Regression Estimates Research Articles

Second Order Biases and Mean Squared Errors of Some Estimators Using Single Auxiliary Variable

The ratio, product, chain ratio, chain product, chain regression and ratio-cum product estimators have been considered by Chand (1975), Kiregyera (1980, 1984), Upadhyaya et. al. (1990, 1992), Srivastava et. al. (1990), Prasad et. al. (1992), Sahoo and Sahoo (1993), Singh (1993). Most of them discussed these estimators along with their first order bias and mean square error. In this paper, we have tried to find out the second order biases and mean square errors of these estimators based on simple random sampling. Finally, we have compared the performance of these estimators with some numerical illustration.

Regression estimation using surrogate responses obtained by presmoothing

Regression estimation using surrogate responses obtained by presmoothing

Exploring the nexus of geopolitical risk, green financing, and natural resource rents: A study of Russia's economic growth

Geopolitical risk encompasses various uncertainties arising from political, social, and economic factors, which can significantly influence a country's economic performance. Therefore in this study we analyzed the impact of geopolitical risk (GPR), green financing, and natural resource rents (NRR) on Russia's economic growth during 2000–2022 is examined in this study. The collected data is analyzed using simple quantile regression, the ADF unit root test, Johansen Co-integration, and other time series methods. A unit root test shows that level (1) data is stable and that variables are co-integrated. Quantile regression research shows that GPR positively impacts economic growth at the median and higher quantiles. In addition, green finance and commerce boost economic growth across all quantiles. The results support the resource curse hypothesis, which claims that NRR negatively affects economic growth. The Granger causality test shows that GDP and its explanatory components are causally related. These findings were compatible with quantile regression estimates after a parametric examination. The policy implications for researchers and politicians concerned with green finance, natural resource sustainability, and geopolitical dangers to economic growth are significant.

Residential exposure to ambient fine particulate matter (PM2.5) and nitrogen dioxide (NO2) and incident breast cancer among young women in Ontario, Canada

BackgroundAir pollution has been classified as a human carcinogen based largely on findings for respiratory cancers. Emerging, but limited, evidence suggests that it increases the risk of breast cancer, particularly among younger women. We characterized associations between residential exposure to ambient fine particulate matter (PM2.5) and nitrogen dioxide (NO2) and breast cancer. Analyses were performed using data collected in the Ontario Environmental Health Study (OEHS). MethodsThe OEHS, a population-based case-control study, identified incident cases of breast cancer in Ontario, Canada among women aged 18–45 between 2013 and 2015. A total of 465 pathologically confirmed primary breast cancer cases were identified from the Ontario Cancer Registry, while 242 population-based controls were recruited using random-digit dialing. Self-reported questionnaires were used to collect risk factor data and residential histories. Land-use regression and remote-sensing estimates of NO2 and PM2.5, respectively, were assigned to the residential addresses at interview, five years earlier, and at menarche. Logistic regression was used to estimate odds ratios (OR) and their 95 % confidence intervals (CI) in relation to an interquartile range (IQR) increase in air pollution, adjusting for possible confounders. ResultsPM2.5 and NO2 were positively correlated with each other (r = 0.57). An IQR increase of PM2.5 (1.9 µg/m3) and NO2 (6.6 ppb) at interview residence were associated with higher odds of breast cancer and the adjusted ORs and 95 % CIs were 1.37 (95 % CI = 0.98–1.91) and 2.33 (95 % CI = 1.53–3.53), respectively. An increased odds of breast cancer was observed with an IQR increase in NO2 at residence five years earlier (OR = 2.16, 95 % CI: 1.41–3.31), while no association was observed with PM2.5 (OR = 0.96, 95 % CI 0.64–1.42). ConclusionsOur findings support the hypothesis that exposure to ambient air pollution, especially those from traffic sources (i.e., NO2), increases the risk of breast cancer in young women.

Survival Analysis Without Sharing of Individual Patient Data by Using a Gaussian Copula.

Cox regression and Kaplan-Meier estimations are often needed in clinical research and this requires access to individual patient data (IPD). However, IPD cannot always be shared because of privacy or proprietary restrictions, which complicates the making of such estimations. We propose a method that generates pseudodata replacing the IPD by only sharing non-disclosive aggregates such as IPD marginal moments and a correlation matrix. Such aggregates are collected by a central computer and input as parameters to a Gaussian copula (GC) that generates the pseudodata. Survival inferences are computed on the pseudodata as if it were the IPD. Using practical examples we demonstrate the utility of the method, via the amount of IPD inferential content recoverable by the GC. We compare GC to a summary-based meta-analysis and an IPD bootstrap distributed across several centers. Other pseudodata approaches are also considered. In the empirical results, GC approximates the utility of the IPD bootstrap although it might yield more conservative inferences and it might have limitations in subgroup analyses. Overall, GC avoids many legal problems related to IPD privacy or property while enabling approximation of common IPD survival analyses otherwise difficult to conduct. Sharing more IPD aggregates than is currently practiced could facilitate "second purpose"-research and relax concerns regarding IPD access.

