On the Interaction between Ultra–high Frequency Measures of Volatility
Giampiero M. Gallo, Margherita Velucchi
We analyze several measures of volatility (realized variance, bipower variation and squared daily returns) as estimators of integrated variance of a continuous time stochastic process for an asset price. We use a Multiplicative Error Model to describe the evolution of each measure as the product of its conditional expectation and a positive valued iid innovation. By inserting past values of each measure and asymmetric effects based on the sign of the return in the specification of the conditional expectation, one can investigate the information content of each indicator relative to the others. The results show that there is a directed dynamic relationship among measures, with squared returns and bipower variance interdependent with one another, and affecting realized variance without any feed-back from the latter.
Flexible Time Series Forecasting Using Shrinkage Techniques and Focused Selection Criteria
Christian T. Brownlees, Giampiero M. Gallo
Nonlinear time series models can exhibit components such as long range trends and seasonalities that may be modeled in a flexible fashion. The resulting unconstrained maximum likelihood estimator can be too heavily parameterized and suboptimal for forecasting purposes. The paper proposes the use of a class of shrinkage estimators that includes the Ridge estimator for forecasting time series, with a special attention to GARCH and ACD models. The local large sample properties of this class of shrinkage estimators is investigated. Moreover, we propose symmetric and asymmetric focused selection criteria of shrinkage estimators. The focused information criterion selection strategy consists of picking up the shrinkage estimator that minimizes the estimated risk (e.g. MSE) of a given smooth function of the parameters of interest to the forecaster. The usefulness of such shrinkage techniques is illustrated by means of a simulation exercise and an intra-daily financial durations forecasting application. The empirical application shows that an appropriate shrinkage forecasting methodology can significantly outperform the unconstrained ML forecasts of rich flexible specifications.
Regime Switching: Italian Financial Markets over a Century
The frequency of crashes and the magnitude of crises in international financial markets are growing more severe over time. Recent financial crises are not singular events portrayed in recent accounts, rather, they erupt in circumstances that are very similar to the economic and financial environments of the earlier eras. This paper analyzes the Italian stock market in two very peculiar periods (1901-1911 and 1993-2004): the “Second” and the “Third Industrial Revolution”. We use Markov Switching Models to test whether the Italian stock market volatility has increased in the long run and if it can be represented by different volatility regimes. We find that volatility regimes exist; that Banking sector has a central role and “New Economy” sectors perform quite well while traditional sectors do not, in both periods.
Volatility Forecasting Using Explanatory Variables and Focused Selection Criteria
Christian T. Brownlees, Giampiero. M Gallo
This paper assesses the performance of volatility forecasting using focused selection and combination strategies to include relevant explanatory variables in the forecasting model. The selection and combination schemes proposed are said to be focused in that they depend on the current forecasting problem of interest and are thus useful in real-time forecasting applications. The methodology is applied to a daily recursive 1--step ahead value--at--risk (VaR) forecasting exercise of 4 widely traded New York Stock Exchange stocks. The proposed focused methods are also compared with other strategies, including the well established AIC and BIC. Results show that VaR forecasts can significantly be improved upon using focused forecast strategies for the selection of relevant exogenous information. The set of explanatory variables that helps improving prediction is stock dependent. Traditional information criteria do not appear to be helpful in suggesting the inclusion of explanatory variables that actually improve prediction significantly.
Published as Journal of Financial Econometrics, Volume 6, Issue 4, pp. 513-539, 2008; link, published.
wp2007_05 (Economic Statistics)
Competitiveness and Survival: A Comparative Analysis of Italian Regions
Margherita Velucchi, Alessandro Viviani
This paper focuses on business demography of Italian firms to identify the relationships among firms characteristics and their competitiveness using, as a proxy, their survival in the market. We use a 6-digit level of aggregation to capture market dynamics and we focus on five Italian regions between 2000 and 2005 both for manufacturing and service sectors. The empirical analysis shows that firms are characterized by small size and low technological intensity in all regions. Both for manufacturing and service sectors the survival rates for large size firms are significantly higher than those of smaller firms and, on average, the survival rates after few years are very low. Service firms live longer than manufacturing firms and their hazard rates turn out to be less sensitive to size. From the empirical analysis we derive that regions have a similar structure and we find evidence of technological niches in Emilia Romagna, Toscana and Puglia.
