Regression Approach Research Articles

Advancing Nuclear Energy Forecasting: Exploring Regression Modeling Techniques for Improved Accuracy

The urgent requirement for sustainable and dependable energy sources has stimulated an increased fascination with precisely forecasting nuclear energy generation. This work utilizes sophisticated regression modeling approaches, namely XGBoost, to predict nuclear energy generation by leveraging economic indices such as Gross Domestic Product (GDP). Each model’s prediction accuracy has been evaluated by examining historical data on nuclear energy output and GDP from various locations. Here, measures such as mean squared error (MSE) and coefficient of determination (R2) to analyze their effectiveness have been used. The results of this study demonstrate that the XGBoost model outperforms standard regression approaches, showing greater R2 values and lower MSE scores. Furthermore, the consequences of these discoveries for the development of energy policy offer possible directions for future study in energy forecasting. This study provides useful insights for energy planners and policymakers, enabling a more profound comprehension of the complex relationship between economic indicators and nuclear energy generation.

Exploring the relationship between blood platelet and other components utilizing count regression: A cross-sectional study in Bangladesh.

Blood, vital for transporting nutrients and maintaining balance, comprises red blood cells, white blood cells, and platelets, each pivotal. Imbalances lead to issues-low red cells cause fatigue (anemia), high white cells hint at infection, low counts raise infection risks. Using trendy statistical approaches, investigating the complex link between platelet counts and numerous blood components. Our investigation, leveraging count regression approaches, revealed deep insights into the interaction between platelet counts and other important hematological markers. A cross-sectional study utilized data from 3120 individuals, including both male and female participants, who visited these hospitals between June 16, 2022 and December 17, 2022, to assess their blood samples through testing by using convenience non-parametric sampling framework. Platelet count was taken into account as a measure of outcome in this research. This specific study region was chosen for its easy accessibility, which helped the seamless execution of the data-gathering technique. Count regression, negative binomial regression, and quasi-Poisson regression techniques have been employed for examining relationship of the data sets. Three different count regression models were utilized to assess the proper association between the response and the relevant covariates and we found negative binomial count regression model (Akaike information criterion = 76.55, Bayesian information criterion = 76.59, and deviance = 3.14) was providing comparatively better performance than others. Based on the chosen model we found white blood cell, erythrocyte sedimentation rate, and eosinophils are significant but neutrophil, monocyte, and lymphocyte are not significant. We have also gone through proper model adequacy checking for our selected model and we found enough evidence to justify our model. From the result, we found insightful remarks into the mechanisms involved in platelet production and regulation, which can aid in developing increased effective treatments and interventions to maintain optimal platelet levels and prevent health problems related to abnormal platelet counts.

Reconstructing blood flow in data-poor regimes: a vasculature network kernel for Gaussian process regression.

Blood flow reconstruction in the vasculature is important for many clinical applications. However, in clinical settings, the available data are often quite limited. For instance, transcranial Doppler ultrasound is a non-invasive clinical tool that is commonly used in clinical settings to measure blood velocity waveforms at several locations. This amount of data is grossly insufficient for training machine learning surrogate models, such as deep neural networks or Gaussian process regression. In this work, we propose a Gaussian process regression approach based on empirical kernels constructed by data generated from physics-based simulations-enabling near-real-time reconstruction of blood flow in data-poor regimes. We introduce a novel methodology to reconstruct the kernel within the vascular network. The proposed kernel encodes both spatiotemporal and vessel-to-vessel correlations, thus enabling blood flow reconstruction in vessels that lack direct measurements. We demonstrate that any prediction made with the proposed kernel satisfies the conservation of mass principle. The kernel is constructed by running stochastic one-dimensional blood flow simulations, where the stochasticity captures the epistemic uncertainties, such as lack of knowledge about boundary conditions and uncertainties in vasculature geometries. We demonstrate the performance of the model on three test cases, namely, a simple Y-shaped bifurcation, abdominal aorta and the circle of Willis in the brain.

Project characteristic-based performance prediction model for school constructions: hierarchical regression approach

Project underperformance remains a significant concern in the construction industry. The majority of prior studies have focused on identifying the subjective factors that affect project performance. However, there are currently no in-depth studies evaluating the influence of project characteristics and managerial/organizational obstacles on construction project performance for design-bid-build projects using empirical data. Therefore, this study aims to present a predictive model that illustrates the correlation between project characteristics, managerial/organizational complexity and difficulties, and construction project performance. Project data relating to the construction of 101 public schools within a developing country was collected. Subsequently, the project characteristics were identified, and two performance indicators (schedule performance index and cost performance index) were calculated for each project. A survey was conducted with construction professionals who took part in all of the control and management processes of these school projects to evaluate their managerial and organizational difficulties. Hierarchical regression model approach and correlation analyses were employed to develop the predictor model. The results indicate that factors such as location, school type, and project duration significantly predict both the schedule performance and managerial and organizational difficulties in school construction. An indirect correlation, rather than a direct association, was found between schedule performance and managerial and organizational difficulties. The proposed model will be a helpful guide for construction professionals, engineering managers and government decision-makers seeking to improve the performance of "design-bid-build" school construction projects. We suggest integrating the qualification-based selection (QBS) system into traditional procurement methods for public investments.

