Nuova ricerca

Elvira PELLE

Professore Associato
Dipartimento di Comunicazione ed Economia

Home | Didattica |


Pubblicazioni

2022 - Digital Twins and Artificial Intelligence as Pillars of Personalized Learning Models [Articolo su rivista]
Furini, Marco; Gaggi, Ombretta; Mirri, Silvia; Montangero, Manuela; Pelle, Elvira; Poggi, Francesco; Prandi, Catia
abstract

Modern educational systems have not really evolved enough to meet the needs of modern students.21 No wonder, the percentage of dropouts from university studies is quite high (40% in the U.S. and 10% in Europe7,9). The university student profile has changed over the years. While yesterday's students were mainly full-time, today's students face challenges such as work commitments, family obligations, financial constraints, physical impairments, and learning models that do not adequately engage students or help them understand core concepts.11 One might think that this issue concerns only those who fail to complete their studies, but this is view is shortsighted. Today's educational system deficiencies will affect the welfare of tomorrow's society.

2022 - Support provided by elderly in Italy: a hierarchical analysis of ego networks controlling for alter–overlapping [Articolo su rivista]
Pelle, E.; Zaccarin, S.; Furfaro, E.; Rivellini, G.
abstract

Providing support outside the household can be considered an actual sign of an active social life for the elderly. Adopting an ego–network perspective, we study support Italian elders provide to kin or non–kin. More specifically, using Italian survey data, we build the ego–centered networks of social contacts elders entertain and the ego–networks of support elders provide to other non–cohabitant kin or non–kin. Since ego–network data are inherently multilevel, we use Bayesian multilevel models to analyze variation in support ties, controlling for the characteristics of elders and their contacts. This modeling strategy enables dealing with sparseness and alter–alter overlap in the ego support network data and to disentangle the effects related to the ego (the elder), the dyad ego–alter, the kind of support provided, as well as social contacts and contextual variables. The results suggest that the elderly in Italy who provide support outside their household — compared to all elders in the sample — are younger, healthier, more educated, and embedded in a more diversified ego–network of social contacts. The latter also conveys both the type and the recipient of the support, with the elderly who entertain few relationships with kin being more prone to provide aid to non–kin. Further, a “peer homophily” effect in directing elder support to a non–kin is also found.

2022 - The role of citation networks to explain academic promotions: an empirical analysis of the Italian national scientific qualification [Articolo su rivista]
Martini, Maria Cristiana; Pelle, Elvira; Poggi, Francesco; Sciandra, Andrea
abstract

2021 - A clustering procedure for mixed-type data to explore ego network typologies: an application to elderly people living alone in Italy [Working paper]
Pelle, Elvira; Pappadà, Roberta
abstract

2021 - A clustering procedure for mixed-type data to explore ego network typologies: an application to elderly people living alone in Italy [Articolo su rivista]
Pelle, Elvira; Pappadà, Roberta
abstract

2021 - Constructing personal networks in light of COVID-19 containment measures [Articolo su rivista]
Furfaro, Emanuela; Rivellini, Giulia; Pelle, Elvira; Zaccarin, Susanna
abstract

The policies for containing the spread of the SARS-CoV2 virus include a number of measures aimed at reducing physical contacts. In this paper, we explore the potential impact of such containment measures on social relations of both young adults and the elderly in Italy. We propose two ego-centered network definitions accounting for physical distance in light of the COVID-19 containment measures: the easy-to-reach network, that represents an accessible source of support that can be activate in case of new lockdown; the accustomed-to-reach network, which includes proximity and habit to meet in person. The approach used for constructing personal (ego-centered) networks on data from the most recent release of Families and Social Subject survey allows us to bring to the foreground people exposed to relational vulnerability. The analysis of the most vulnerable individuals by age, gender, and place of residence reveals that living alone is often associated with a condition of relational vulnerability for both the elderly and for young adults.

2021 - Ego-centered Support Networks: a Cross-national European Comparison [Relazione in Atti di Convegno]
Furfaro, Emanuela; Pelle, Elvira; Rivellini, Giulia; Zaccarin, Susanna
abstract

This contribution aims at comparing patterns of social support -provided and received- among the elderly population in European countries. Adopting an egocentered network perspective, by means of multivariate techniques for categorical data, we intend to map the ego-support network structures of the elderly, as well as ego-network functional content of provided and received support in the different countries. Individual and country socio-demographic characteristics will be also considered in interpreting results.

2021 - Item Count Technique in Ranked Set Sampling [Capitolo/Saggio]
Cobo, Beatriz; Pelle, Elvira
abstract

In situations where the estimation of the proportion of sensitive variables relies on the observations of real measurements that are difficult to obtain, there is a need to combine indirect questioning techniques. In the present work, the authors will focus on the item count technique, with alternative methods of sampling, such as the ranked set sampling. They are based on the idea proposed by Santiago et. al (2019), which combines the randomized response technique proposed by Warner together with ranked set sampling. The authors will carry out a simulation study to compare the item count technique under ranked set sampling and under simple random sampling without replacement.