wp2007_06 (Social Statistics, Medical Statistics)
Studio delle reti di supporto - Un'applicazione ai dimessi ospedalieri
Marco Marchi, Silvana Schifini D'Andrea, Filomena Maggino, Tiziana Mola
E’ noto come le trasformazione familiari degli ultimi decenni abbiano portato ad una crescente delega dell’assistenza delle persone bisognose (anziani, malati, ecc.) alle strutture pubbliche. La razionalizzazione della spesa nel settore sanitario porta a degenze sempre più brevi e dimissioni precoci che possono creare difficoltà organizzative nella gestione assistenziale della famiglia. In particolare il paziente anziano dimesso dall’ospedale a seguito di patologie croniche e/o invalidanti si viene a trovare, quasi sempre, in una situazione critica caratterizzata dalla mancanza di autonomia sia fisica che psicologica e spesso anche economica. Emerge quindi la necessità di quantificare l’entità dei bisogni al fine di valutare forme e modalità di supporto adeguate (in qualità e quantità) per venire incontro ai momenti critici post-ricovero che si vengono a determinare per soggetti “deboli” in termini di capacità gestionale delle famiglie a fronte di una inesistenza/inconsistenza di una rete di supporto. Il presente studio mette a punto una metodologia di rilevazione della rete (in termini di parenti, amici, vicini) di supporto (inteso come assistenza sia fisico/pratica che psicologico/emotiva) nella fase successiva alla dimissione ospedaliera. Viene presentato una proposta di rilevazione articolata in due fasi: la prima, con questionario cartaceo, si svolge in reparto al momento della dimissione; la seconda, con tecnica CATI, rileva a distanza di alcuni giorni l’inserimento del paziente nella realtà familiare. Lo studio giunge alla proposta della tecnica di rilevazione, al collaudo dei questionari e alla realizzazione di un sondaggio pilota che ha consentito la verifica degli strumenti, della loro funzionalità e della conseguente applicabilità. Vengono infine proposti i seguenti indicatori compositi di reti sociali e familiari: dimensione della rete, intensità di supporto, bisogni, supporto ricevuto e soddisfazione dei bisogni.
La fecondità della donna in Toscana dalla fine del secondo conflitto mondiale ad oggi
Antonio Santini, Silvana Salvini
Traditionally Tuscany, between the Italian Regions, has been always characterized by a very low cohort fertility and by a steadily cohort nuptiality, following, since the most recent cohorts, the classical ‘European first marriage pattern’. In a period perspective, the trends of both phenomena are in line, except for rates level, with the picture we can observe in whole Italy and in the other Regions. In the paper the Authors analyze, mainly on the basis of official data, fertility and first marriage rates for Tuscan women born from 1920 (1937 for nuptiality) to 1970 – in the period perspective it covers the years 1952-2003 – comparing those series with the analogous ones for Italy, for the Central regions and, above all, for Emilia-Romagna. This Region, in fact, is distinguished in the national context both by the lowest cohort and period fertility and by an advanced welfare system. The results lead to the hypothesis of an end of the dramatic decrease of fertility (but not of nuptiality) and symptoms emerge of a possible, although moderate, reverse of the declining trend, mostly through the contribution of the higher fertility of foreign women.
wp2007_08 (Demography, Statistics)
The rising marital disruption in Italy and its correlates
Daniele Vignoli, Irene Ferro
Most of our knowledge on divorce pertains to the USA and Northern Europe, while demographic studies from Southern Europe are relatively scarce. This study looks at this knowledge gap through an analysis of the correlates to recent rising marital instability in Italy. We use a recent survey — the 2003 Italian Gender and Generation Survey – which captures recent trend on marital disruption, also among relatively young cohort. Event history techniques are employed. Results show that beside the expected correlation of marital disruption with women’s birth cohort and socio-economic status, other correlates, more closely linked to Italian peculiarities, may also be identified. The explanatory role of religious values and the complex legal procedure to obtain a divorce can be, in this sense, alluded to.
