1% in the Medicare population; the prevalence of HE increased by 4.3% and 2.5%, respectively. Rates of OHE hospitalizations decreased from 27.5% to 5.5% (Commercial) and from 26.2% to 9.5% (Medicare), and rates of liver transplantation increased. Average payer costs (Commercial) and provider charges (Medicare) per OHE hospitalization increased (from $40,881 to $77,699 and from $45,913 to $74,894, respectively). Use of rifaximin ± lactulose showed an increasing trend during the observation period whereas lactulose use declined steadily. The health care burden of cirrhosis and HE in the US is increasing. Trends are projected to continue unless action is taken, such as improving medication access and developing policies addressing the contributing factors.

Credit Risk Influence on Insurance Performance During Credit Restructuring Policy

This study analyzes the relationship between banking credit risk and general insurance performance during the banking credit restructuring policy period in Indonesia from March 2020 to March 2024. Credit, Nonperforming loans (NPL), and credit interest rates variables are used as proxies for banking risk. General insurance performance is proxied by credit premium, credit claim, and profit before tax. Through multiple regression analysis using Ordinary Least Squares (OLS), this study shows that there is a significant effect of banking risk on general insurance performance. The relationship between banking and insurance can be a complementary or substitution relationship, depending on how important risk transfer and capital allocation. The result provides useful insights to achieve co-evolution of banking and insurance in maintaining financial system stability. Keywords: banking credit risk; credit restructuring policy; general insurance performance

DNA methylation clocks struggle to distinguish inflammaging from healthy aging, but feature rectification improves coherence and enhances detection of inflammaging.

Biological age estimation from DNA methylation and determination of relevant biomarkers is an active research problem which has predominantly been tackled with black-box penalized regression. Machine learning is used to select a small subset of features from hundreds of thousands of CpG probes and to increase generalizability typically lacking with ordinary least-squares regression. Here, we show that such feature selection lacks biological interpretability and relevance in the clocks of the first and next generations and clarify the logic by which these clocks systematically exclude biomarkers of aging and age-related disease. Moreover, in contrast to the assumption that regularized linear regression is needed to prevent overfitting, we demonstrate that hypothesis-driven selection of biologically relevant features in conjunction with ordinary least squares regression yields accurate, well-calibrated, generalizable clocks with high interpretability. We further demonstrate that the interplay of inflammaging-related shifts of predictor values and their corresponding weights, which we term feature shifts, contributes to the lack of resolution between health and inflammaging in conventional linear models. Lastly, we introduce a method of feature rectification, which aligns these shifts to improve the distinction of age predictions for healthy people vs. patients with various chronic inflammation diseases.

Big 4 auditors, client informational problems, and bank loan contracting: evidence from Saudi Arabia

Purpose This study has three objectives: (i) to examine whether using a Big 4 auditor reduces loan interest rates; (ii) to analyze how loan interest rates differ between smaller firms, which face more acute asymmetric information problems, and larger firms; and (iii) to investigate whether the negative relationship between Big 4 auditors and loan interest rates is a function of client size. Design/methodology/approach The sample comprises all publicly traded nonfinancial companies listed on the Saudi Stock Exchange from 2007 to 2020. Pooled ordinary least squares (OLS) regression tests the hypothesized relationship between the dependent and independent variables. Findings The study offers three notable findings. First, borrowers audited by Big 4 auditors receive significantly lower interest rates than those audited by non-Big 4 auditors. Second, banks offer lower interest rates to larger firms (i.e. firms with fewer informational problems) than to smaller ones. Third, no conclusive evidence exists that the beneficial effects of Big 4 auditors (in terms of reduced interest rates) differ significantly between larger and smaller firms. This finding is attributable to the idea that Big 4 auditors do not report more favorably for larger clients or more conservatively for smaller clients. The results remain robust, even after addressing the endogeneity arising from auditor self-selection bias, which is validated by the results of two econometric tests: Heckman’s two-stage procedure and propensity score matching. Originality/value To the best of the author’s knowledge, this study is the first to examine the relationship between auditor size and bank loan contracting in Saudi Arabia.

