1,721,023 research outputs found
Approcci multilineari e inferenziali all’analisi fattoriale di matrici a tre indici
No full textSome models for three-mode component and three-mode factor analysis are compared focalizing on their exploratory capabilities. In particular, a statistica! reformulation of the PARAllel FACtor analysis mode! (PARAFAC) is proposed pointing out the advantages in the factorial interpretation and proving some properties of factorial uniqueness. The advantages will be also illustrated by an example taken from the child development literature
Un metodo per l'analisi simultanea di più matrici di dati quadrate asimmetriche
No full textAlcuni metodi per il trattamento simultaneo di più matrici di dati quadrate asimmetriche sono stati in passato proposti nello Scaling Multidimens1onale e nell'Analisi Fattoriale. Tali metodi consentono di analizzare l'asimmetria per diversi tipi di dati (matrici di prossimità, tabelle di contingenza, ecc.) attraverso particolari modelli di distanza euclidea ponderata o in componenti principali, o anche con approcci non basati su rappresentazioni geometriche. Essi costituiscono delle generalizzazioni di metodi proposti per il trattamento di una singola matrice e si possono utilizzare con scopi prettamente esplorativi o anche successivamente a un'analisi di tipo confermativo per rappresentare graficamente le stime o i residui dei modelli statistici utilizzati (cfr. ad es. Bove, 1992 e Bove e Critchley, 1993 per il caso di una singola matrice). Un problema centrale per i metodi grafici è quello della difficoltà di analisi contemporanea delle diverse rappresentazioni fornite che spesso rende complessa la.ricostruzione dell'informazione presente nei dati. Il metodo che si propone in questo lavoro ha come principale obiettivo quello di fornire nuovi tipi di rappresentazioni grafiche dei dati sfruttando la decomposizione unica delle matrici quadrate nelle due componenti simmetrica ed emisimmetrica. ..
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Latent variable models to evaluate the final exam in the Italian lower secondary school
No full textRecently, the need for an objective way to assess student performance has quickly increased in the Italian educational system. The competence evaluation can be carried out by analyzing the results of a questionnaire containing a set of items. In this work, we analyze the results of a test on mathematics literacy administered to pupils attending the last year of lower secondary school. In particular, we compare different methods in the latent variable model framework
Some issues on robustness of regression trees
No full textRegression trees represent one of the most popular tools in predictive data mining applications. However, their performances severely degrade in the presence of highly-skewed and/or long-tailed error distributions, and especially for grossly mis-measured values of the dependent variable. In this paper, these issues are discussed from both a theoretical and a practical point of view, and some recent proposals to overcome these difficulties are presented
Interpreting air quality indices as random quantities
No full textSynthetic indices are a solution for condensing complex situations into a
single value: air quality indices are a very popular example. Statistics is helpful in
their construction, for summarizing multidimensional information. In this work, we
consider synthetic air quality indices as random quantities coming from asymmetric
distributions and investigate their main properties
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Detecting multiple cluster structures through model-based clustering methods
No full textIn cluster analysis it is generally assumed that one single cluster structure is contained in a data matrix, and that this structure may be confined to a subset of the observed variables. This paper investigates a new solution that simultaneously selects the relevant variables and discovers multiple cluster structures from possibly dependent subsets of variables. The basic idea is to recast the problem as a model comparison problem in which conditional independence assumptions are introduced using multivariate regression models with correlated and non-normal error terms. A
stepwise procedure for selecting a locally optimal model is also proposed. Results obtained from a Monte Carlo study are briefly described
- …