Energy-related uncertainty shocks and inflation dynamics in the U.S: A multivariate quantile-on-quantile regression approach

Existing literature suggests that uncertainty shocks can propagate like aggregate demand shocks or aggregate supply shocks. By way of extension, this study investigates the effect of energy-related uncertainty shocks on U.S. inflation while incorporating the effect of industrial production and interest rate uncertainty shocks. Using a multivariate quantile-on-quantile regression for the period 2000:M6 to 2019:M7, the findings reveal that energy-related uncertainty shocks amplify inflation by manifesting as cost-push shocks with a stronger connection emerging in quantiles slightly above the median quantile distribution of energy-related uncertainty. Although industrial production positively drives inflation, its effect is observed less around median quantiles of inflation than in the lower and upper quantiles. Furthermore, the effect of interest rate uncertainty is negative and stronger in quantiles around the median of inflation, suggesting that interest rate uncertainty behaves like aggregate demand shocks. Based on these findings, policy implications are offered.

THE INFLUENCE OF ACCOUNTING DIGITALISATION TRANSFORMATION AND SUSTAINABLE MANAGEMENT ON ESG PERFORMANCE TO ACHIEVE ENVIRONMENTAL SUSTAINABILITY

This research aims to examine and analyse the influence of accounting digitalisation transformation and sustainable management on ESG (Environmental, Social, and Governance) performance as a supporting capacity for hotel environmental sustainability programs. This research was conducted on a population of 1,010 four and five-star hotels in Indonesia based on data from the Central Statistics Agency. The study employed a quantitative research method with a survey design, utilising both online and offline questionnaires. Data analysis was conducted using a multiple linear regression approach. The empirical findings indicate that the digital transformation of accounting and sustainable management has a notable positive impact on ESG performance, thereby indicating its potential to bolster environmental sustainability within the hotel industry. This suggests that leveraging the digital transformation of sustainable accounting and management as a proxy for legitimacy theory can genuinely enhance ESG performance and contribute to environmental sustainability practices in the hotel sector. The research contribution is aimed at strengthening legitimacy theory in research in the field of sustainability accounting and can practically be used as a management reference in managing hotels towards sustainable hotels oriented towards environmental sustainability and receiving the title of green hotel.

Exploring spatiotemporal Dynamics and influencing factors of cyber-fraud: A quantile regression approach in Xiaoshan District, China

This study utilizes data on cyber-fraud crimes from the Public Security Bureau in Xiaoshan District for the year 2021 as its case study. It examines the spatiotemporal distribution of various types of cyber-fraud and investigates the influencing factors from social and built environments. Additionally, quantile regression models are employed to analyze the variation in the number of cases across different quantiles of the influencing factors. The study reveals significant differences in individual characteristics among victims of different types of fraud. Cyber-fraud occurrences exhibit distinct temporal patterns across various temporal scales, with significant differences in the duration of crimes among different fraud types. Cyber-fraud demonstrates significant spatial clustering, mainly concentrated in residential areas. The results of quantile regression indicate that cyber fraud is influenced by both the built environment and social environment, with noticeable variations in the coefficient of influence across different quantiles of the independent variables.

MODELING STUNTING PREVALENCE IN INDONESIA USING SPLINE TRUNCATED SEMIPARAMETRIC REGRESSION

Semiparametric regression combines parametric and nonparametric regression approaches. It is employed when the relationship pattern of the response variable is known with some predictors, while for other predictors, the relationship pattern is uncertain. The parametric regression component in this study is linear regression, while the nonparametric component utilizes a spline truncated estimator, resulting in a semiparametric spline truncated regression model. The case study focuses on the prevalence of stunting across 34 provinces in Indonesia in 2022, revealing a relatively high prevalence of 21.60%. The research aims to determine the optimal number of knots, the best model, and factors influencing stunting prevalence in Indonesia. The findings indicate that the optimal three-knot model with a GCV of 9.30 yields an RMSE of 1.70 and R2 of 92.71%. Significance tests for simultaneous and partial parameters reveal that all predictor variables significantly influence stunting prevalence.

