Search

The changes that are constantly occurring in the labour sector have led organisations and companies to move towards digital transformation. This process was accelerated by the COVID-19 pandemic and conducted to a massive recourse to the practice of remote working, which in this study is understood as the term for the way of performing work outside the usual workplace and with the support of ICT. Currently, there are no flexible scales in the literature that allow measuring the benefits and disadvantages of remote working with a single instrument. Thus, the distinction between the positive and negative consequences of working remotely, substantiated by a solid literature, provides a framework for a systematical understanding of the issue. The aim of the present study is to develop and validate a scale on remote working benefits and disadvantages (RW-B&D scale). For this end, a preliminary Exploratory Factor Analysis (EFA) with 304 participants, a tailored EFA with a sample of 301 workers and a Confirmatory Factor Analysis (CFA) with 677 workers were conducted. Participants were all Italian employees who worked remotely during the period of the COVID-19 health emergency. Data were collected between October 2020 and April 2021. The psychometric robustness of the model was assessed through bootstrap validation (5000 resamples), fit indices testing and measurement of factorial invariance. The statistical analyses demonstrated the bifactorial nature of the scale, supporting the research hypothesis. The model showed good fit indices, bootstrap validation reported statistically significant saturations, good reliability indices, and convergent and discriminant validity. Measurement invariance was tested for gender and organisational sector. The results suggested that the novel scale facilitates the quantitative measurement of the benefits and disadvantages associated with remote working in empirical terms. For this reason, it could be a streamlined and psychometrically valid instrument to identify the potential difficulties arising from remote working and, at the same time, the positive aspects that can be implemented to improve organisational well-being.

The topic of community resilience attracts as much academic research as it does social media. Understanding the drivers of change and community adaptation in the face of critical events is a key clue to governance actions and local measures. However, both academia and the media often provide partial definitions of community resilience. Beginning with an integration of theory-driven and data-driven knowledge, the study aims to uncover and operationalize the building blocks of community resilience potential within a measurement tool. An assessment study, conducted on 1278 participants from diverse communities statistically supported a broad, inclusive model: Community Resilience Potential is composed of four main constituents (social capital, community competence, structural-functional potential, socio-economic potential). The Confirmatory Composite Analysis formalized for Partial Least-Squares Structural Equation Modeling revealed its good psychometric properties and measurement invariance. Although the study has limitations, it provides researchers with a valuable, theoretically grounded, widely-applicable tool for the investigation of the community resilience potential.

The present paper offers a new extension to the Ishita distribution called Size-Biased Ishia distribution (SBID). Various structural statistical properties of this distribution are derived such as the jth moment, moment generating function, the coefficients of variation, skewness and kurtosis. Also, the distribution of order statistics, harmonic mean, mode, reliability analysis, maximum likelihood estimation are provided, as well as the Fisher’s information, generalized and Renyi entropies are derived. The main advantage of using sized-based distributions appears when the sample are recorded with unequal probabilities. Accordingly, the superiority of the SBI distribution is illustrated to ball bearings data. It is shown that the SBID is the most appropriate model for this data set as compared to Rama distribution, Ishita distribution and Marshall–Olkin Esscher Transformed Laplace distribution. We believe that the SBID is an alternative distribution to lifetime data analysis.

The focus of this paper is on spatial structural equation models (S-SEM) also extended to a Panel data framework. More specifically, our objective is to introduce a generalized maximum entropy formulation for the class of S-SEM with the aim of developing a composite index. We present an application of the method to real data finalized to investigate dynamics and complex interactions between some selected dimensions that represent the main measures of intangible assets for a panel of OECD countries over the period 1998–2008.

A common situation in the analysis of latent constructs is the availability of external information about the data which could affect the model parameters’ estimation. In this paper a procedure for isolating these information based on the orthogonal projectors in the frame of second order PLS-PM is presented. An application to a case study in the field of the measurement of the subjective quality of work will show the way of functioning and the results obtained from the proposed procedure.

We use the generalized maximum entropy (GME) estimator to take into account the measurement error in the regression model with a composite indicator, Likert-type scales based, as explanatory variable. We show that, the reliability measure of the observed composite indicator can be used to define an estimator of the error variance and the supports required by the GME approach. As well as to obtain an estimate of the slope parameter of the model, that has statistical properties similar to the classical ordinary least squares adjusted for attenuation estimator, GME approach allows to estimate the measurement error that can be used to adjust the composite indicator of the latent explanatory variable. An extensive simulation and two case studies show the usefulness of this approach.

In this paper we present a crisp-input/fuzzy-output regression model based on the rationale of generalized maximum entropy (GME) method. The approach can be used in several situations in which one have to handle with particular problems, such as small samples, ill-posed design matrix (e.g., due to the multicollinearity), estimation problems with inequality constraints, etc. After having described the GME-fuzzy regression model, we consider an economic case study in which the features provided from GME approach are evaluated. Moreover, we also perform a sensitivity analysis on the main results of the case study in order to better evaluate some features of the model. Finally, some critical points are discussed together with suggestions for further works.