2021 - Some evidences and applications of the randomized response crossed model in a survey of sensitive population behaviors [Articolo su rivista]
Pelle, Elvira; Perri, Pier Francesco
abstract

2020 - A clustering procedure for ego-network data: an application to Italian elders living in couple [Relazione in Atti di Convegno]
Pelle, Elvira; Pappadà, Roberta
abstract

The analysis of ego-network characteristics (especially size and composition) has become crucial in studying many aspects of everyday life. In this work, we propose a clustering procedure to find a partition of ego-networks into homogeneous groups according to their features. We use data from the “Family and Social Subjects” (FSS) survey conducted by the Italian National Statistical Institute in 2009, on elderly couples with both partners aged 65 years and more. Preliminary results show the suitability of our proposal to analyze this kind of ego-network data.

2018 - Estimating the size of regional innovation network through a capture-recapture approach [Articolo su rivista]
Pelle, Elvira; DE STEFANO, Domenico; Zaccarin, Susanna
abstract

The effectiveness of inter-organizational collaboration rely on several factors, among which the composition of cooperation participants (partners in the inter-organizational network) and the number of cooperation participants (size of the network) play an important role. Thus, it is crucial to have a reliable estimate of the number of alters and the composition of collaboration networks. This task can be viewed as a particular case of hard-to-reach population estimation. In this work, we propose an adaptation of capture-recapture approach to estimate the number of actors in the personal networks of firms participating in the POR-FESR 2007-2013 call in Friuli Venezia Giulia (a region in the north-east of Italy). The alters (other organizations, also not regionally bounded) they listed in their network before and after their participation to the call will be considered as the two lists on which the proposed capture-recapture approach is applied.

2018 - Improving mean estimation in ranked set sampling using the Rao regression-type estimator [Articolo su rivista]
Pelle, Elvira; Perri, Pier Francesco
abstract

Ranked set sampling is a statistical technique usually used for a variable of interest that may be difficult or expensive to measure, but whose units are simple to rank according to a cheap sorting criterion. In this paper, we revisit the Rao regression-type estimator in the context of the ranked set sampling. The expression of the minimum mean squared error is given and a comparative study, based on simulated and real data, is carried out to clearly show that the considered estimator outperforms some competitive estimators discussed in the recent literature.

2018 - Support provided by elderly Italian people: a multilevel analysis [Relazione in Atti di Convegno]
Pelle, Elvira; Rivellini, Giulia; Zaccarin, Susanna
abstract

The characteristics of social networks determine the availability of social support, that is the aid individuals gain from their network members. Despite the literature usually investigate the importance of having support, the role of the support provided to alters had not yet received the same attention. In particular, the support elderly provide to their networks members shows an active participation in the social life, that is one dimension of the active ageing. Using data from 2009 edition of “Famiglia e Soggetti Sociali (FSS)” survey carried out by the Italian National Statistical Institute, we propose a Bayesian multilevel model to highlight the determinants of observing a provided support tie by elders to family or non-family members.

2017 - A multidimensional Rasch model for multiple system estimation where the number of lists changes over time [Capitolo/Saggio]
Pelle, Elvira; Hessen, David J.; van der Heijden, Peter G. M.
abstract

This chapter discusses the estimation of the population size in a capture-recapture context using the log-linear multidimensional Rasch model. This model can be used in those situations with two or more incomplete and overlapping lists of cases available from different sources. Under the assumption that lists can be viewed as indicators of the latent variables which account for correlations among lists it is shown how the probability of a generic capture profile can be easily expressed in a log-linear form. The model is discussed either in the case with or without a stratifying variable is available. The chapter also shows how the proposed model can be performed when lists refer to different populations (e.g. different periods of time or regions). In such cases, lists that are not observed are assumed to be missing and the EM algorithm is used to estimate the missing values. Finally, an application to real data set on children born with a neural tube defect in the Netherlands during the years 1988 through 1998 is presented and results on the yearly estimates of the incidence of spina bifida are discussed.

2017 - Estimating the size of regional innovation network through a capture-recapture approach [Abstract in Atti di Convegno]
Pelle, Elvira; De Stefano, Domenico; Zaccarin, Susanna
abstract

In recent years a relevant issue in the analysis of regional innovation policies supporting collaboration between firms and other organizations (e.g.: other firms, universities, research centres, etc.) is to evaluate the impact of such policies on the personal network of the targeted firms in a given region. To deal with this issue, it becomes of primary importance to have a reliable estimates of the size of innovation networks. In this work, we propose a novel use of capture-recapture approach to estimate the size and the composition of the personal networks of firms involved in regional innovation networks. Capturerecapture is a statistical method widely used to estimate the size of hidden population using two or more samples drawn from the population. The number of individuals observed in a sample and the number of those observed in both samples is used to estimate the number of those not selected in any sample. The method can be also used if two or more incomplete and overlapping lists of ascertained cases from different sources are available. We apply the proposed method on data from a survey conducted on a sample of 536 companies located in Friuli Venezia Giulia (a region in the north-east of Italy) who participated in the POR-FESR 2007-2013 call, named “Innovation, research, technology transfer and entrepreneurship”. The collaboration ties they claimed to entertain with other organizations (also not regionally bounded) before and after their participation to the call will be considered as the two lists on which the proposed capture-recapture approach is applied. The idea is to account for unobserved ties (and thus to estimate the network size of companies) using the number of ties observed only before or only after the participation to the call and the number of ties common to both.