LOGISTIC AND PROBIT REGRESSION MODELING TO PREDICT THE OPPORTUNITIES OF DIABETES IN PROSPECTIVE ATHLETES

Diabetes is among the most prevalent chronic diseases globally, posing significant health risks to individuals. The identification of individuals at risk of developing these conditions is of paramount importance, particularly in high-stress and physically demanding activities such as athletic training. To find out the chances of a prospective athlete suffering from diabetes or not, models for binary data can be used, including logistic regression and probit models. The data used is primary data from prospective athletes in East Java, including prospective athletes from the State University of Surabaya and East Java Koni Athletes. This study aimed to develop an early prediction model for diabetes in prospective athletic candidates using a bivariate logistic and probit regression approach while considering the influence of socio-demographic and anthropometric factors. To selecting the best model between logistic regression and probit regression using Akaike’s Information Criterion (AIC) value, the smaller the AIC value gets means that the model is closer to the actual value or being the best model. Logistic regression has a smaller AIC value (129,85) than probit regression, this means that the logistic model is the best model. In this paper, an attempt is made to explore the use of logistic and probit regression to determine the factors which significantly influence the diabetes disease and we got that the logistic model as the best model because it has a smaller AIC value than the probit model. Based on the result of analysis and discussion, it can be concluded that there are two factors called mother’s job and finance which are influenced to the response variable, diabetes disease at significance level of 5%.

Supplementary rental supply? The digital market for low-cost and informal housing in Sydney, Australia

This article examines real estate platforms and the data they generate to provide new insights into housing markets and practices, focusing on lower-cost and informal sectors, where building or rental regulations are often bypassed or contravened. We examine online listings advertised in Sydney, one of the most expensive cities in Australia and the world, compiling data from four dominant platforms – Realestate.com.au, Flatmates.com.au, Gumtree.com.au and Airbnb.com – each of which offers a particular type of rental accommodation. Using these datasets, we identify a typology of lower-cost and informal tenures and dwelling units, ranging from secondary dwellings and illegally subdivided apartments to shared accommodation and precarious rental agreements. Our study highlights a supplementary supply of rental housing, operating within the conventional private rental market, accessed and made visible via the platforms we examine. Applying a statistical regression approach, we examine relationships between concentrations of informal housing supply and socio-economic variables. The findings reveal intersections between digital platforms and evolving informal market practices and have implications for urban planning and housing policy.

Mapping desertification susceptibility in the Hodna watershed Algeria, using a remote sensing-based logistic regression approach

Mapping desertification susceptibility in the Hodna watershed Algeria, using a remote sensing-based logistic regression approach

Enhancing Entrepreneurial Orientation among Women: A Multi Regression Approach

The survival, growth and prosperity of any region depend upon its economy. While the government undertakes every step it can take to boost the economy of a region, it cannot uplift the economy alone. The entrepreneurs play a pivotal role in assisting the government in completing this Herculean task. The contribution of entrepreneurs is even more significant in small states like Uttarakhand, which is still in its nascent state after being carved out in 2000 as the 27th state of India. The hilly terrains, remoteness from the center, and extreme climate all contribute to making its economy more contingent upon the entrepreneurial ventures of the indigenous people. While there is a surge of entrepreneurial activities in urban areas close to the plains, there is a dearth of such endeavors in the hilly areas. The situation is graver in the rural areas of the hilly region, especially for women as most of them lack awareness, resources and support and are primarily engaged in agricultural and husbandry activities. A paradigm change is required for the inclusion of such women for the holistic and heuristic development of the economy. This demands a shift from an agrarian to an entrepreneurial civilization. However, entrepreneurial orientation cannot be developed overnight and in isolation. It requires the instillation of personality characteristics. In the present paper, the researchers have identified three personality variables: – self-esteem, self-efficacy, and locus of control as the antecedents of entrepreneurial orientation and, using multiple regression, have explored the contribution of these personality variables to entrepreneurial orientation among women in the hilly region of Uttarakhand. The data for the present study were collected using stratified sampling and structured questionnaires from 200 women in the age group of 18 years to 40 years. The finding revealed that the personality variables accounted for 66.5 % of the variation in entrepreneurial orientation. Further, it also revealed that locus of control (LOC) contributed most to the development of entrepreneurial orientation (EO), followed by self-efficacy and self-esteem.