Regional Comparative Analysis of Family Catastrophic Health Expenditure in Pakistan

The amount of money Pakistani families spend on medical care is examined in this paper making use of PSLM data for 2018–19. It looks into the elements and factors that affect how much money families spend on various illnesses. Numerous factors, such as the type of disease, the number of people living in different provinces, the location (rural or urban) and age of the family heads affect the cost of a family's catastrophic expenditure. According to the estimation results, it can be concluded that in light of all factors have a positive influence on policy recommendations for health expenditure. Furthermore, any finding could have a broad impact on health expenditure of Pakistan. Each of these elements has a distinct impact on how the government determines what amount of funding to allocate to the health sector. The regression was conducted using regression analysis and the ordinary least squares (OLS) method. This method and technique are used in specific situations when the dependent variable in a model is quantitative. Estimates and results will be used to develop the policy and find solutions for every issue that can be attributed to the variables and household health spending.

India-APEC trade relations: prospects for cooperation in the Asia Pacific region

India has expressed interest in joining the Asia Pacific Economic Cooperation (APEC) forum since 1991. Over the past two decades, India’s trade relations with the APEC region have increased significantly. The trade relationship between India and APEC is examined using a gravity model of international trade. The gravity equations have been analysed separately for advanced and emerging and low-income developing economies of APEC by utilising both the poisson pseudo maximum likelihood (PPML) and ordinary least squares (OLS) estimators with several panel specifications. The results show that the majority of the underlying variables exhibit statistical significance. The study suggested that there is an increasing importance of the APEC region for India to promote its export-led growth strategy, as it provides enormous potential for its trade expansion. India’s membership in the APEC would not only boost India’s trade competitiveness in the region, but also provide an opportunity to reform its trade regime.

A Comprehensive Approach to CO2 Emissions Analysis in High-Human-Development-Index Countries Using Statistical and Time Series Approaches

Reducing carbon dioxide (CO2) emissions is vital at both global and national levels, given their significant role in exacerbating climate change. CO2 emissions, stemming from a variety of industrial and economic activities, are major contributors to the greenhouse effect and global warming, posing substantial obstacles in addressing climate issues. It is imperative to forecast CO2 emissions trends and classify countries based on their emission patterns to effectively mitigate worldwide carbon emissions. This paper presents an in-depth comparative study on the determinants of CO2 emissions in twenty countries with high Human Development Index (HDI), exploring factors related to economy, environment, energy use, and renewable resources over a span of 25 years. The study unfolds in two distinct phases: initially, statistical techniques such as Ordinary Least Squares (OLS), fixed effects, and random effects models are applied to pinpoint significant determinants of CO2 emissions. Following this, the study leverages supervised and unsupervised time series approaches to further scrutinize and understand the factors influencing CO2 emissions. Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX), a statistical time series forecasting model, is first used to predict emission trends from historical data, offering practical insights for policy formulation. Subsequently, Dynamic Time Warping (DTW), an unsupervised time series clustering approach, is used to group countries by similar emission patterns. The dual-phase approach utilized in this study significantly improves the accuracy of CO2 emissions predictions while also providing a deeper insight into global emission trends. By adopting this thorough analytical framework, nations can develop more focused and effective carbon reduction policies, playing a vital role in the global initiative to combat climate change.

The Relationship Between Education Funding and Student Performance in Unity Schools in Nigeria

Developing countries need to significantly increase education funding in order to meet the Sustainable Development Goal 4 (SDG 4) targets. The question remains as to whether increased funding leads to improved learning outcomes and whether allocated scarce resources are used efficiently to maximize learning outcomes. Using ordinary least squares (OLS) regression and stochastic frontier analysis (SFA), we investigate the relationship between education funding and student performance using a representative sample of secondary schools in Nigeria and analyze school efficiency in utilizing the funding (budget). The OLS analysis robustly indicates that an increase in the released budget—in real terms—is consistently associated with a higher pass rate, while the SFA shows that after controlling for past budgets the average inefficiency is approximately 47–60%. Our correlation findings support the argument for more funding to improve performance. However, the SFA shows that more can still be achieved with current levels of funding if schools become more efficient. We observe differences across school type and school geographical location, concluding that these factors also influence performance and efficiency. Future research should examine the performance and efficiency differences between all-girls schools and mixed schools, and the higher efficiency of schools in low socioeconomic status (SES) and conflict-affected states.