A Note on Rounding Error in The Variables: Understanding Its Influence on Statistical Estimators

When estimating the variance, higher moments, and regression coefficients using rounded data, bias is commonly introduced into these estimates. Sheppard’s correction can be used to approximately adjust for this bias under certain conditions. This study investegated the conditions that allow for the valid application of Sheppard’s corrections. A significant observation from the research was that the rounding error-often displaying a uniform distribution-was not independent of the original, unrounded variable. The study provided a thorough investigation of instances where variables, distributed uniformly, undergo rounding. This investigation yielded crucial insights into the statistical behavior and potential ramifications of such variables within statistical analyses. An integral part of this study was the computation and discussion of the density function of the rounding error. Deriving this density function facilitated a nuanced analysis of the differences between the moments of rounded data and the original, unrounded data. Sheppard’s regularities, under which Sheppard’s correction is applied, were discussed. The letter also carefully considered the effects of rounding error on regression estimates. In this context, Sheppard’s correction was implemented to the biased regression parameters to evaluate its efficacy in providing more accurate estimations. Further, our research provides new insights into how rounding can affect statistical outcomes, depending on the underlying distribution of the data. We have discovered that the impact is minimal under uniform distribution assumptions but becomes significantly pronounced under non-uniform distributions. This highlights the importance of considering the distributional characteristics of data when applying rounding corrections to ensure the reliability of statistical inferences.

Discovering the determinants of energy intensity of Indian manufacturing firms: a panel data approach

Our study pores on evaluating the impact of firm specific and macro level determinants of energy intensity of Indian firms belonging to manufacturing and power sector. We collect a panel dataset of 3316 firms for 10 years ranging from 2010 to 2020. We employ the advanced biased corrected method of moments estimator and the quantile regression estimator for panel data models for our empirical analysis. We find that poor labor efficiency is largely responsible for increasing energy intensity of the sample firms. Energy intensity can be optimized by investing in better plant and machinery. Moreover, machineries that require frequent repairs and maintenance need to be replaced with latest tools. While larger firms are found to be energy intensive, profitable firms are found to be in a better position to enhance their energy efficiency. Under macroeconomic scenario, GDP growth and trade openness lead to boosting up the energy consumption at the firm level whereas, the global energy prices act as a constraint and necessitate careful use of energy. Based on our findings we provide certain policy recommendations and suggestions in order to limit energy intensity and enhance energy efficiency of the Indian manufacturing firms.

Ethical ideology and fraud rationalization among future accountants in Nigeria

ABSTRACT This study examines the effect of ethical ideology on fraud rationalization among future accountants in Nigeria. Specifically, it investigates whether being a moral idealist or moral relativist influences the ability of future accountants to rationalize fraud. The study collected data from 225 participants with a scenario-based questionnaire, which was analysed using independent sample t-tests and regression estimation techniques. The results reveal a direct correlation between ethical ideology and fraud rationalization, indicating that future accountants who are high in moral relativism and low in moral idealism have higher tendencies to rationalize fraud than those who are high in moral idealism and low in moral relativism. These findings emphasize the importance of ethical ideology as an intrinsic psychological mechanism that can predict fraud rationalization tendencies in individuals. The study highlights the important implications of its findings and provides suggestions for future research.

The economic determinants of world disorder events: An empirical analysis

This paper delves into the economic determinants of World Disorder Events (WDE) using robust empirical methodologies applied to a cross-section of world data over the period 1997-2022. By employing econometric models such as Robust Least Squares (RLS), complemented with Artificial Intelligence methods, such as Ridge Regression (RR) and Artificial Neural Networks (ANN), we uncover the influence of various economic, environmental, and health factors on the frequency and intensity of WDE. RR is used to address multicollinearity among predictors, thereby enhancing the reliability of our regression estimates. The robustness of our findings is further ensured through ANN models, which improve prediction accuracy and model stability. This analysis not only identifies key economic drivers of WDE but also offers policy recommendations to reduce the incidence and impact of these events. By integrating multiple applied techniques, this paper contributes to a more nuanced understanding of the complex interplay between economic conditions and global stability, offering valuable insights for policymakers and economic analysts.

