Secondo fascicolo del 2014
CONTENTS
by Eugenio Brentari
pages: 1
Download
by Ignazio Drudi, Giorgio Tassinari
pages: 15
Download
Abstract ∨
This article uses data from the 2002-2010 waves of Bank of Italy Survey on Households Income and Wealth. It reports data on the evolution of the distribution of income by main households’ income sources and by households’ income rank and on the evolution of concentration indexes by the same characters. The decompositions of Theil and Gini indexes are used to assess if the changes in overall concentration are mainly driven by a deeping of inequality between groups or by increases of within groups concentration and of overlapping among groups distributions.
by Rosalia Castellano, Gennaro Punzo
pages: 19
Download
Abstract ∨
The paper deals with the effects of formal education on workers’ earnings comparatively for Germany, Italy and the United Kingdom, three countries of Western Europe with three alternative combinations of stratification/standardisation processes and vocational specificity in their education systems. The aim is to evaluate cross-country differences in returns on education along the conditional earnings distributions as well as their role in affecting the between-levels and within-levels inequality in light of institutional variety in the design of national education systems. Drawing upon 2005 EU-SILC data, a series of two-stage probit models with quantile regression (QR) in the second stage allows estimating Mincerian equations with sample selection by employment status (employees vs self-employed) and gender. In short, a clear contrast in terms of differentials in returns on education exists in favour of the highly stratified and more vocationally oriented system of Germany even though the gaps with Italy and the United Kingdom vary along the conditional earnings distributions.
by Antonio Frenda, Sergio Scippacercola
pages: 17
Download
Abstract ∨
In this paper we show an approach to assessing both the impact of business cycles on economic indicators and on the underlying macroeconomic variables and one of these variables in nowcasting GDP: this approach is based on the real-time ability of financial and real variables to reproduce business cycles. We observe that using both a large dataset and a smaller set of accurately targeted financial and real indicators in each phase of the cycle can deliver more accurate predictions, in particular concerning the identification of turning points. Since the recession of 2008-2009, we have found that a large part of the countries’ business cycles is due to real common shocks.
by Maria Iannario, Domenico Piccolo
pages: 28
Download
Abstract ∨
An alternative approach has been proposed for the analysis and the modelling of ordinal data: it is based on the psychological process by which a respondent expresses his/her evaluation about the item with an inherent indecision. This class of models has been developed with many variants and it is now indicated as CUB models. The purpose of this paper is to introduce users to the version 4.0 of a program, written in the R statistical environment, to make effective applications of CUB models and variants by exploiting their capabilities both from computational and graphical points of view. After a specification of the different structures, the basic commands are presented with some examples. Generalizations and extensions of the standard models are also mentioned. For a more extensive study a bibliographic note concludes the paper.
by Marica Manisera, Paola Zuccolotto
pages: 19
Download
Abstract ∨
Nonlinear CUB models have been recently introduced in the literature to model ordinal data taking into account the unequal spacing among response categories. Nonlinear CUB models can be effectively used in a variety of fields, typically when human perceptions and attitudes are measured by questionnaires with questions having ordered response categories. This paper introduces the code developed in the free software environment R for Nonlinear CUB estimation, graphical representation of a variety of outputs, fit evaluation, along with data simulation according to the Nonlinear CUB data generating process.
by Priyantha Wijayatunga
pages: 11
Download
Abstract ∨
Well known Simpson’s paradox is puzzling and surprising for many, especially for the empirical researchers and users of statistics. However there is no surprise as far as mathematical details are concerned. A lot more is written about the paradox but most of them are beyond the grasp of such users. This short article is about explaining the phenomenon in an easy way to grasp using simple algebra and geometry. The mathematical conditions under which the paradox can occur are made explicit and a simple geometrical illustration is used to describe it. We consider the reversal of the association between two binary variables, say, X and Y by a third binary variable, say, Z. We show that it is always possible to define Z algebraically for non-extreme dependence between X and Y, therefore occurrence of the paradox depends on identifying it with a practical meaning for it in a given context of interest, that is up to the subject domain expert. And finally we discuss the paradox in predictive contexts since in literature it is argued that the paradox is resolved using causal reasoning.
|
|