Proposed Regression Model Research Articles

How capital markets assess the credibility and accuracy of CSR reporting: Exploring the effects of assurance quality and CSR restatement issuance

AbstractThis research examines how the credibility and accuracy of corporate social responsibility (CSR) disclosures enhance market confidence by exploring their effect on the cost of capital. How do capital markets react to higher‐quality assurance of CSR reporting? Can the hypothetical reduction in the cost of capital that assurance quality produces be explained by restatements of previous information given in these CSR reports? We explore the relationship between assurance quality, as a proxy for credibility and market confidence, and the mediating effect of CSR restatements as indicators of accuracy. We propose regression models with a sample of CSR reports issued by European companies. Building upon the signalling and legitimacy theories, the results support the positive effect of higher assurance quality statements on market confidence by confirming a decrease in the cost of capital; assurance quality gives an indication of credibility to the capital market and restatements related to methodological updates signal accuracy. The reduction in the cost of capital brought on by higher assurance quality appears to be determined by the issuance of CSR restatements, which create legitimacy for both client companies and assurance providers. CSR reporting and assurance have reached a greater level of maturity as demonstrated by the evolution of these practices and financial market perceptions.

Human detection in aerial thermal imaging using a fully convolutional regression network

Thermal imaging can play a critical role in surveillance by promising higher robustness to the bad weather and night vision. Human detection and localization are important surveillance tasks for security purposes and maintaining law and order. This paper proposes a novel regression-based method for human detection from thermal infrared images. A fully convolutional regression network is designed to map the human heat signature in the input thermal image to the spatial density maps. The regressed density map is then post-processed for human detection and localization in the image. 25% data holdout validation scheme is used to train and test the proposed regression model using two benchmark thermal image datasets, the autonomous system lab thermal infrared dataset and the Ohio state university thermal pedestrian database. The proposed regression-based method can detect humans with 99.16% precision and 98.69% recall, outperforming the state-of-the-art conventional hand-crafted and CNN-based techniques for human detection from thermal images. Further, the designed fully convolutional regression network has much reduced computational complexity; yet, the detection performance is on par with the state-of-the-art fully convolutional architectures for predicting the density maps for human detection in thermal images.

Short Term Active Power Load Prediction on A 33/11 kV Substation Using Regression Models

Electric power load forecasting is an essential task in the power system restructured environment for successful trading of power in energy exchange and economic operation. In this paper, various regression models have been used to predict the active power load. Model optimization with dimensionality reduction has been done by observing correlation among original input features. Load data has been collected from a 33/11 kV substation near Kakathiya University in Warangal. The regression models with available load data have been trained and tested using Microsoft Azure services. Based on the results analysis it has been observed that the proposed regression models predict the demand on substation with better accuracy.

Predicting COVID-19 statistics using machine learning regression model: Li-MuLi-Poly.

In this paper, linear regression (LR), multi-linear regression (MLR) and polynomial regression (PR) techniques are applied to propose a model Li-MuLi-Poly. The model predicts COVID-19 deaths happening in the United States of America. The experiment was carried out on machine learning model, minimum mean square error model, and maximum likelihood ratio model. The best-fitting model was selected according to the measures of mean square error, adjusted mean square error, mean square error, root mean square error (RMSE) and maximum likelihood ratio, and the statistical t-test was used to verify the results. Data sets are analyzed, cleaned up and debated before being applied to the proposed regression model. The correlation of the selected independent parameters was determined by the heat map and the Carl Pearson correlation matrix. It was found that the accuracy of the LR model best-fits the dataset when all the independent parameters are used in modeling, however, RMSE and mean absolute error (MAE) are high as compared to PR models. The PR models of a high degree are required to best-fit the dataset when not much independent parameter is considered in modeling. However, the PR models of low degree best-fits the dataset when independent parameters from all dimensions are considered in modeling.

