Search results
1 – 10 of over 12000Salwa Ben Ammou, Zied Kacem and Nabiha Haouas
In this paper, it is set out a hybrid data analysis method based on the combination of wavelet techniques and principal‐components regression (PCR). The purpose of this paper is…
Abstract
Purpose
In this paper, it is set out a hybrid data analysis method based on the combination of wavelet techniques and principal‐components regression (PCR). The purpose of this paper is to study the dynamics of the stock returns within the French stock market.
Design/methodology/approach
Wavelet‐based thresholding techniques are applied to the stock price series in order to obtain a set of explanatory variables that are practically noise‐free. The PCR is then carried out on the new set of regressors.
Findings
The empirical results show that the suggested method allows extraction and interpretation of the factors that influence the stock price changes. Moreover, the wavelet‐PCR improves the explanatory power of the regression model as well as its forecasting quality.
Practical implications
The proposed technique offers investors a better understanding of the mechanisms that explain the stock return dynamics as it removes the noise that affects financial time series.
Originality/value
The paper uses a new denoising framework for financial assets. The paper thinks that this framework might be of great value for academics as well as for financial investors.
Details
Keywords
Hassan Adaviriku Ahmadu, Yahaya Makarfi Ibrahim, Ahmed Doko Ibrahim and Muhammed Abdullahi
– This paper aims to develop a multivariate model that will be applicable to the Nigeria construction industry.
Abstract
Purpose
This paper aims to develop a multivariate model that will be applicable to the Nigeria construction industry.
Design/methodology/approach
A self-administered questionnaire survey was used to source information on project scope factors and qualitative factors considered in the study. Principal component regression was used for data analysis and model development, using SPSS 16.0 for windows, while T-test was used for model testing and validation.
Findings
The study found that delay in progress payment by owner, lateness in revising and approving design document by owner, delay in delivering the site to the contractor by the owner, change order by owner during construction, complexity of project design, poor site management and supervision by contractors, and rain effect on construction activities are qualitative/non-project scope factors with good predictive abilities.
Research limitations/implications
Cost, gross floor area and number of floors were the only quantitative/project scope factors considered in the study. The developed models therefore do not account for any variation in duration which may arise from other project scope factors, such as location, procurement route and type of contract.
Originality/value
The qualitative factors which emerged as predictors in the derived models increased the accuracy of the models. The models developed therefore serve as useful construction time prediction tools for both consultancy firms and contractor organizations in the Nigerian construction industry.
Details
Keywords
Bailing Zhang and Hao Pan
Many applications in intelligent transportation demand accurate categorization of vehicles. The purpose of this paper is to propose a working image-based vehicle classification…
Abstract
Purpose
Many applications in intelligent transportation demand accurate categorization of vehicles. The purpose of this paper is to propose a working image-based vehicle classification system. The first component vehicle detection is implemented by applying Dalal and Triggs's histograms of oriented gradients features and linear support vector machine (SVM) classifier. The second component vehicle classification, which is the emphasis of this paper, is accomplished by an improved stacked generalization. As an effective ensemble learning strategy, stacked generalization has been proposed to combine multiple models using the concept of a meta-learner. However, it was found that the well-known meta-learning scheme multi-response linear regression (MLR) for stacked generalization performs poorly on the vehicle classification.
Design/methodology/approach
A new meta-learner is then proposed based on kernel principal component regression (KPCR). The stacked generalization scheme consists of a heterogeneous classifier ensemble with seven base classifiers, i.e. linear discriminant classifier, fuzzy k-nearest neighbor, logistic regression, Parzen classifier, Gaussian mixture model, multiple layer perceptron and SVM.
Findings
Experimental results using more than 2,500 images from four types of vehicles (bus, light truck, car and van) demonstrated the effectiveness of the proposed approach. The improved stacked generalization produced consistently better results when compared to any of the single base classifier used and four other beta learning algorithms, including MLR, majority voting, logistic regression and decision template.
Originality/value
With the seven base classifiers, the KPCR-based stacking offers a performance of 96 percent accuracy and 95 percent κ coefficient, thus exhibiting promising potentials for real-world applications.
Details
Keywords
Vivekanand Venkataraman, Syed Usmanulla, Appaiah Sonnappa, Pratiksha Sadashiv, Suhaib Soofi Mohammed and Sundaresh S. Narayanan
The purpose of this paper is to identify significant factors of environmental variables and pollutants that have an effect on PM2.5 through wavelet and regression analysis.
Abstract
Purpose
The purpose of this paper is to identify significant factors of environmental variables and pollutants that have an effect on PM2.5 through wavelet and regression analysis.
Design/methodology/approach
In order to provide stable data set for regression analysis, multiresolution analysis using wavelets is conducted. For the sampled data, multicollinearity among the independent variables is removed by using principal component analysis and multiple linear regression analysis is conducted using PM2.5 as a dependent variable.