Pengaruh Rasio Likuiditas dan Rasio Aktivitas Terhadap Profitabilitas Pada PT. Surya Toto Indonesia, Tbk

This study aims to analyze the influence of liquidity ratio and activity ratio on profitability in PT. Surya Toto Indonesia, Tbk. Liquidity ratio is measured using Current Ratio (CR) and Quick Ratio (QR), while activity ratio is measured using Total Asset Turnover (TATO) and Inventory Turnover (ITO). The research method used is a quantitative method with a multiple linear regression approach. The data used in this study is secondary data obtained from the financial statements of PT. Surya Toto Indonesia, Tbk during the 2018-2022 period. The results show that the liquidity ratio and activity ratio have a significant influence on profitability as measured by Return on Assets (ROA). Current Ratio (CR) and Total Asset Turnover (TATO) have a positive and significant effect on profitability, while Quick Ratio (QR) and Inventory Turnover (ITO) have a negative but insignificant effect. These findings indicate that companies should pay attention to liquidity management and their operational activities to increase profitability.

The Influence of Earning Per Share (EPS) and Price Earnings Ratio (PER) on Stock Prices in the Food and Beverage Sector on the Indonesian Stock Exchange (BEI) for the 2015-2019 Period

The objective of this study is to examine the impact of earnings per Share (EPS) and Price Earnings Ratio (PER) on the stock prices of companies in the food and beverage industry listed on the Indonesia Stock Exchange (BEI) from 2015 to 2019. EPS is utilized as a metric to gauge the profitability of each share, whereas PER characterizes the market's assessment of the earnings generated per share. The research employed a descriptive verification analysis method, utilizing a sample of seven prominent organizations within the researched sector.The data utilized is derived from the yearly financial reports of each company, specifically secondary data. The investigation employed multiple regression approaches to examine the hypothesis regarding the impact of EPS and PER on stock prices. The test utilizes the coefficient of determination to ascertain the extent to which the regression model can account for the fluctuations in stock prices.The research findings indicate a substantial correlation between EPS (Earnings Per Share), PER (Price Earnings Ratio), and firm share prices within the food and beverage industry on the IDX (Indonesia Stock Exchange). The R^2 value of 0.753 suggests that 75.3% of the changes in stock prices can be accounted for by the independent variables, EPS and PER. In this industry, share prices are primarily influenced by the profitability per share and market valuation.In addition, this study emphasizes that additional variables not investigated in this research can significantly impact stock prices, including macroeconomic conditions, market sentiment, government regulations, and other external factors. Stable macroeconomic conditions can lead to more favorable circumstances for increased stock values, whereas government policy or market sentiment alterations can profoundly influence a company's stock performance.The recommendations derived from this study are intended for investors and corporate executives operating in the food and beverage industry on the IDX. Investors are advised to consider the earnings per share (EPS) and price-to-earnings ratio (PER) components of their fundamental analysis to make better-informed investment choices. It is recommended that companies prioritize enhancing their financial performance and ensuring openness in their financial reporting to boost market trust and raise the value of their shares.Subsequent investigations might broaden the range by including supplementary variables like Dividend Yield or Return on Equity (ROE) while doing a more extensive analysis of qualitative elements that impact market perceptions of EPS and PER. This research contributes to understanding the factors that impact share prices in the Indonesian capital market, particularly within the food and beverage industry.

From biomass to Energy: Investigating Chlorella pyrenoidosa’s potential for fuel and carbon materials

This study investigated the bioenergy potential of Chlorella pyrenoidosa (CP) for use as fuel and carbon material through chemical and thermal characterization. The thermo-kinetic characteristics of Chlorella pyrenoidosa were assessed using isoconversional, linear regression, and non-linear regression approaches. The physicochemical analysis revealed high carbon (53.1 %), volatile (69.35 %), and low moisture (2.19 %), ash content (3.42 %). The results indicated that the non-linear model fitting method was the most accurate with the approximated activation energy (Eα) and pre-exponential Arrhenius constant (Ln A) were 124.92 ± 2.74 kJ/mol and 23.38 ± 4.63 min−1, respectively. Additionally, the inclusion of sodium bicarbonate resulted in a significant increase in BET surface area. FTIR analysis revealed several functional groups beneficial for carbon material, while XRD analysis showed a broad peak correlated with an amorphous structure. This study highlighted the potential of Chlorella pyrenoidosa biomass for various applications, including carbon material and renewable fuel.