Census Tract Rurality, Predominant Race and Ethnicity, and Distance to Lung Cancer Screening Facilities : An Ecological Study.

The U.S. Preventive Services Task Force recommends annual lung cancer screening (LCS) for adults who meet specific age and smoking history criteria. To evaluate race-, ethnicity-, and rurality-based differences in distance to the nearest LCS facility. Cross-sectional ecological study. U.S. census tracts. 71 691 census tracts. The outcome variable was road network distance in miles between a census tract and the nearest LCS facility. Distance was log-transformed, and geometric means are reported. Census tracts were classified as majority (>50%) American Indian/Alaska Native (AI/AN), Asian, Black, non-Hispanic White (NHW), no single race, or Hispanic. Rurality was defined using the rural-urban commuting area codes. Ordinary least-squares regression examined the associations between distance and census tract race, ethnicity, and rurality. Geometric mean distance to the nearest LCS facility was 6.5 miles. Compared with NHW-majority census tracts, distance to the nearest LCS facility was 5.26 times (426%) longer in AI/AN-majority census tracts and 7% to 39% shorter in Asian-, Black-, and Hispanic-majority census tracts. Adjustment for rurality reduced the mean distance in AI/AN-majority census tracts, but the mean distance was still 3.16 times the distance in NHW-majority census tracts. Adjustment for rurality reduced the observed advantage in Asian- and Black-majority census tracts and changed the direction of associations in Hispanic-majority census tracts. Analyses did not account for travel time or cost. Differences exist in distance to LCS facilities by race and ethnicity that can only be partially explained by rurality. Lung Ambition Alliance and the Center for Lung Research in Honor of Wayne Gittinger.

Do majority shareholder control deviation results in financial constraints?

Purpose: This study aims to analyze how the moral hazard of the majority shareholder results in financial constrainsts for Brazilian companies listed on Brazil, Bolsa and Balcão (B3).Method: we used the Ordinary Least Squares (OLS) to compare the cash flow sensitivity of cash for firms that have high control deviations control, presenting high moral hazard (constraints), with companies that have low control deviations, presenting low moral hazard (no restrictions).Originality/Relevance: The originality of the research resides in the evidence that the deviation of shareholding control can be understood as a source of credit restriction, putting in check a particular and idiosyncratic source in emerging markets such as Brazil.Results: our first result evidenced that, in historical terms, the control deviation declined significantly. On the other hand, the results reveal that the moral hazard of the majority shareholder, represented by the deviation of control, results in financial restrictions of Brazilian companies listed on B3.Theoretical/methodological/practical contributions: the main implication of the research is to reveal idiosyncratic sources of credit in Brazil, since the majority shareholder control deviation (MSCD) reflects the weak legal protection for minority shareholders and creditors (civil law). This research helps capital market investors in countries with weak legal protections to choose companies that are concerned about governance issues, as well as companies to understand that such deviations can be harmful to corporate debt.

Transforming Governance Into Social Value: The Critical Role of Board Culture Diversity and Anti‐Corruption Policies in Affecting Corporate Social Performance in G20 Countries

ABSTRACTThis paper tends to examine the role of board cultural diversity (BCD) in affecting corporate social performance within G20 countries, centralizing on the interaction of BCD with global initiatives to curb corruption such as OECD convention, Global Compact and Global Reporting Initiative (GRI) standards. Using data extracted from Eikon for the period 2005–2022, this study focuses on different governance systems in both developed and non‐developed G20 countries. Employing ordinary least squares (OLS), fixed‐effects, and random‐effects models, along with bootstrap standard errors and generalized method of moments, we analyze a comprehensive dataset to assess the impact of governance factors on social performance. The results reveal that BCD, OECD, the presence of anti‐bribery and corruption policies, and United Nations Global Compact (UNGC) are significantly positively related to corporate social performance in OLS 1 and OLS2 models, with significantly different fixed‐effects specifications. The outcomes assert that where BCD is related to corporate social performance, it is significantly context‐dependent and influenced by the presence of effective anti‐corruption strategies and commitment to international initiatives. The study highlights the complexity of governance influences on corporate social responsibility, emphasizing that diverse boards are most effective when embedded within effective governance framework that includes anti‐corruption and sustainability commitments.