2017 - Le reti di collaborazione per l'innovazione. Indagine sulle imprese partecipanti ai bandi europei per ricerca, sviluppo e innovazione (POR-FESR 2007/2013) in Friuli Venezia Giulia – Misura 1.1.a [Capitolo/Saggio]
Capellari, Saveria; Pelle, Elvira; Zaccarin, Susanna
abstract

Il lavoro presenta i risultati di un’indagine rivolta alle imprese partecipanti ai bandi europei per l’innovazione della regione Friuli Venezia Giulia, volta ad indagare le caratteristiche delle collaborazioni avviate dalle imprese con università, centri di ricerca ed altre imprese per la realizzazione di attività di ricerca, sviluppo e innovazione. È noto, infatti che la collaborazione rappresenta un elemento chiave per l'attivazione di processi di innovazione e di sviluppo del sistema produttivo. Obiettivo del presente lavoro è quello di contribuire alla riflessione scientifica, nazionale e internazionale, sul tema degli effetti degli incentivi alla collaborazione, offrendo al contempo all’Amministrazione Regionale elementi di conoscenza utili per la programmazione dei nuovi interventi Horizon 2020, nei quali l’incentivazione della collaborazione resta uno dei pilastri della politica regionale a favore dell’innovazione. L’indagine è stata rivolta alle imprese che hanno partecipato ai bandi POR FESR 2007-2013 - Asse 1 “Innovazione, ricerca, trasferimento tecnologico e innovazione” della Regione Friuli Venezia Giulia. Il questionario è originale e pensato per osservare il cambiamento nel tempo del comportamento delle imprese. I risultati ottenuti permettono di evidenziare alcuni aspetti del comportamento delle imprese oggetto di indagine, con particolare riferimento alle caratteristiche e all’evoluzione delle attività innovative poste in essere nel corso del periodo considerato.

2016 - A log-linear multidimensional Rasch model for capture-recapture [Articolo su rivista]
Pelle, E.; Hessen, D. J.; van der Heijden, P. G. M.
abstract

In this paper, a log-linear multidimensional Rasch model is proposed for capture-recapture analysis of registration data. In the model, heterogeneity of capture probabilities is taken into account, and registrations are viewed as dichotomously scored indicators of one or more latent variables that can account for correlations among registrations. It is shown how the probability of a generic capture profile is expressed under the log-linear multidimensional Rasch model and how the parameters of the traditional log-linear model are derived from those of the log-linear multidimensional Rasch model. Finally, an application of the model to neural tube defects data is presented.

2016 - Estimating Induced Abortion and Foreign Irregular Presence Using the Randomized Response Crossed Model [Articolo su rivista]
Perri, Pier Francesco; Pelle, Elvira; Stranges, Manuela
abstract

We present the theoretical framework and the results of a pilot survey conducted in Calabria, a region in the south of Italy, to investigate the prevalence of two sensitive characteristics, namely induced abortion among foreign women residing in this region, and irregular immigrant status. Collecting data on these two attributes by means of traditional survey modes typically produces underestimates of the diffusion of the phenomena due to the stigmatizing nature of the investigated topics. In order to overcome this problem, we employ an alternative data collection method known as the Randomized Response Technique. In particular, we focus on the implementation of the crossed model recently proposed by Lee et al. (Stat Probab Lett 83:399–409, 2013) to estimate two sensitive characteristics and some related measures of association.

2016 - The Rao regression-type estimator in ranked set sampling [Relazione in Atti di Convegno]
Pelle, Elvira; Perri, Pier Francesco
abstract

We revisit the Rao regression-type estimator in the context of the ranked set sampling. The expression of the minimum mean squared error is obtained and a simulation study is carried out to evaluate the gain of efficiency of the considered estimator upon some competitive estimators.

2014 - Log-linear multidimensional Rasch model for capture-recapture [Relazione in Atti di Convegno]
Pelle, Elvira; Hessen, David J.; Peter G. M., Van der Heijden
abstract

The traditional capture-recapture method assumes homogeneity of the capture probabilities. However, dierences of character or behaviour between individuals may occur and models that allow for varying susceptibility to capture over individuals and unequal catchability have been proposed and psychometric models, such as the Rasch model, were successfully applied. In the present work, we propose the use of the multidimensional Rasch model in the capture-recapture context. We assume that lists may be divided into two or more subgroups, such that they can be viewed as indicators of the latent variables which account for correlations among lists. We show how to express the probability of a generic capture prole in terms of log-linear multidimensional Rasch model and apply the methodology to a real data set.