Published as Demographic Research, Volume 20, Issue 1, pp. 11-36, 2009; link, published.
wp2007_09 (Statistics, Econometrics)
Finding alternative sources of identification in generalized selection models using principal stratification
Fabrizia Mealli, Barbara Pacini
In this paper we consider two approaches for dealing with "endogenous selection'' problems when estimating causal effects, namely selection models (SM) and principal stratification (PS). Our main goal is to highlight similarities and differences of the two approaches, by first investigating the different nature of their parametric hypotheses. In order to support our reasoning, we show their different performances by simulations under both approaches. We argue that principal stratification is able to suggest alternative identification strategies not always easily translated into assumptions of a selection model.
Selection bias in linear mixed models
Leonardo Grilli, Carla Rampichini
The paper investigates the consequences of sample selection in multilevel or mixed models, focusing on the random intercept two-level linear model under a selection mechanism acting at both hierarchical levels. The behavior of sample selection and the resulting biases on the regression coefficients and on the variance components are studied both theoretically and through a simulation study. Most heoretical results exploit the properties of Normal and Skew-Normal distributions. In the case of clusters of size two, analytic formulae of the bias are provided that generalize Heckman’s formulae. The analysis allows to outline a taxonomy of sample selection in the multilevel framework that can support the qualitative assessment of the problem in specific applications and the development of suitable techniques for diagnosis and correction.
Published as Metron, 2010, forthcoming.
Volatility Spillovers, Interdependence and Comovements: A Markov Switching Approach
Giampiero M. Gallo, Edoardo Otranto
The transmission mechanisms of volatility between markets can be characterized within a new Markov Switching bivariate model where the state of one variable feeds into the transition probability of the state of the other. A number of model restrictions and hypotheses can be tested to stress the role of one market relative to another (spillover, interdependence, comovement, independence, Granger non causality). The model is estimated on the weekly high--low range of five Asian markets, assuming a central (but not necessarily dominant) role for Hong Kong. The results show plausible market characterizations over the long run with a spillover from Hong Kong to Korea and Thailand, interdependence with Malaysia and comovement with Singapore.
Published as Computational Statisitics and Data Analysis, Volume 52, Issue 6, pp. 3011-3026, 2008; link, published.
Two-Stage Restricted Adaptive Cluster Sampling
Adaptive cluster sampling can be a useful technique for parameter estimation when a population is highly clumped with clumps widely separated. In this design, however, the size of the final sample cannot be predicted prior to sampling, thus leading to design problems. In this paper a new version of adaptive cluster sampling which allows the sampler to know prior to sampling the exact upper limit of the final sample size and consequently the highest total sampling effort, is suggested. It is drawn from a combination of the restricted adaptive cluster sampling of Brown (1994) and a two-stage adaptive cluster sampling. For this new sampling design an unbiased estimator of the total and its sample variance are also suggested. The results of a simulation study, performed in order to provide a first evaluation of the method, are promising.
Young workers and flexibility of the labour market: what family strategies?
Silvana Salvini, Irene Ferro
Recently, the working strategy “job to job” is diffusing in Italy. On the one side, temporary works has concurred to a lessening of young people unemployment. On the other side, they have led to an increase of precariousness and insecurity for the future. And this phenomenon regards just those ones that seem to present many difficulties to the “transition to adulthood”. Parents have a great role in this transition: especially in Italy, where certainly there are cultural factors that “keep” young people into the parental home, we must consider also that parents represent the only support in front of the uncertainties of a fluctuating labour market, due also to the lack of adequate policy. The aim of our paper, is to study if instability may assume a large importance in the delay of the assumption of the responsibilities of the adulthood. Using data stemming from an Italian and a Tuscan survey, we carried out firstly some exploratory analysis with the aim to find the most discriminative variables and finally an interpretative regression analysis. The crucial role of the educative curriculum in the delay of building family emerges, such as the gender differences. And the contractual form has a significant role: the probability to enter into a partnership is lower for people having an atypical work than for people occupied in a traditional one. In Tuscany, for 51% of those who live out of the parental home, fertility projects are conditioned by the type of contract.
