Search

Over the last few years many studies have been carried out in Italy to identify reliable small area labour force indicators. Considering the rotated sample design of the Italian Labour Force Survey, the aim of this work is to derive a small area estimator which “borrows strength” from individual temporal correlation, as well as from related areas. Two small area estimators are derived as extensions of an estimation strategies proposed by Fuller (1990) for partial overlap samples. A simulation study is carried out to evaluate the gain in efficiency provided by our solutions. Results obtained for different levels of autocorrelation between repeated measurements on the same outcome and different population settings show that these estimators are always more reliable than the traditional composite one, and in some circumstances they are extremely advantageous.

We analyze the anti-poverty effect of social cash transfers using a micro-econometric approach. Aggregate analyses, based on comparing average poverty indicators before and after public transfers, fail to address who receives the transfers and how the transfers are distributed among the poor. We consider three dichotomous outcome variables: (i) poverty status before the receipt of transfers; (ii) the receipt of transfers; and (iii) poverty status after the receipt of transfers. We use a trivariate probit model with sample selection, connecting the outcome variables to the characteristics of the household and its head. Our empirical results highlight that the Italian social transfers system overprotects certain household typologies at the expense of others, as social transfers are primarily awarded to employees with permanent positions and the elderly, while the system is not generous enough to large households with dependant children, the self-employed, temporary contract workers, and the unemployed.

A model-based small area method for calculating estimates of poverty rates based on different thresholds for subsets of the Italian population is proposed. The subsets are obtained by cross-classifying by household type and administrative region. The suggested estimators satisfy the following coherence properties: (i) within a given area, rates associated with increasing thresholds are monotonically increasing; (ii) interval estimators have lower and upper bounds within the interval (0, 1); (iii) when a large domain-specific sample is available the small area estimate is close to the one obtained using standard design-based methods; (iv) estimates of poverty rates should also be produced for domains for which there is no sample or when no poor households are included in the sample. A hierarchical Bayesian approach to estimation is adopted. Posterior distributions are approximated by means of MCMC computation methods. Empirical analysis is based on data from the 2005 wave of the EU-SILC survey.

In this paper, we explore the internationalization pattern of firms and its relationship with firms’ heterogeneity. Besides the more traditional exports and Foreign Direct Investments (FDI), we consider various forms of non-equity internationalization. The use of a Multivariate Probit Model allows us to assess the associations among the choices driving the firms’ internationalization strategy as a whole and, at the same time, to avoid a priori assumptions on the internationalization patterns. From the empirical evidence, two main results emerge. At first, we observe that Italian firms jointly adopt various internalization forms, others than exports and FDI, conditionally to characteristics of the firms. The hypothesis reported in literature of a complementary or subsidiary relationship between exports and FDI is then confirmed also for non-equity internationalization forms. Secondly, we find that the heterogeneity of firms, measured by a large range of variables, has an important role in defining the choice of firms on the patterns of internalization. Thus in this context, we endorse the emerging opinion asserting that various dimensions other than productivity are relevant, Statistica; Vol 68, No 1 (2008); 31-55

In recent years, the measure of regional disparities on household poverty and social exclusion has received increasing attention by policy makers and this has produced a growing demand of sub-national statistical information on income parameters. Many studies have shown a strong connection between poverty and some characteristics of the household such as its composition, highlighting the concentration of the greatest economic difficulties in particular household typologies. For this reason, the aim of the work is to provide estimates of some poverty indicators for domains defined by cross-classifying the population by household typology (9 categories) and administrative region (20 categories), on the basis of data collected for Italy by the “European Union – Statistics on Income and Living Conditions” survey (EU-SILC). The need of estimating simultaneously more than one parameter is due to the multidimensionality of the studied phenomenon. In particular, we focus on three poverty rates based on three different thresholds, so to distinguish between poor people (PR, standard poverty threshold defined as the 60% of median of personal equivalent income), very poor people (PR80, threshold defined as the 80% of the standard poverty threshold) and people who are at risk of becoming poor (PR120, threshold defined as the 120% of the standard poverty threshold). The considered source, EU-SILC, is a sample survey on households’ income and social conditions, coordinated by Eurostat (Eurostat, 2005), designed to provide reliable estimates of main parameters of interest for areas within countries that do not correspond to our target domains. The number of units sampled from those domains are too scarce, in many cases, to obtain reliable estimates of the parameters of interest, therefore some small area estimation strategies have to be considered.