Compositional Scalar-on-Function Regression with Application to Sediment Particle Size Distributions

The chemical composition of sediments is controlled predominantly by the sediment grain size, and thus evaluating their relationship is an important task in sedimentary geochemistry. The grain size is characterized by the respective particle size distribution, which can be expressed as a probability density function. Because of the relative character of densities, the Bayes space methodology was employed to build a regression model between a real response and a density function as a covariate, here the chemical composition and the particle size density. For practical computations, density functions were expressed in the standard $$L^2$$ space using the centred logratio transformation and spline approximation of the input discretized densities was utilized by respecting the induced zero-integral constraint. After a concise simulation study, supporting the relevance of the proposed regression model, the new methodology was applied to examine the relationship between sediment grain size and geochemical composition, with samples being obtained in the Czech Republic in the Skalka Reservoir and in the Ohře River floodplain upstream of the reservoir, to reveal proper grain size proxies. The Al/Si and Zr/Rb logratios in the sediments that were studied showed grain-size control, which makes them suitable for this purpose.

A robust Birnbaum–Saunders regression model based on asymmetric heavy-tailed distributions

Skew-normal/independent distributions provide an attractive class of asymmetric heavy-tailed distributions to the usual symmetric normal distribution. We use this class of distributions here to derive a robust generalization of sinh-normal distributions (Rieck in Statistical analysis for the Birnbaum–Saunders fatigue life distribution, 1989), we then propose robust nonlinear regression models, generalizing the Birnbaum–Saunders regression models proposed by Rieck and Nedelman (Technometrics 33:51–60, 1991) that have been studied extensively. The proposed regression models have a nice hierarchical representation that facilitates easy implementation of an EM algorithm for the maximum likelihood estimation of model parameters and provide a robust alternative to estimation of parameters. Simulation studies as well as applications to a real dataset are presented to illustrate the usefulness of the proposed model as well as all the inferential methods developed here.

Regression Models for Symbolic Interval-Valued Variables.

This paper presents new approaches to fit regression models for symbolic internal-valued variables, which are shown to improve and extend the center method suggested by Billard and Diday and the center and range method proposed by Lima-Neto, E.A.and De Carvalho, F.A.T. Like the previously mentioned methods, the proposed regression models consider the midpoints and half of the length of the intervals as additional variables. We considered various methods to fit the regression models, including tree-based models, K-nearest neighbors, support vector machines, and neural networks. The approaches proposed in this paper were applied to a real dataset and to synthetic datasets generated with linear and nonlinear relations. For an evaluation of the methods, the root-mean-squared error and the correlation coefficient were used. The methods presented herein are available in the the RSDA package written in the R language, which can be installed from CRAN.

Prediction model of isolated iliac and abdominal aneurysms.

We analyse the cardiovascular risk factors in patients undergoing screening for Isolated Iliac Aneurysm (IIA) and Abdominal Aortic Aneurysm (AAA) and propose a logistic regression model to indicate patients at risk of IIA and/or AAA. A screening programme was carried out to identify the presence of aneurysm based on Duplex scan examination. Cardiovascular risk factors information was collected from each subject. A descriptive analysis for the incidence of IIA and AAA stratified by age and sex was carried out to evaluate factors incidence. A logistic regression model was developed to predict the probability of developing an aneurysm based on the observed risk factor levels. A threshold probability of aneurysm risk for a datum patient was also identified to effectively direct screening protocols to patients most at risk. A cohort of 10842 patients was evaluated: 1.52% affected by IIA, 2.69% by AAA and 3.90% by at least one. Risk factors analysis showed that: IIA was correlated with cardiological status, diabetes, cardiovascular disease family history, and dyslipidaemia; AAA was correlated with cardiological status, body mass index, hypertension, and dyslipidaemia; diabetes and dyslipidaemia were the most relevant factors with at least one aneurysm. The prediction tool based on the logistic regression and the threshold probability predict the presence of IIA and AAA in 69.7% and 83.8% of cases, under k-fold cross-validation. The proposed regression model can represent a valid aid to predict IIA and AAA presence and to select patients to be screened.