Gender and new family patterns in Europe: attitudes, behaviours, and opinions
Ginevra Di Giorgio, Francesca Fiori, Elisabetta Santarelli, Daniele Vignoli
The great social changes experienced by many countries since the Second World War, and particularly throughout the most recent years, concern various aspects of individual and collective life, which also influence demographic behaviours: from the sexual and contraceptive behaviour to the models of couples’ formation and dissolution and to reproductive choices. Many scholars related this plurality of family forms also to a mutated attitude of men and women towards the family: the transformation in family formation appears therefore to be strongly influenced also by the changes in gender roles. The ideational system also seems to play a major role on the diffusion of new models of behaviour: opinions, attitudes and approaches towards ideal life styles represent one of the main determining factors of family and reproductive choices. The aim of this work is to explain the variability of family behaviours by adopting a gender approach: specifically, its originality consists in considering not only the gendered behaviours but also the opinions towards gender roles as main discriminant factors of the attitudes towards new family models. Particularly, we ask whether there is a correspondence between opinions favourable to egalitarian gender roles and the openness towards new family behaviour. Or conversely, is the effective gender equity in the division of roles to be more relevant in determining the cultural context at the basis of opinions’ formation of men and women? We did not observe a significant association between opinions towards gender roles and opinions on modern family behaviours. On the contrary, it emerges a clear connection between effective gender equality in the division of roles within the couple and a more openness towards new family behaviours.
Comparison of Volatility Measures: a Risk Management Perspective
Christian T. Brownlees, Giampiero M. Gallo
Volatility measurement has received a boost from the availability of ultra–high frequency data (UHFD) sampled at different frequencies which need to be complemented by appropriate methods to project volatility behavior. In this paper we take a risk management perspective and address the issue of forecasting Value–at–Risk (VaR) using different volatility measures: realized volatility, bipower realized volatility, two scales realized volatility, as well as the daily range. For the sample and assets chosen, volatility clustering occurs around a changing level in average volatility; other features such as persistence and shape appear to change with the UHFD sampling frequency. Building on the existing literature, we propose a novel modeling approach that captures the features of the series called P–Spline Multiplicative Error Model. Such an approach consists of a dynamic model with a flexible trend specification bonded with a penalized maximum likelihood estimation strategy that enhances forecasting ability. Results show that exploiting UHFD volatility measures, VaR predictive ability is improved upon relative to a baseline GARCH approach but the range is not outperformed and that there are relevant gains from modeling volatility trends and the nonnormality of the conditional return distribution.
Published as Journal of Financial Econometrics, Volume 8, Issue 1, pp. 29-56, 2010; link, published.
A Model for Multivariate Non-negative Valued Processes in Financial Econometrics
Fabrizio Cipollini, Robert F. Engle, Giampiero M. Gallo
The Multiplicative Error Model introduced by Engle (2002) for non-negative valued processes is specified as the product of a (conditionally autoregressive) scale factor and an innovation process with positive support. In this paper we propose a multivariate extension of such a model, by taking into consideration the possibility that the vector innovation process be contemporaneously correlated. The estimation procedure is hindered by the lack of probability density functions for multivariate non-negative valued random variables. We suggest the use of copula functions to jointly estimate the parameters of the scale factors and of the correlations of the innovation processes. We illustrate the feasibility of the procedure and the gains over the equation by equation approach using a four variable fully interdependent model with different volatility measures.
wp2007_17 (Economic Statistics)
A Statistical Information System in Support of the Italian Competence System Governance
Flexible work patterns require rigorous plans on adult education and life long learning, based on worker’s personal competence profile. To achieve this point, at European and national level, official competences certification systems are proposed and, in same cases, realized. The paper discusses the role that administrative data on competences could play in the context of economic statistical sources.
Ultimo aggiornamento 23 giugno 2010.