Findings
It is found that few pollutants such as NO2, NOx, SO2, benzene and environmental factors such as ambient temperature, solar radiation and wind direction affect PM2.5. The regression model developed has high R2 value of 91.9 percent, and the residues are stationary and not correlated indicating a sound model.
Research limitations/implications
The research provides a framework for extracting stationary data and other important features such as change points in mean and variance, using the sample data for regression analysis. The work needs to be extended across all areas in India and for various other stationary data sets there can be different factors affecting PM2.5.
Practical implications
Control measures such as control charts can be implemented for significant factors.
Social implications
Rules and regulations can be made more stringent on the factors.
Originality/value
The originality of this paper lies in the integration of wavelets with regression analysis for air pollution data.
Details
Keywords
The main objective of this study is to examine the claim of economic value added (EVA) proponents about its superiority as a financial performance measure compared to five…
Abstract
Purpose
The main objective of this study is to examine the claim of economic value added (EVA) proponents about its superiority as a financial performance measure compared to five traditional performance measures, i.e. net operating profit after tax (NOPAT), cash flow from operations (OCF), earnings per share (EPS), return on capital employed (ROCE) and return on equity (ROE) in Indian manufacturing sector, and simultaneously provide its empirical evidences. To achieve this, relative and incremental information content of various performance measures and their relationship with market value added (MVA) is tested and examined.
Design/methodology/approach
Principal component analysis (PCA) is one of the important multivariate methods utilized in business research for data reduction, latent variable modeling, multicollinearity resolution, etc. The present sample consists of 608 firm‐year observations from the Indian manufacturing sector for the period 2000‐2007. Firstly, principal component analysis (PCA) is employed to determine the important variables that explain market value. Secondly, alongside PCA, multiple regression models (OLS) are used to examine the relative and incremental information content of EVA and traditional performance measures.
Findings
These results about PCA reveal that variables like NOPAT, OCF, ROE, ROCE and EVA have maximum influence on the market value (MVA) of the sample companies, whereas EPS has a negative loading, so, EPS is discarded for further analysis. Further, the PCA loading matrix reveals that NOPAT, OCF, ROE and ROCE outscore EVA. The regression results regarding the relative information content test reveal that NOAPT and OCF outperform EVA in explaining the market value of Indian companies. The incremental information content test shows that EVA makes a marginal contribution to information content beyond NOPAT, OCF, ROCE and ROE. Overall, these empirical results about Indian companies do not support the Stern Stewart hypothesis that EVA is superior to traditional accounting‐based measures in association with market value of the firm.
Originality/value
The study concludes that along with financial variables, other non‐financial variables such as employees, product quality, etc., should be considered in order to capture the unexplained variation in the market value of Indian companies.
Details
Keywords
Bo Xiong, Sidney Newton, Vera Li, Martin Skitmore and Bo Xia
The purpose of this paper is to present an approach to address the overfitting and collinearity problems that frequently occur in predictive cost estimating models for…
Abstract
Purpose
The purpose of this paper is to present an approach to address the overfitting and collinearity problems that frequently occur in predictive cost estimating models for construction practice. A case study, modeling the cost of preliminaries is proposed to test the robustness of this approach.
Design/methodology/approach
A hybrid approach is developed based on the Akaike information criterion (AIC) and principal component regression (PCR). Cost information for a sample of 204 UK school building projects is collected involving elemental items, contingencies (risk) and the contractors’ preliminaries. An application to estimate the cost of preliminaries for construction projects demonstrates the method and tests its effectiveness in comparison with such competing models as: alternative regression models, three artificial neural network data mining techniques, case-based reasoning and support vector machines.
Findings
The experimental results show that the AIC–PCR approach provides a good predictive accuracy compared with the alternatives used, and is a promising alternative to avoid overfitting and collinearity.
Originality/value
This is the first time an approach integrating the AIC and PCR has been developed to offer an improvement on existing methods for estimating construction project Preliminaries. The hybrid approach not only reduces the risk of overfitting and collinearity, but also results in better predictability compared with the commonly used stepwise regression.
Details
Keywords
Since the beginning of 2020, economies faced many changes as a result of coronavirus disease 2019 (COVID-19) pandemic. The effect of COVID-19 on the Egyptian Exchange (EGX) is…
Abstract
Purpose
Since the beginning of 2020, economies faced many changes as a result of coronavirus disease 2019 (COVID-19) pandemic. The effect of COVID-19 on the Egyptian Exchange (EGX) is investigated in this research.
Design/methodology/approach
To explore the impact of COVID-19, three periods were considered: (1) 17 months before the spread of COVID-19 and the start of the lockdown, (2) 17 months after the spread of COVID-19 and the during the lockdown and (3) 34 months comprehending the whole period (before and during COVID-19). Due to the large number of variables that could be considered, dimensionality reduction method, such as the principal component analysis (PCA) is followed. This method helps in determining the most individual stocks contributing to the main EGX index (EGX 30). The PCA, also, addresses the multicollinearity between the variables under investigation. Additionally, a principal component regression (PCR) model is developed to predict the future behavior of the EGX 30.