Smartphone-Based Prediction Model for Postoperative Cardiac Surgery Outcomes Using Preoperative Gait and Posture Measures.

Gait speed assessment increases the predictive value of mortality and morbidity following older adults’ cardiac surgery. The purpose of this study was to improve clinical assessment and prediction of mortality and morbidity among older patients undergoing cardiac surgery through the identification of the relationships between preoperative gait and postural stability characteristics utilizing a noninvasive-wearable mobile phone device and postoperative cardiac surgical outcomes. This research was a prospective study of ambulatory patients aged over 70 years undergoing non-emergent cardiac surgery. Sixteen older adults with cardiovascular disease (Age 76.1 ± 3.6 years) scheduled for cardiac surgery within the next 24 h were recruited for this study. As per the Society of Thoracic Surgeons (STS) recommendation guidelines, eight of the cardiovascular disease (CVD) patients were classified as frail (prone to adverse outcomes with gait speed ≤0.833 m/s) and the remaining eight patients as non-frail (gait speed >0.833 m/s). Treating physicians and patients were blinded to gait and posture assessment results not to influence the decision to proceed with surgery or postoperative management. Follow-ups regarding patient outcomes were continued until patients were discharged or transferred from the hospital, at which time data regarding outcomes were extracted from the records. In the preoperative setting, patients performed the 5-m walk and stand still for 30 s in the clinic while wearing a mobile phone with a customized app “Lockhart Monitor” available at iOS App Store. Systematic evaluations of different gait and posture measures identified a subset of smartphone measures most sensitive to differences in two groups (frail versus non-frail) with adverse postoperative outcomes (morbidity/mortality). A regression model based on these smartphone measures tested positive on five CVD patients. Thus, clinical settings can readily utilize mobile technology, and the proposed regression model can predict adverse postoperative outcomes such as morbidity or mortality events.

Market Concentration and Performance the Case of the U.S. Airline Industry

This paper investigates the role of market power in the US airline industry and its role in the profitability of the U.S. passenger airline sector. To examine this relationship, we propose a model that includes key financial indicators of airline performance. Our data set includes nine air carrier firms and quarterly data from the first quarter of 1980 through the fourth quarter of 2019. Our empirical findings under three assumptions for unbalanced panel estimation of the proposed regression model confirm that the declining concentration of market share in the industry improves industry competitiveness and contributes to air carrier firms’ profitability.

Formability and Failure Evaluation of AA3003-H18 Sheets in Single-Point Incremental Forming Process through the Design of Experiments.

The single-point incremental forming process (SPIF) is one of the emerging manufacturing methods because of its flexibility in producing the desired complex shapes with higher formability at low-cost compared to traditional sheet forming methods. In this research work, we experimentally investigate the forming process to determine the influence of process parameters and their contribution to enhancing the formability without causing a fracture by combining the design of experiments (DOE), grey relational analysis (GRA), and statistical analysis of variance (ANOVA). The surface morphology and the energy dispersive X-ray spectroscopy (EDS) method are used to perform elemental analysis and examine the formed parts during three forming stages. The DOE procedure, a central composite design with a face-centered option, is devised for AA3003-H18 Al alloy sheet for modeling the real-time experiments. The response surface methodology (RSM) approach is adopted to optimize the forming parameters and recognize the optimal test conditions. The statistically developed model is found to have agree with the test measurements. The prediction model’s capability in is computed as 0.8931, indicating that the fitted regression model adequately aligns with the estimated grey relational grade (GRG) data. Other statistical parameters, such as root mean square error (RMSE) and average absolute relative error (AARE), are estimated as 0.0196 and 2.78%, respectively, proving the proposed regression model’s overall closeness to the measured data. In addition, the prediction error range is identified as −0.05 to 0.05, which is significantly lower and the residual data are distributed normally in the design space with variance and mean of 3.3748 and −0.1232, respectively. ANOVA is performed to understand the adequacy of the proposed model and the influence of the input factors on the response variable. The model parameters, including step size, feed rate, interaction effect of tool radius and step size, favorably influence the response variable. The model terms X2 (0.020 and 11.30), X3 (0.018 and 12.16), and X1X2 (0.026 and 9.72) are significant in terms of p-value and F-value, respectively. The microstructural inspection shows that the thinning behavior tends to be higher as forming depth advances to its maximum; the deformation is uniform and homogeneous under the predefined test conditions.

