1,721,089 research outputs found
Metodi e problemi di identificazione tra modelli bancari nel caso della banca mista italiana e della banca universale tedesca all’inizio del XX secolo
No full textConfidence regions for optimal sensitivity and specificity of a diagnostic test
Full text linkWe propose new methods that provide approximate joint confidence regions for the optimal sensitivity and specificity of a diagnostic test, fixed by the Youden index criterion. Such methods are semiparametric and overcome limitations of alternative approaches available in the literature. Our proposal is based on empirical likelihood pivots and covers two situations: binormal model and binormal model after the use of Box-Cox transformations. In the last case, we show how to use two different transformations, for the healthy and the diseased subjects
Introduction to "Statistical Methods for the Evaluation of Educational Services and Quality of Products", Chapter 1
No full textThe evaluation of educational services, as well the analysis of judgements and preferences, poses several methodological challenges because of one or more aspects: the observational nature of the context, the hierarchical structure of the data, the multivariate and qualitative nature of the dependent variables, the presence of non observable factors, an so on. These circumstances strongly ask for the introduction of mixture models and this contribution surveys the main problems and issues related to statistical and computational point of views
Does joining to groups or Facebook pages help students’ retention within the first university year?
No full textUsing observational data, the aim of this paper is to investigate whether university students’ dropout within the first year is influenced by participation into groups or Facebook pages run by other students. Specifically, in this study such participation is considered a treatment condition and represents an extensive concept of student engagement, which can promote or strengthen social relationships among
students. Given non-random treatment assignment, analysis was carried out by using propensity score matching in order to correct for selection bias due to a set of observable pre-treatment variables. Several matching techniques are used and the results were compared. Survey data were collected on a sample of students enrolled in a large Italian university
Predictive performance comparisons of different feature extraction methods in a financial column corpus
Full text linkQuesto contributo riguarda il trattamento di un corpus costituito da una rubrica finanziaria settimanale. In particolare, ci siamo concentrati sull'estrazione di indici a livello di documento e sull'estrazione di variabili testuali. Inoltre, abbiamo confrontato alcuni metodi di estrazione delle variabili per valutare la loro capacità predittiva. I risultati confermano l'ipotesi che i vettori derivati dal word embedding non migliorano la capacità predittiva rispetto ad altri metodi di estrazione delle variabili, ma restano una risorsa fondamentale per cogliere la semantica nei testi.This work concerns the processing of a corpus made up of a financial weekly column. Specifically, we focused on document-level index extraction and textual feature extraction. Moreover, some feature extraction methods had been compared to evaluate their predictive capacity. Results confirm the hypothesis that vectors derived from word embedding do not improve the predictive power compared to other feature extraction methods but remain a fundamental resource for capturing semantics in texts
Performance evaluation of Italian Firms in the last decade: a Latent Growth Models approach.
No full textIn Italy, the crisis period (from 2008 to 2014) was characterized by a deep negative conjuncture until 2009 and by a slight recovery until the first half of 2011, and from 2011 to 2014 by an intense recession. The aim of this work is to collect evidence on the riskiness trends of Italian manufacturing system with the following goals: to calculate the main financial ratios related to firms’ riskiness and distress
risk trend by means of the book-value data; to detect the guide-variables outlining the firms’ riskiness and distress risk trend in the period 2008-2017. A Latent Growth Curve Model is proposed to analyse riskiness by using an important Italian private database containing the book-value data of the joint-stock company Italian firms
Bias correction of the maximum likelihood estimator for Emax model at the interim analysis
No full textThe Emax model is a dose-response model commonly applied in clinical trials, agriculture and environmental experiments. We consider a two-stage adaptive design for collecting \lq\lq optimal" data for estimating the model parameters. At the first stage (interim analysis) a locally D-optimum design is computed to get a sample of independent observations and to produce a first-stage maximum likelihood estimate (MLE). At the second stage, the first-stage MLE is used as initial parameter-value to determine another D-optimum design and then to collect the second-stage observations.\\ %(which depend on the responses observed at the first stage). \\
The first-stage estimate influences the quality of the data gathered at the second stage, where a large number of observations can be collected. In real life problems, instead, the sample size of the interim analysis is usually small; therefore, the first-stage MLE should be precise enough even if based on few data. From this consideration, our guess is that if we improved the behaviour of the first-stage MLE through a bias correction, then the D-optimal design determined at the second stage would produce better experimental points.
In this study we provide the analytic expression of the first-order bias correction of the MLE in the Emax model
The evaluation of heat vulnerability in Friuli Venezia Giulia
No full textHeat waves are leading cause of weather-related illness and death, in a context where their frequency, intensity and impact are expected to surge due to rising climate change, growing urbanisation and population ageing. This work develops a Heat Vulnerability Index by means of the composite indicator methodology with the aimto depict heat vulnerability in Friuli Venezia Giulia atthe census tract level. The results show that heat vulnerability follows a spatial pattern with highest hazard in urban areas, lower risk in rural areas and lowest danger in mountainous areas. The performance interval approach is exploited to validate the Index
A contribution to the L. J. Savage problem
No full textThe aim of this contribution is to provide an answer, from a subjective Bayesian perspective, to the conceptual problem proposed in 1959 by Leonard Jim- mie Savage. For this purpose we propose to apply the Bayesian Discrepancy Mea- sure, which is a new evidence measure recently introduced in the literature
- …