Achieving carbon-neutrality goals in Asian emerging economies: Role of investment in clean energy, eco-regulations, and green finance

Predicting the future of the globe due to severe climate changes caused by the emission of human-induced gases is heated debate of this era. Paris Climate Accord (COP26) is one of the initiatives taken by the nations to achieve carbon neutrality (zero carbon) and prevent the planet from the hazardous effect of carbon emission. This study aims to examine if renewable energy consumption, green finance and eco-regulations help in reducing carbon emission in four emerging Asian economies. Utilizing the panel data from 2010 to 2021, this study applies cross sectional ARDL regression estimation to empirically examine the research issue. The findings indicate that the promotion of clean energy initiatives via renewable energy consumption, implementation of eco-regulations and utilization of green finance substantially reduce carbon emissions while enhancing a nation’s capacity to reach the objective of carbon neutrality. The findings have practical implication for the regulatory bodies to develop eco-regulations and motivate the nation towards using renewable energy in order to combat with carbon emission.

ASSESSMENT OF RURAL HOUSEHOLDS’ PARTICIPATION IN CONSERVATION OF VANISHING RAINFOREST IN DELTA STATE, NIGERIA

The study assessed rural household participation in conservation of vanishing rainforest in Delta State, Nigeria. A sample of 270 households were selected through multistage random sampling techniques. Data was collected with a structured questionnaire and analysed using descriptive statistics and regression analysis. The regression estimates of socio-economic determinants to participation in rainforest conservation showed that the coefficients and t-values (in parenthesis) of age 0.042 (0.707) was positive and significant at 10%. It implied that the youths and elderly can participate in conservation programmes when involved. Educational status 0.075 (2.861), forest association membership 0.057 (1.045), and land ownership 0.244 (2.104) were positive and significant at 0.05 while engagement in forest activities 0.665 (-.319) and forest income 0.735 (-3.198) were negative and significant at 0.05. Exclusion from making forest policies and neglect of indigenous knowledge of rural communities were the major constraints to rural household participation in rainforest conservation. Recommendations include education and enlightenment to change the orientation of rural households toward rainforest conservation; rural households should be involved in every plan to restore the rainforest since they are the major culprits of deforestation activities.

Estimator Comparison for the Prediction of Election Results

Cluster randomized experiments and estimator comparisons are well-documented topics. In this paper, using the datasets of the popular vote in the presidential elections of the United States of America (2012, 2016, 2020), we evaluate the properties (SE, MSE) of three cluster sampling estimators: Ratio estimator, Horvitz–Thompson estimator and the linear regression estimator. While both the Ratio and Horvitz–Thompson estimators are widely used in cluster analysis, we propose a linear regression estimator defined for unequal cluster sizes, which, in many scenarios, performs better than the other two. The main objective of this paper is twofold. Firstly, to indicate which estimator is most suited for predicting the outcome of the popular vote in the United States of America. We do so by applying the single-stage cluster sampling technique to our data. In the first partition, we use the 50 states plus the District of Columbia as primary sampling units, whereas in the second one, we use 3112 counties instead. Secondly, based on the results of the aforementioned procedure, we estimate the number of clusters in a sample for a set standard error while also considering the diminishing returns from increasing the number of clusters in the sample. The linear regression estimator is best in the majority of the examined cases. This type of comparison can also be used for the estimation of any other country’s elections if prior voting results are available.

Medical Data for the Nadaraya-Watson Kernel Method in Nonparametric Regression Models Based on Hyperbolic Secant Function

Nonparametric kernel estimates used in this work aim to compare different treatment options by examining the recorded medical data. The following use of the suggested strategy depends on a kernel function and a parameter called bandwidth. The Nadaraya-Watson kernel (NWK) estimation is a necessary nonparametric kernel estimator used in regression models. A new Nadaraya-Watson regression estimate depends on the hyperbolic secant kernel (HSK) with fixed bandwidth (FNW) and Variable Bandwidth (VNW) is proposed.. We calculated some properties of the unknown regression function estimator, including bias, variance, optimal bandwidth, and a global measure of error criterion mean square error. Finally, simulation and three real data sets are used to evaluate its performance. Results from simulation and real data showed that the VNW using HSK is more effective than the FNW based on Average Mean Square Error Criterion. Also, Nadaraya-Watson using HSK function is more effective than Nadaraya-Watson using the Gaussian kernel density function.