Ultrasound-Assisted Extraction of Carotenoids from Orange Peel Using Olive Oil and Its Encapsulation in Ca-Alginate Beads.

The paper was aimed at developing an ultrasound-assisted extraction of carotenoids from orange peel using olive oil as a solvent. A central composite design was used to define the optimal conditions for their extraction. Under the optimal conditions (extraction time of 35 min, extraction temperature of 42 ℃, and a liquid-to-solid ratio of 15 mL/g), the experimental and predicted values of carotenoid content were 1.85 and 1.83 mg/100 g dry weight, respectively. The agreement of these values indicated the adequacy of the proposed regression model. The extraction temperature only had a negative influence on carotenoid content. The impact of extraction parameters on the carotenoid content was decreased according to the following order: extraction time, liquid-to-solid ratio, and extraction temperature. Ca-alginate beads were prepared using the extrusion process to increase the stability and protect the antioxidant activity of olive oil enriched with carotenoids. The encapsulation efficiency and particle mean diameter were 89.5% and 0.78 mm, respectively. The presence of oil extract in Ca-alginate beads was confirmed by Fourier-transform infrared spectroscopy. The antioxidant activity of the oil enriched with carotenoids before and after encapsulation in the alginate beads was determined according to the DPPH assay.

On the Regression Model for Generalized Normal Distributions.

The traditional linear regression model that assumes normal residuals is applied extensively in engineering and science. However, the normality assumption of the model residuals is often ineffective. This drawback can be overcome by using a generalized normal regression model that assumes a non-normal response. In this paper, we propose regression models based on generalizations of the normal distribution. The proposed regression models can be used effectively in modeling data with a highly skewed response. Furthermore, we study in some details the structural properties of the proposed generalizations of the normal distribution. The maximum likelihood method is used for estimating the parameters of the proposed method. The performance of the maximum likelihood estimators in estimating the distributional parameters is assessed through a small simulation study. Applications to two real datasets are given to illustrate the flexibility and the usefulness of the proposed distributions and their regression models.

Transmuted Lower Record Type Fréchet Distribution with Lifetime Regression Analysis Based on Type I-Censored Data

This paper introduces a new lifetime distribution by mixing the first two lower record values and various distributional properties are examined. Statistical inference on distribution parameters are discussed with five estimators. A Monte Carlo simulation study is carried out to evaluate the risk behavior of these estimators for different sample of sizes. The distribution modeling analysis is provided based on real data to demonstrate the fitting ability of the proposed model. In addition, a lifetime regression model is described by re-parameterization on the log lifetimes. The superiority of proposed regression model is revealed in well-known models.

A new regression model for bounded response variable: An alternative to the beta and unit-Lindley regression models.

A new distribution defined on (0,1) interval is introduced. Its probability density and cumulative distribution functions have simple forms. Thanks to its simple forms, the moments, incomplete moments and quantile function of the proposed distribution are derived and obtained in explicit forms. Four parameter estimation methods are used to estimate the unknown parameter of the distribution. Besides, simulation study is implemented to compare the efficiencies of these parameter estimation methods. More importantly, owing to the proposed distribution, we provide an alternative regression model for the bounded response variable. The proposed regression model is compared with the beta and unit-Lindley regression models based on two real data sets.