Governance and the relationship between corruption and FDI in Africa: a threshold regression analysis

ABSTRACT Research on the institutional environment, corruption, and FDI highlights an important facilitating relationship between these factors. The effect of corruption on FDI vis-à-vis the grabbing hand vs. the helping hand hypotheses has been previously examined with suggestions that both hypotheses can co-exist under the assumption that the FDI-corruption relationship depends on the level of institutions. This study revisits this relationship for 34 African countries over the 2005 to 2019 period using the dynamic panel threshold model, which allows for an endogenous threshold variable. Previous studies that have examined this relationship using a threshold regression approach are either not based exclusively on African countries (where the implication of this relationship is more salient) or use a threshold regression that assumes exogeneity of the threshold variable. This study examines the facilitating nature of governance measures – political stability, government effectiveness, rule of law and regulatory quality – on the corruption-FDI relationship. The results indicate significant threshold effects and shows that while the grabbing hand hypothesis is consistent with the data irrespective of the institutional proxy used, the helping hand hypothesis is sensitive to the choice of governance. These results agree with the strand of literature that supports a weak helping hand hypothesis.

Exploring the role of cultural diversity as a mediator in tactical leadership and inventiveness

The goal is to determine how cultural diversity, acting as a mediator between different cultures, influences creativity in the Indian police management sector. The Indian police administration's information from staff members was gathered using a quantitative research technique and survey methodologies. To ensure that the workers' responses were accurate, the self-administrative surveys were sent out. As a result, 380 surveys were dispersed among the 80 branches mentioned, and 300 valid responses were gathered. In this study, the anticipated characteristics and the identifiable characteristics were projected to an unfamiliar environment to analyze the regression approach and verify the hypothesis. The results of this research have demonstrated the variables' dependability and validity to support this investigation. According to this study, values support innovative leadership and innovation strategies, tactical inventiveness and leadership. The framework has made an essential contribution to the Indian police administration's subsequent growth.

Accelerating NMR Shielding Calculations Through Machine Learning Methods: Application to Magnesium Sodium Silicate Glasses.

In this work, we have applied the Kernel Ridge Regression (KRR) method using a Least Square Support Vector Regression (LSSVR) approach for the prediction of the NMR isotropic magnetic shielding (σiso) of active nuclei (17O, 23Na, 25Mg, and 29Si) in a series of (Mg, Na) - silicate glasses. The Machine Learning (ML) algorithm has been trained by mapping the local environment of each atom described by the Smooth Overlap of Atomic Position (SOAP) descriptor with isotropic chemical shielding values computed with DFT using the Gauge-Included-Projector-Augmented-Wave (GIPAW) approach. The influence of different training datasets generated through molecular dynamics simulations at various temperatures and with different inter-atomic potentials has been tested and we demonstrate the importance of a wide exploration of the configurational space to enhance the transferability of the ML-regressor. Finally, the trained ML-regressor has been used to simulate the 29Si MAS NMR spectra of systems containing up to 20000 atoms by averaging hundreds of configurations extracted from classical MD simulations to account for thermal vibrations. This ML approach is a powerful tool for the interpretation of NMR spectra using relatively large systems at a fraction of the computational time required by quantum mechanical calculations which are of high computational cost.

Investigating the impact of the COVID-19 pandemic and macroeconomic variables on unemployment among university graduates in Indonesia: Regression and Fs-QCA approaches

Investigating the impact of the COVID-19 pandemic and macroeconomic variables on unemployment among university graduates in Indonesia: Regression and Fs-QCA approaches

The effects of specific vegetable subtypes on constipation incidence in the general United States population.

While the intake of larger quantities of vegetables has been linked to a reduction in constipation risk, which vegetables in particular underlie this risk reduction remains incompletely understood. As such, the present study was developed to explore correlations between the intake of particular vegetable types and the risk of constipation. This cross-sectional analysis was based on data from the National Health and Nutrition Examination Survey (NHANES) collected from 2005-2010. Classifications and intake assessments for different vegetables were assessed with the Food Patterns Equivalents Database (FPED), while stool frequency or stool consistency was used to define constipation. Relationships between the intake of particular vegetable components and constipation were assessed through a weighted logistic regression approach. Subgroup and restricted cubic spline (RCS) regression analyses were further employed to explore associations between specific vegetable subtypes and constipation. This study included 13,860 eligible subjects, of whom 1,405 and 12,455 were respectively classified into the constipated and non-constipated groups. Following multivariate adjustment, the intake of non-starchy vegetables including orange, red, dark green, and other vegetables was found to be positively associated with a reduction in constipation risk. In contrast, constipation was unrelated to total starchy vegetable or potato intake. Tomatoes, in particular, were associated with a marked decrease in constipation risk (odds ratios: 0.80, 95% confidence interval: 0.71-0.91). These results were confirmed through RCS and subgroup analyses. Non-starchy vegetables, particularly tomatoes, were found to be associated with a pronounced reduction in constipation risk, which was unaffected by the intake of potatoes or starchy vegetables.