In this paper we present a method to evaluate the quality of a rater’s judgement, which can integrate and enrich the use of inter-rater agreement as a reliability measure. Our proposal is an integrative one and evaluates the quality of a rater’s performance through an analysis of the profile of that individual rater’s performance. We discuss its rationale on the basis of the interpretation of inter-rater agreement, highlighting some critical issues. For this purpose, we adopt a computational model based on fuzzy set theory, demonstrating its main characteristics with an exemplary case study.

Fuzzy statistics provides useful techniques for handling real situations which are affected by vagueness and imprecision. Several fuzzy statistical techniques (e.g., fuzzy regression, fuzzy principal component analysis, fuzzy clustering) have been developed over the years. Among these, fuzzy regression can be considered an important tool for modeling the relation between a dependent variable and a set of inde- pendent variables in order to evaluate how the independent variables explain the empirical data which are modeled through the regression system. In general, the standard fuzzy least squares method has been used in these situations. However, several applicative contexts, such as for example, analysis with small samples and short and fat matrices, violation of distributional assumptions, matrices affected by multicollinearity (ill-posed problems), may show more complex situations which cannot successfully be solved by the fuzzy least squares. In all these cases, different estimation methods should instead be preferred. In this paper we address the problem of estimating fuzzy regression models characterized by ill-posed features. We introduce a novel fuzzy regression framework based on the Generalized Maxi- mum Entropy (GME) estimation method. Finally, in order to better highlight some characteristics of the proposed method, we perform two Monte Carlo experiments and we analyze a real case study.

The aim of this paper is to analyze a Job Satisfaction (JS) model by using an information theoretic approach based on the semi-parametric Generalized Maximum Entropy (GME) estimator. The GME is used in order to estimate the parameters of the Structural Equation Model (SEM), which represents the theoretical representation of the relationships between the human being and his job. Moreover, thanks to the entropy index measure, the theoretical model is analyzed in its some particular aspects, which can be seen as sub-structures in the relationships.

The authors propose a method for analyzing the psychotherapy process: discourse flow analysis (DFA). DFA is a technique representing the verbal interaction between therapist and patient as a discourse network, aimed at measuring the therapist- patient discourse ability to generate new meanings through time. DFA assumes that the main function of psychotherapy is to produce semiotic novelty. DFA is applied to the verbatim transcript of the psychotherapy. It defines the main meanings active within the therapeutic discourse by means of the combined use of text analysis and statistical techniques. Subsequently, it represents the dynamic interconnections among these meanings in terms of a ‘‘discursive network.’’ The dynamic and structural indexes of the discursive network have been shown to provide a valid representation of the patient-therapist communicative flow as well as an estimation of its clinical quality. Finally, a neural network is designed specifically to identify patterns of functioning of the discursive network and to verify the clinical validity of these patterns in terms of their association with specific phases of the psychotherapy process. An application of the DFA to a case of psychotherapy is provided to illustrate the method and the kinds of results it produces.

In this paper, a study on 40 semi-structured interviews with users of the Italian health services and self-help groups is presented to gain a deeper insight on how members describe, understand, and face their problems with substance or behavioral addiction. A simple correspondence analysis (CA) was applied to the transcripts of the interviews to detect the main dimensions of sense which organize the users’ discourse about their problem and their request for help. In addition, constraint correspondence analysis (CCA) was applied to evaluate whether these dimensions are affected by the kind of help context the users belong to, type of addiction, age, and gender. No substantial differences emerged from CA and CCA. Results show that the users’ discourses focus on two different kinds of experience: the substance or gambling problem and the experience of being helped. Furthermore, dis/similarity in the user discourses concerns the way of symbolizing the problem motivating the request for help, identified with the addiction or with the breakup of one’s family and social relationships. Through the interviews, a view of addiction as a disorder affects the way users define their problem and define the goal of the treatment.

The concept and the mathematical properties of entropy play an im- portant role in statistics, cybernetics and information sciences. Indeed many al- gorithms and statistical data processing tools, with a wide range of targets and scopes, have been designed based on entropy. The paper describes two estima- tors inspired by the concept of entropy that allow to robustly cope with multi- collinearity, in one case, and outliers, in the other. The Generalized Maximum Entropy (GME) estimator optimizes the Shannon’s entropy function subject to consistency and normality constraints. In regression applications GME allows, for example, to estimate model coefficients in the presence of multicollinearity. The Least Entropy-Like (LEL) estimator is a novel prediction error model co- efficient identification algorithm that minimizes a nonlinear cost function of the fitting residuals. As the cost function that is minimized shares the same mathe- matical properties of entropy, it allows to compute an estimate of the model co- efficients corresponding to a positively skewed distribution of the residuals. The resulting estimator exhibits higher robustness to outliers with respect to standard, as ordinary least squares (OLS) model coefficient approaches. Both the GME and LEL estimation methods are applied to a common case study to illustrate their respective properties.