Multiple Environmental Variables as Covariates to Improve the Accuracy of Spatial Prediction Models for SOM on Karst Aera

ABSTRACTAims accurately predicting the spatial distribution of soil organic matter (SOM) is essential for environmental management and carbon storage estimation. However, the diversity of sources of variables poses a challenge in studying the spatial distribution of SOM. Methods in order to address this issue, we propose leveraging multiple environmental variables and employing machine learning models, specifically Lightweight gradient boosting machine learning (LightGBM) and random forest (RF), for predicting SOM spatial distribution. 128 soil samples were collected from the Caohai National Nature Reserve, and their SOM content was measured. Results the study found that the average SOM content was 36.75 g/kg. Compared to traditional linear regression models such as ordinary kriging (OK), ordinary least squares (OLS), and geographically weighted regression (GWR), the machine learning models based on nonlinear regression, LightGBM and RF, demonstrated higher cross‐validated coefficients of determination (R2) of 0.62 and 0.60, respectively, outperforming the other models. Additionally, RF exhibited lower mean absolute error (MAE) and root mean square error (RMSE), indicating higher stability and generalization capability. The spatial distribution of SOM among the models showed consistency, with higher SOM content observed in southern and near‐Caohai Lake regions and lower SOM content in northern and farther regions from Caohai Lake. Results from the Shapley additive explanations (SHAP) model highlighted agricultural land (AL), pH, and Elevation (ELV) as primary covariates influencing SOM spatial distribution. Conclusions this study provides valuable insights and support for environmental management and carbon storage estimation in the karst plateau region.

The effects of technology investment on financial stability: Evidence from commercial banks in Vietnam

This study examines the effects of technology investments on financial stability at commercial banks in Vietnam. Financial services provided by banks are vital to the growth and development of the Vietnamese economy. Due to competitive constraints and the need to keep up with fast-moving FinTech startups, Vietnamese banks have made digital transformation a top strategic goal. Therefore, the study aims to investigate the impact of technology investment on the financial stability of commercial banks in Vietnam from 2012 to 2023. The research used financial data from 26 joint-stock commercial banks and panel data analysis with the ordinary least squares (OLS), fixed effect model (FEM), random effects model (REM), and generalized method of moments (GMM) to look into the link between bank stability and technology spending. The findings reveal that while technology investment significantly enhances operational efficiency and market competitiveness, it poses risks, particularly during the initial stages of digital transformation. The results show a significant negative effect of technology investment on financial stability, highlighting the need for strategic planning and robust regulatory frameworks. These insights provide valuable recommendations for bank management and policymakers to balance technological advancements with financial stability, especially in economic disruptions like the COVID-19 pandemic. Finally, the practical implications help commercial banks strive to increase asset size and expand operations to strengthen financial capacity, increase brand recognition, create solid customer trust, improve competitiveness, and bring high profits.

Income of workers in industrial parks post-COVID-19 pandemic: The raised issues in Vietnam

This study aimed to analyze the adaptation of workers in industrial parks in Vietnam post-COVID-19 through fluctuations in their income. Data were collected from a survey of 438 workers working in industrial parks and in-depth interviews with five workers in different positions in industrial parks. The study utilized the ordinary least squares (OLS) method to quantify the factors influencing workers’ income. Additionally, the difference test method was applied to assess the income variations among workers based on their professional qualifications and occupational skills. The most significant factor identified is the experience of workers (unstandardized coefficient = 0.271), followed by the education level of workers (unstandardized coefficient = 0.128). Additionally, the study reveals that differences in professional qualifications lead to an income disparity of 1.898 million VND per month, while the variations in complementary skills contribute to an income difference of 0.592 million VND per month. Furthermore, the adaptation of workers in Vietnam’s industrial parks post-COVID-19 is at a relatively good level. From there, the study suggests several solutions to enhance workers’ income to adapt to new post-COVID-19 conditions.