Estimating principal plane positions for ocular power calculations in children and adults

To develop an age-dependent model to estimate the positions of the ocular and lenticular principal planes (pps) for use in ocular and axial power calculations. Ocular power of the eye (Peye ) and axial power (Pax ) were calculated based on previously published average data of the ocular biometry and refraction in newborn infants, children and adults, as well as the associated pp positions. Next, regressions of the pp positions were made as a function of the logarithm of age, which were subsequently used to estimate Peye and Pax . These regression-based estimates were compared with the original data for validation. Finally, this procedure was repeated using the Atchison myopic eye model to determine the influence of myopia on the regression estimates. In adults, the corneal pps almost coincide at 0.058mm in front of the cornea. The first lenticular pp position relative to the corneal apex is described by the equation: 5.809 - 0.697·exp(-0.211·Age) (r2 =0.96), and the second lenticular pp by 6.026 - 0.684·exp(-0.232·Age) (r2 =0.95). The first ocular pp position relative to the corneal apex is at 0.293·exp(-0.232·Age)-2.2·10-3 ·Age + 1.723 (r2 =0.99) and the second ocular pp is located at 0.392·exp(-0.181·Age) - 2.4·10-3 ·Age + 2.093 (r2 =0.99). Estimates of Peye and Pax derived from these regressions led to minor differences from the original values (0.00±0.06D and 0.00±0.10D, respectively). These errors were not affected by ocular refraction between -10D and 0D, with errors of+0.12±0.00D and -0.02±0.05D for Peye and Pax , respectively. The proposed regression models of the pp positions are sufficiently accurate to estimate Peye and Pax reliably. Interestingly, although the adult lens undergoes considerable physiological changes, its pps remain fixed with respect to the corneal apex.

Influential Parameter Analyses for Sinking Velocity with Measured Data

To study the effect of operational parameters on the sinking velocity of the landing gear of carrier-based aircraft, the influential analyses of various related parameters were performed based on the measured data of F/A-18. The probabilistic statistical characteristics of the sinking velocity were firstly investigated. And then correlation coefficient method and Levenberg-Marquardt (LM) algorithm were applied to finish influential parameter analyses. The analysis results show that the important influential parameters are aircraft glide angle, deck pitch angle, approaching velocity and engaging velocity; the mathematical model of sinking velocity is established by LM algorithm, and the determination coefficient is calculated via the variance analysis, which reveals that the proposed regression model is good. Compared with the measured data, the average errors for the predicted values of the established model of sinking velocity are less than 5%, which validates the effectiveness and feasibility of the method in engineering practice. The present efforts provide a way to study the relationships of the sinking velocity and the related influential parameters. And this work was proved to be a useful method for the study of sinking velocity.

Estimating Gestational Age From Maternal-Fetal Heart Rate Coupling Parameters

Maternal and fetal heartbeat couplings are evident throughout fetal development. Most of the published work, however, did not consider maternal physiological factors such as Heart Rate Variability (HRV), and did not investigate the interrelationships of maternal-fetal coupling parameters. The aims of this study are to investigate whether: 1) maternal-fetal Heart Rate (HR) coupling ( $\lambda $ -based) parameters are associated with fetal development, and 2) fetal gold standard Gestational Age (GA) can be estimated using maternal-fetal HR coupling and variability of various recording lengths. The study considered Electrocardiogram (ECG) signals from 60 healthy pregnant women with no records of fetal abnormalities. HRV and $\lambda $ parameters at various Maternal:Fetal coupling ratios were calculated, and stepwise regression was utilized to create generalized linear regression models considering various lengths of recorded signals (1 and 5 min) to produce a robust estimate of fetal age. Cross-validation performances were evaluated by the mean square root of the average of squared errors (mRMSE) between age values estimated by the proposed models and gold standard GA identified by Crown-Rump Length (CRL). Effect of Fetal Behavioral States (FBSes) on proposed models with different recording lengths was considered to examine the highly nonstationary nature of signals. We found that HR coupling strength for a specific ratio is not constant throughout gestation. Results showed that ratios of 2:3 and 2:4 were common between the proposed models. The value of $\lambda $ [2:3] was found to be positively correlated with GA, while $\lambda $ [2:4] had a negative correlation. Compared with gold standard GA identified by CRL, the proposed regression model resulted in mRMSE of 2.67 and 3.69 weeks for the recordings of 5 and 1 min, respectively. However, when FBS was considered, both models produced lower estimation errors. Fetal GA can be more reliably estimated by a multivariate model incorporating fetal and maternal HR coupling and HRV parameters using 5 min of ECG signals.