The aim of the paper is to present a Partial Least Squares Path Modeling based on high-order latent variables to analyze the concept of General Distress. In order to depict General Distress concept, two approaches to second order construct modeling are presented and compared: the repeated indicators and the two-step approach. It is shown how to implement the two estimation approaches and a comparative study is proposed.

The objective of this paper is to develop a GME formulation for the class of spatial structural equations models (S-SEM). In this respect, two innovatory as- pects are introduced: (i) the formalization of the GME estimation approach for the spatial structural equations models which accounts for spatial heterogeneity and spa- tial dependence; (ii) the extension of the methodology to a panel data framework. We also present an application of the method to real data finalized to investigate dispari- ties of unemployment rates in OECD countries over the period 1998-2006.

La ricerca sul ruolo dei sostenitori nell’ambito del Sostegno a Distanza (SaD) na- sce dalla collaborazione tra l’Università del Salento e La Gabbianella Onlus di Roma, come proseguimento del Censimento nazionale sul SaD del 2008 (Ciavolino et al., 2008). L’idea è nata dall’ipotesi che l’atto del sostegno a distanza, può essere visto co- me un processo unico di erogazione del servizio, che parte dal sostenitore ed, attra- verso gli Enti SaD, arriva al beneficiario. L’obiettivo di questo contributo è presentare i risultati dell’indagine pilota sul ruo- lo dei sostenitori nell’ambito del SaD. La struttura del lavoro, si articola secondo i seguenti punti: studiare le percezio- ni e le aspettative dei sostenitori italiani; definire un profilo medio comportamenta- le, attraverso l’utilizzo dei dati socio-anagrafici, dei sostenitori; indagare le motiva- zioni di sostegno e le diffidenze verso il SAD attraverso le percezioni e le impressio- ni di chi scelto di compiere tale gesto; valutare il livello di soddisfazione dei sosteni- tori e quali sono le caratteristiche che devono essere migliorate, in modo da definire possibili miglioramenti nel rapporto tra l’ente e il sostenitore e di conseguenza ver- so il beneficiario.

This paper presents a review of the original method recently developed by the authors with the Generalized Maximum Entropy (GME) estimator for the simple linear Measurement Error Model (MEM) and the Structural Equation Model (SEM). In socio-economic research, these two models often concern subjective or psychological variables (composite indicators), and represent relations between latent variables. In this review, two applications to the statistical modelling of economic perception and job satisfaction are presented.

The current paper aims to present the method of Non-Symmetrical Correspondence Analysis (NSCA) based on Emerson’s orthogonal polynomials, which takes into account, in efficient way, the ordinal structure of the data. The extension of NSCA is the so called Singly Ordered Non-Symmetrical Cor- respondence Analysis version (SONSCA), that, by taking into account the ordinal structure in the ta- ble, improving the interpretation ability of the analysis. The methods was applied to 40 in-depth in- terviews, gathered with people in treatment for their problems with addiction. NSCA and SONSCA are used to evaluate if the classes of age of the subjects interviewed influence the addiction thematic categories that characterize their discourses.The work provides insight on NSCA and SONSCA methods and how they could be applied in the psychological context and in particular to study the dependence between ordinal and categorical variables reported in a contingency table.

The non-indigenous hydrozoan Clytia hummelincki, recorded for the first time in the Mediterranean Sea in 1996, has now become established on barren grounds where conditions of low diversity, high grazing pressure and low levels of competition occur. The mechanisms of persistence of this species, as well as its population dynamics in this habitat and in species-rich, algae-dominated shallow rocky communities were investigated in situ at four sampling sites in the Northern Ionian Sea from October 2012 to September 2014. Multivariate analyses were conducted to assess the differences in population dynamics of this species in both contrasting habitats. Clytia hummelincki reached peak abundance during summer, with numerous reproductive structures observed in August and September. A remarkable regression period was evident in the cold season, when colonies were largely reduced to dormant tissue in the coenosarc of the hydrorhiza and were often covered by encrusting algae. Both regeneration of colonies from resting hydrorhizae and recruitment of new planulae are involved in the maintenance of the populations. Colonies regrew from hydrorhizae less than half of the time. Population dynamics in sea-urchin barren grounds and algae-dominated communities did not differ significantly, suggesting that populations of this hydrozoan are now well established in the central Mediterranean Sea. This species is no longer confined to low diversity, highly grazed, low competition environments.