Implications of Fiscal Policy on Economic Growth

This study's objective is to evaluate Pakistan's growth-oriented fiscal policy elements from 1980 to 2023. This research uses secondary sources of data. The paper utilized the Autoregressive Distributed Lag (ARDL) model as analytical techniques to assess the short- and long-term dynamics between Pakistan's fiscal policy components and economic growth. According to our regression estimations, government expenditure slows down economic expansion, whereas taxes have a growth-oriented effect. The investigation also examined the significant and negative impact of debt. Interest rates, the control variable, strongly and adversely impact growth. The analysis concludes that shifting the balance of government spending from non-development to development goals is the only way to achieve sustained growth. In addition, the government ought to ensure political stability, create laws that will encourage business, build infrastructure using foreign loans, and use debt to develop human capital.

Contributions of Tax Revenue and Government Expenditure to Sustainable Development Goals in Nigeria

This study empirically examined the effect of tax revenue and government expenditure on sustainable development goals in Nigeria. The ex-post facto research design was adopted using time series data sourced from the Central Bank of Nigeria's statistical bulletin and World Bank database. The study covered 22 years from 2001 to 2021. Descriptive and inferential statistical tools were used in analyzing the data after carrying out unit root tests on the stationarity of the series to avoid obtaining invalid and unauthentic regression estimates. The Vector Error Correction Model (VECM) was applied in analyzing the relationship. The study found that Tax Revenue (TR) exhibited a negative and significant effect on sustainable development goals, while Government expenditure (GEXP) indicated a positive and significant effect on Sustainable Development Goals (SDGIS) in the long run. Furthermore, the study revealed that in the short-run Tax Revenue (TR) and Government expenditure (GEXP) both had a negative effect on the SDGIS in Nigeria. There is need for government to develop strategies to broaden the tax base and bring more entities into the tax net while ensuring equitable contribution. They should also align budget allocations with SDG priorities to ensure tax revenue is directed sustainable development projects. Hence the study recommended that government should channel its resources towards closing up infrastructural deficits while increasing productive units that would enhance the economy and ensure optimal utilization of tax revenue towards sustainable developments in Nigeria especially in the achievement of the Sustainable development goals.

Empirical evidence of the relationship between regulatory efficiency, market openness, and bank productivity in economies at different income levels: Evidence from selected Asian and MENA countries

Research background: Economic freedom plays a pivotal role in ensuring the progressive productivity of banks. It fosters a favorable economic climate and acts as a catalyst for the generation of innovative ideas. In addition, economic freedom allows new domestic and foreign entrants in the banking sector which leads to increased competition as well as wider range of product offerings and thus potentially affect bank efficiency. Purpose of the article: This study aims to identify the effects of regulatory efficiency and market openness in terms of economic freedom on the bank’s productivity at three income levels: lower-middle, upper-middle, and high-income economies. Methods: A sample of 15 countries are included in the study from differing income levels. The study uses the data envelopment analysis (DEA) based Malmquist productivity index (MPI) approach to measure banks’ productivity. This non-parametric approach measures the relative efficiency of banks by considering the production change while taking into account technical efficiency change and technological change in order to capture a comprehensive view over time. Then, regression analysis was performed utilizing the ordinary least squares (OLS) approach, fixed effect (FE), and random effect (RE) panel multiple regression estimation methods are utilized to measure economic freedoms and other determinants’ effect on banks’ productivity change over time. Findings & value added: The results show that banks in high-income economies are more productive and have higher growth rates than those in upper- and lower-income economies. Furthermore, starting, obtaining permits, and closing businesses under business freedom have a detrimental effect on banks’ output, whereas the effects of labor freedom on employing, managing, and supervising staff members have a substantial favorable impact on banks’ productivity. Moreover, financial freedom and investment freedom under the market openness dimension negatively influence banks’ productivity. Government intervention is required to introduce regulations that allow foreign countries to provide labor at lower wages, introduce tax allowances, and control inflation rates. Thus, the empirical results of this study will benefit regulators and policymakers in developing a system and plan to increase banks’ productivity based on indicators of business, labor, financial, and investment freedom.

