Search results

We address the problem of selecting the common factors that are relevant for forecasting macroeconomic variables. In economic forecasting using diffusion indexes, the factors are ordered, according to their importance, in terms of relative variability, and are the same for each variable to predict, that is, the process of selecting the factors is not supervised by the predictand. We propose a simple and operational supervised method, based on selecting the factors on the basis of their significance in the regression of the predictand on the predictors. Given a potentially large number of predictors, we consider linear transformations obtained by principal components analysis. The orthogonality of the components implies that the standard t-statistics for the inclusion of a particular component are independent, and thus applying a selection procedure that takes into account the multiplicity of the hypotheses tests is both correct and computationally feasible. We focus on three main multiple testing procedures: Holm's sequential method, controlling the familywise error rate, the Benjamini–Hochberg method, controlling the false discovery rate, and a procedure for incorporating prior information on the ordering of the components, based on weighting the p-values according to the eigenvalues associated to the components. We compare the empirical performances of these methods with the classical diffusion index (DI) approach proposed by Stock and Watson, conducting a pseudo-real-time forecasting exercise, assessing the predictions of eight macroeconomic variables using factors extracted from an U.S. dataset consisting of 121 quarterly time series. The overall conclusion is that nature is tricky, but essentially benign: the information that is relevant for prediction is effectively condensed by the first few factors. However, variable selection, leading to exclude some of the low-order principal components, can lead to a sizable improvement in forecasting in specific cases. Only in one instance, real personal income, we were able to detect a significant contribution from high-order components.

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.

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.

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.

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.

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.

This paper aims to develop a multivariate model that will be applicable to the Nigeria construction industry.

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.

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.

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.

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.

This chapter aims to examine the influence of governance on entrepreneurship in several countries, members of the European Union, in 2012–2017. The selection of the countries was based on human development index and expected years of schooling criteria, thus considering several sustainable development goals, involving the governments’ roles, the private sector, civil society, and citizens. The empirical analysis consisted of correlations, principal component analysis, and regression models. The Pearson correlation coefficient evidenced a series of negative relationships, statistically significant, between the governance indicators and business demography. The principal component analysis returned two main components for our database: the main one incorporates five governance proxies (control of corruption, rule of law, regulatory framework, government effectiveness, and political stability), while the second component is based on the voice and accountability. Therefore, the first governance component is more related to the public sector, while the second one reflects the involvement of civil society. The regression analysis considered besides the ordinary least squares model, the fixed effects and random effects model to emphasize whether or not differences across countries would impact the regression results. Several entrepreneurship variables were employed as dependent variables: business demography, high growth enterprise rates by employment, employer enterprise net growth, and business demography by size class. The consistent regression results emphasized an indirect impact from public governance toward high growth enterprise rates by employment and employer enterprise net growth. Based on our findings, the main conclusion is that public policies do not support entrepreneurship or the national context for entrepreneurs’ development. Moreover, the citizens’ involvement and their opportunities to participate in public decisions in terms of supporting entrepreneurship are also limited.

Aim: This chapter aims to examine the connection between government policies and entrepreneurial dimensions present in 13 European Union member countries, over the period 2002–2019. As long as the policies represent a set of decisions and actions issued by state-run structures, bodies with political, legislative, and financial authority to act to deal with a matter of public interest, this study overviews how intervention channels and policy instruments act upon supporting entrepreneurship.

Method: The methodology employed consists of correlations, principal component analysis (PCA), and regression models, in order to emphasise the statistically significant relationships between governance indicators and several entrepreneurial dimensions (financing for entrepreneurs, taxes and bureaucracy, basic school entrepreneurial education and training), and also the robustness of the results.

Results and Discussion: After observing the correlations evidencing strong relationships between the governance indicators, the results from PCA returned two main components for the Worldwide Governance Indicators: one incorporates the direct effect of control of corruption, government effectiveness, voice and accountability, regulatory quality, and rule of law, while the second component is based on political stability and absence of violence/terrorism factor. Results proved that governance has a significant impact on the financing available for entrepreneurs, especially from the first principal component, while taxes and regulations applied to new businesses have more impact in supporting entrepreneurship in countries with lower political stability levels. The consistent regression results emphasised that entrepreneurs feel more support from an institutional environment and more financing opportunities in an economy characterised by good governance, and taxes and regulations applied to new businesses have more impact in supporting entrepreneurship in countries with lower political stability levels.

Originality/Value: This study contributes to the literature studying the role of government policies on economic growth, by bringing more insights on the governance aspects and policies which are more favourable to productive entrepreneurship.

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.

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.

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.

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.

The purpose of this paper is to identify significant factors of environmental variables and pollutants that have an effect on PM_2.5 through wavelet and regression analysis.

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 PM_2.5 as a dependent variable.

It is found that few pollutants such as NO₂, NO_x, SO₂, benzene and environmental factors such as ambient temperature, solar radiation and wind direction affect PM_2.5. The regression model developed has high R² value of 91.9 percent, and the residues are stationary and not correlated indicating a sound model.

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 PM_2.5.

Control measures such as control charts can be implemented for significant factors.

Rules and regulations can be made more stringent on the factors.

The originality of this paper lies in the integration of wavelets with regression analysis for air pollution data.

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.

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.

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.

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.

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.

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.

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.

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.