The aim of the paper is to present a study on the high-order latent variables for the partial least squares path modelling (PLS-PM). A Monte Carlo simulation study is proposed for comparing the performances of the two best-known methods for modelling higher-order constructs, namely the repeated indicators and the two-step approaches. The simulation results, far from covering all the potential uses of the two approaches, could provide some useful suggestions to those researchers who are intending to introduce a further level of abstraction in modelling the phenomenon of interest. An illustrative case study on the job satisfaction is reported in order to show how theoretical and statistical instances have to be taken into consideration when modelling higher-order constructs.

Local development, inter-municipal cooperation, proximity. The case of Apulia.- The phenomena of organized proximity observed in Puglia show two important aspects: the objectives and strategies do not involve significant discontinuities; the partnerships tend to be relatively stable over time, but they present important (and potentially conflicting) overlappings in space. The forms of organized proximity detected have probably led to a depletion of development projects, but they also increased the availability of local actors to cooperate.

Il contributo dimostra attraverso l'utilizzo di un modello statistico che le performance degli Atenei sono determinate dal contesto territoriale di appartenenza. Tale dimostrazione consente agli autori di sottolineare i rischi insiti nell'attuale modello di finanziamento delle Università che, come oggi delineati, rischiano di accrescere i processi di divergenza territoriale.

For several years it has become the practice of Public Administration quality assessment as part of the institutional activities carried out by offices to improve public services by monitoring the produc- tion process. The Ministry of Labour and Social Policies has adopted a system of ‘‘quality assess- ment’’ based on indicators selected as representative of the inspection carried out in decentralized offices. This scoring system – called Project Quality – is defined by three ‘‘synthetic indicators’’ de- termined periodically by the 92 Provincial Labour Directorates (in Italian: Direzioni Provinciali del Lavoro – DPL) operating in the country. It does indeed have a rating system that defines a ranking between the offices. This paper presents the results of the research in order to analytically describe the performance level with a different model and also suggesting the possible influence exerted by the ‘‘local context variables’’, i.e., those relating to the geo-socio-economic differentials, in explain- ing the efficiency of inspection. The data are analyzed according to the variable inspection and lo- cal was formalized through a second-order structural equations model.

L’obiettivo di questo progetto è stato la raccolta di dati sul fenomeno del Sostegno a Distanza (SAD) per una successiva analisi con tecniche statistiche descrittive e multidimen- sionali in modo da ottenere una visione analitica del fenomeno SAD sul territorio italiano. La raccolta dati ha rappresentato un momento strategico per la lettura del fenomeno in quan- to ha consentito di conoscere il numero degli Enti che operano nel settore e mediante l’ana- lisi delle loro caratteristiche, opinioni ed esigenze, è stato possibile delineare un quadro ge- nerale della situazione italiana, definendo le relazioni con gli attori coinvolti (beneficiari e so- stenitori) e il confronto con gli Enti pubblici e con la società. I risultati della ricerca danno una visione statisticamente rappresentativa del SAD, in mo- do da consentire una maggiore e più consapevole diffusione del fenomeno, delineandone con maggiore precisione i punti di forza e di debolezza del fenomeno e anche i luoghi e le moda- lità di intervento sui territori dei paesi in cui gli Enti operano. La raccolta dei dati è avvenuta nel 2007 e fa riferimento all’anno 2006. Lo strumento di rilevazione è stato un questionario elettronico con autocodifica delle mo- dalità di risposta inviato tramite email, il quale ha consentito una notevole riduzione dei co- sti e dei tempi della ricerca. Questo contributo contiene anche gli interventi dei partecipanti al seminario organizzato da La Gabbianella: “IL SOSTEGNO A DISTANZA, UN ATTO DI GIUSTIZIA?”

We develope a multigroup structural equation model (SEM) based on the generalized maximum entropy (GME) estimator, allowing integration with Rasch Analysis. The proposed method can simplify the development of the final model, with more control on the statistical properties of the manifest variables (with the Rasch Analysis) and integrating the obtained measures in the multigroup SEM by using GME estimator.

The aim of this paper is to define a new approach, called Hybrid Two-Step, to estimate the parameters of a second-order latent variable (LV) model in the case of formative relationships between the first-order and the second-order LVs. In this respect, we introduce the two main approaches to the estimation of second-order constructs through the partial least squares-path modelling: the so-called Repeated Indicators approach and the Two-Step approach. Some criticisms of these methodologies are highlighted and a solution to the issue of the identification of formative second-order constructs is suggested through the adoption of a Hybrid Two-Step approach. A Monte Carlo simulation study aimed at comparing the approach proposed with the traditional ones was performed. Finally, a case study about the passenger satisfaction is presented to show the implementation of the method and to give some comparative empirical results.

Atti conclusivi del progetto We the Young People of Europe finanziato da Erasmus Plus, in collaborazione con l'APS Demostene, la University of Coventry, Laazarsky University of Warsaw