ВОСПРОИЗВОДСТВЕННЫЕ ПРОЦЕССЫ В НЕДРОПОЛЬЗОВАНИИ КАК ОСНОВА УСТОЙЧИВОГО СОЦИАЛЬНО-ЭКОНОМИЧЕСКОГО РАЗВИТИЯ НЕФТЕДОБЫВАЮЩИХ РЕГИОНОВ

There are numerous studies on different aspects of the impact of hydrocarbon production on Russian economy. Nevertheless, direct and indirect effects of reserve reproduction on social and economic development of oil-producing regions have been insufficiently assessed, even though it differs due to various macroeconomic processes and existing state mechanisms of subsoil use. The present paper examines the upstream sector of the petroleum industry comprising hydrocarbon exploration and production. The research hypothesis states that an imbalance in subsoil use results in growing inequality of socio-economic development of Russian regions, while the expansion of geological exploration work will reduce this effect. The study analyses the influence of geological exploration, leading to an increase in oil reserves and oil production, on gross regional product (GRP) per capita and personal income. For that purpose, the analysis was performed based on statistical data on five regions of the Russian Federation using the Cobb-Douglas production functions. According to the results obtained for blocks of the proposed regression model, Russian regions were divided into clusters in terms of the input effect on expected results. Overall, the influence of oil production on GRP per capita and average income is more significant compared to an increase in oil reserves. Moreover, the impact of the upstream sector in Tomsk oblast is stronger than in other constituent entities of the Russian Federation. The existing regional imbalance in social-economic development depends on not only available natural capital and tax relief system in subsoil management, but also differences in economic development and the role of petroleum industry in the analysed regions. In the context of recession, the expansion of geological exploration is required to increase natural capital that would provide the income many times higher than investments at the upswing of the cycle. The study results can be used for petroleum industry management in the field of geological exploration to justify the use of financial and fiscal incentives.

Prediction of Hole Expansion Ratio of Titanium Alloys Using R Programming

The hole expansion ratio (HER) is an important material property which defines the extent of edge formability of sheet metals. The stress states observed at the hole edge after the hole expansion test are similar to those seen during traditional uniaxial tensile deformation. This observation has provoked research, directed at ascertaining a correlation between the HER and tensile properties. In order to account for the forming behaviour of complex materials like titanium, a highly robust model that takes into account the material formability in all sheet-processing directions must be considered. The R programming language was used in this research to build a model fitting expression capable of predicting the HER as well as generating a regression model equation for titanium alloys, based on their thickness and Erichsen index number. The proposed regression model equation for predicting HER of titanium alloys exhibited an excellent statistical significance (p= 0.00076), indicating the robustness of the model fitting expression to predict HER values of titanium alloys. An accompanying adjusted R squared value of 0.9987 for the generated regression model equation also shows how well the regression line fits the data for accurate prediction of the HER of titanium alloys. A numerical validation analysis of the strength of the relationship derived between the predicted and the experimental HERs gave a correlation coefficient of 0.9884. This result shows a strong linear relationship between the experimental and predicted HER values of the titanium alloys with an average absolute error of 8.8%.