Concave and convex effects of ESG performance on corporate sustainable development: Evidence from China

Research background: Corporate sustainable development (CSD) is essential to a company's success and survival. Environmental, social, and governance (ESG) are regarded as major factors in measuring the impact of CSD. Companies that perform well in terms of ESG can maintain a competitive advantage and achieve sustainable development. Poor management of ESG performance and involvement in controversial activity can harm a company's credibility and reputation in the market, as well as negatively impact sustainable development. Purpose of the article: Drawing on the stakeholder and signaling theories, this paper investigates the curvilinear nexus between ESG performance and CSD. Methods: Empirical studies were conducted on a sample of 697 Chinese listed manufacturing firms that disclosed ESG information from 2010 to 2020, with a total of 5699 firm-year observations. Quantile regression analysis and the U-test were used to examine the curvilinear ESG-CSD relationship. This technique was supplemented by conducting instrumental variables tests and propensity score matching to address concerns relating to the potential existence of endogeneity problems. Findings & value added: The results of the quantile regression estimation confirm the concave-convex (inverted U-shaped and U-shaped) ESG-CSD relationship via the U-test. The relationships between the environmental and social components and CSD follow an inverted U-shaped or half-inverted U-shaped pattern, while the relationship between the governance component and CSD exhibits a concave-convex pattern. A concave ESG-CSD nexus is evident in environmentally sensitive industries, whereas a half concave-convex ESG-CSD nexus is confirmed in non-environmentally sensitive industries. This study improves scholars’ understanding of ESG performance and provides a comprehensive perspective on the double-edged effects (positive and negative consequences) of ESG practices. The instrumentalization of ESG practices for management to seek personal gain has a negative impact on CSD, while ESG practices that add value for stakeholders have a positive impact. These findings provide empirical evidence for Chinese publicly listed manufacturing firms to effectively conduct ESG practices.

Leverage ratio and corporate performance: Do marginal cost and marginal benefit of debt matter

This study examines leverage ratio and firm performance considering marginal benefits and marginal costs of debt to a firm. A total of 16 non-financial firms over a 15 year period (2001-2015) were randomly selected for the study. The panel data were subjected to Panel Least Square, Fixed Effects, and Random Effects regression estimations to test the formulated models in the study. Also the study employed Hausman Test to ascertain whether random effects model is the appropriate model or if fixed effects model is the appropriate model. The results shows that long term debt ratio (LTDR) have positive and significant influence on performance of Nigerian firms measured by Return on Asset (ROA) and Return on Equity (ROE). Short term debt ratio (STDR) on the other hand, established negative and significant effect on ROA, and negative and insignificant impact on ROE. STDR accounting for 75% mean value of the total debt ratio of the sampled firms, the researcher therefore, infer that financial structure has negative and significant influence on the performance of Nigerian firms. This outcome is attributed to mismatch of funds and high risk investment (asset substitution effect) resulting to marginal benefits of monitoring and bonding activities less than the marginal costs as noted by agency cost theory. The study therefore concludes that debt is valuable in reducing the agency costs of equity in professionally managed firm but at the same time debt is costly as it increase the agency cost of debt.

Deep learning-based estimation of time-dependent parameters in Markov models with application to nonlinear regression and SDEs

We present a novel deep-learning method for estimating time-dependent parameters in Markov processes through discrete sampling. Departing from conventional machine learning, our approach reframes parameter approximation as an optimization problem using the maximum likelihood approach. Experimental validation focuses on parameter estimation in multivariate regression and stochastic differential equations (SDEs). Theoretical results show that the real solution is close to SDE with parameters approximated using our neural network derived under specific conditions. Our work contributes to SDE-based model parameter estimation, offering a versatile tool for diverse fields.

Unlocking Green Productivity Through Green Lending, Digitalisation and Financial Literacy

Purpose — This study aims to measure green productivity in the agricultural sector, specifically on Sumatra Island, with some driving factors such as green lending from rural banks (both conventional and Sharīʿah), digitalisation, and the intermediation of financial literacy. Design/Methodology/Approach — The study employs panel data from 154 regencies on Sumatra Island for the period 2018 to 2022. Data Envelopment Analysis was employed to generate agricultural green total factor productivity, followed by regression estimation to see the influence of each determining factor. Findings — This study reveals the significant impact of green lending on green productivity. However, in Sharīʿah rural banks, which adhere strictly to Sharīʿah rules, this impact is positive only when moderated by financial literacy. On the other hand, digitalisation is also found to influence green productivity, but the effect weakened when the level of financial literacy could not be controlled. Originality/Value — To the best of the author’s knowledge, this study is the first to observe green productivity in the agricultural sector within a dual economic system that fosters both Islamic and conventional financial practices at the regional level. Practical Implications — This study implies that governments and banks should integrate green lending and digitalisation across various levels of financial literacy.