Findings
The results demonstrate that the first three principal components (PCs) could be considered to explain 89%, 85%, and 88% of data variability at (1) before COVID-19, (2) during COVID-19 and (3) the whole period, respectively. Furthermore, sectors of food and beverage, basic resources and real estate have not been affected by the COVID-19. The resulted Principal Component Regression (PCR) model performs very well. This could be concluded by comparing the observed values of EGX 30 with the predicted ones (R-squared estimated as 0.99).
Originality/value
To the best of our knowledge, no research has been conducted to investigate the effect of the COVID-19 on the EGX following an unsupervised machine learning method.
Details
Keywords
Nursuhana Alauddin, Saki Tanaka and Shu Yamada
This paper proposes a model for detecting unexpected examination scores based on past scores, current daily efforts and trend in the current score of individual students. The…
Abstract
Purpose
This paper proposes a model for detecting unexpected examination scores based on past scores, current daily efforts and trend in the current score of individual students. The detection is performed soon after the current examination is completed, which helps take immediate action to improve the ability of students before the commencement of daily assessments during the next semester.
Design/methodology/approach
The scores of past examinations and current daily assessments are analyzed using a combination of an ANOVA, a principal component analysis and a multiple regression analysis. A case study is conducted using the assessment scores of secondary-level students of an international school in Japan.
Findings
The score for the current examination is predicted based on past scores, current daily efforts and trend in the current score. A lower control limit for detecting unexpected scores is derived based on the predicted score. The actual score, which is below the lower control limit, is recognized as an unexpected score. This case study verifies the effectiveness of the combinatorial usage of data in detecting unexpected scores.
Originality/value
Unlike previous studies that utilize attribute and background data to predict student scores, this study utilizes a combination of past examination scores, current daily efforts for related subjects and trend in the current score.
Details
Keywords
Sang Quang Van, Long Le-Hoai and Chau Ngoc Dang
The purpose of this paper is to predict implementation cost contingencies for residential construction projects in flood-prone areas, where floods with storms frequently cause…
Abstract
Purpose
The purpose of this paper is to predict implementation cost contingencies for residential construction projects in flood-prone areas, where floods with storms frequently cause serious damage and problems for people.
Design/methodology/approach
Expert interviews are conducted to identify the study variables. Based on bills of quantities and project documents, historical data on residential construction projects in flood-prone areas are collected. Pearson correlation analysis is first used to check the correlations among the study variables. To overcome multicollinearity, principal component analysis is used. Then, stepwise multiple regression analysis is used to develop the cost prediction model. Finally, non-parametric bootstrap method is used to develop range estimation of the implementation cost.
Findings
A list of project-related variables, which could significantly affect implementation costs of residential construction projects in flood-prone areas, is identified. A model, which is developed based on an integration of principle component analysis and regression analysis, is robust. Regarding range estimation, 10, 50 and 90 percent cost estimates, which could provide information about the uncertainty levels in the estimates, are established. Furthermore, implementation cost contingencies which could show information about the variability in the estimates are determined for example case projects. Such information could be critical to cost-related management of residential construction projects in flood-prone areas.
Originality/value
This study attempts to predict implementation cost contingencies for residential construction projects in flood-prone areas using non-parametric bootstrap method. Such contingencies could be useful for project cost budgeting and/or effective cost management.
Details
Keywords
The purpose of the present study was to improve the fit of women’s bifurcated garments by developing an equation that can predict the crotch length accurately by using a few basic…
Abstract
Purpose
The purpose of the present study was to improve the fit of women’s bifurcated garments by developing an equation that can predict the crotch length accurately by using a few basic body measurements. This equation could provide a simple mass-customization approach to the design of bifurcated garments.
Design/methodology/approach
Demographic characteristics and easy-to-record body measurements available in the size USA database were used to predict the crotch length. Different methodologies including best subset regression, lasso regression and principal components regression were experimented with to identify the most important predictor variables and establish a relationship between the significant predictors and crotch length.
Findings
The lasso regression model provided the highest accuracy, required only five body dimensions and dealt with multicollinearity. The preliminary pattern preparation and garment fit tests indicated that by utilizing the proposed equation, patterns of customized garments could be successfully altered to match the crotch length of the customer, thereby, improving the precision and efficiency of the pattern making process.
Originality/value
Crotch length is a crucial measurement as it determines bifurcated garment comfort as well as aesthetic fit. The crotch length is usually estimated arbitrarily based on non-scientific methods while drafting patterns, and this increases the likelihood of dissatisfaction with the fit of the lower-body garments. The present study suggested an algorithm that could predict crotch length with 90.53% accuracy using the body dimensions height, hips, waist height, knee height and arm length.
Details