Bayesian estimators of small area parameters may be very effective in improving the precision of “direct”, design-based estimates. By the way, the may be poor estimators of the actual Empirical Distribution Function of the ensemble of small area parameters. In this paper we review different adjusted estimators that correct or mitigate this problem in the context of Hierarchical Bayesian modelling, considering also extensions to the case of multivariate models that are widely used in Small Area estimation. In particular we consider constrained and linear constrained Hierarchical Bayes estimators, along with an estimation method recently by Zhang. The posterior Mean Square Errors are proposed as measures of uncertainty. Different methods are compared by means of a simulation exercise in which many situations occurring in small area estimation applied problems are artificially re-created. The main goals of the simulation is to assess the ability of various estimators to properly estimate the actual Empirical Distribution Function of area parameters and secondly to assess the frequentist properties of posterior MSEs. The method of Zhang emerges as best in both the univariate and the multivariate setting, although the picture in the latter case is less clear.

In this paper we propose the use of a Small Area Estimation (SAE) approach so as to obtain reliable estimates of the number of “recruits replacing employees leaving the firm (substitute recruits – SR) and of “recruits filling new positions (new recruits – NR). These estimates would clearly be of use in analysing the composition of that human capital required by Italian Industrial Districts, and subsequently in evaluating local economic systems’ ability to achieve a long-term competitive long-edge by expanding and/or renewing human capital. As we are interested in evaluating the dynamics of Industrial Districts s compared with those of non-Districts s, we have chosen to focus on the manufacturing sector. We use model-based estimators relying on “area level” models, because the UNIONCAMERE will not release individual data, due to privacy constraints, but only domain-level data on request. In order to specify a suitable SAE model, we first need to deal with the following problems. Firstly, our targeted estimation is the number of recruits. In this case, the standard Normal-Normal model would not hold, and so we need to use a small-area model for count data. Secondly, in order to increase the reliability of estimates, we have taken account of the correlation between sampling errors associated to NR and SR estimators by adopting a multivariate SAE model that borrows strength not only from areas but also from this correlation. As sample correlations between NR and SR are mainly negative, we suggest the use of an SAE model based on the multivariate Poisson-Log Normal distribution. Unlike other multivariate distributions for counts proposed in the literature, this particular distribution allows for unconstrained (both positive and negative) correlations. Finally, a problem due to the instability of estimated variances of direct estimators has to be faced. Usually, an approximately unbiased estimate of the variance of direct estimators may be available. In SAE modelling, the variance of direct estimators is generally assumed to be known and equal to its estimate. In the case of large samples, this assumption is commonly stated and largely accepted, whereas in the case of small samples, the variance estimate suffers from instability as do direct point estimators. Linked to this, a further problem arises due to the rarity of recruitments in certain domains. In fact, when direct estimates of SR or of NR (or of both) are equal to zero, sampling variances and covariances are also equal to zero. Note that estimated variances equal to zero do not necessarily imply the high degree of accuracy of the estimates. This problem is known in the literature, but no solution has been proposed as yet. Some studies (that of the National Research Council, 2000, for example) adopt a logarithmic transformation of the mean (or total) direct estimates of the count data in order to use a linear SAE model: these studies simply discard those estimates equal to zero. In this way, the problem of “zero variance” is overcome, although the adopted solution can lead to biased estimates of the model parameter and to the discarding of a portion of the sample in an “insufficient sample size” setting. To deal with both the instability of estimated variances and of estimated variances equal to zero, we propose a smoothing covariance matrix solution based once again on the Poisson-Log Normal distribution, following a Generalized Variance Function approach. We adopt a fully hierarchical Bayesian approach. In this field, relatively complex models, such as the multivariate one, can be easily implemented; furthermore, posterior distributions can be approximated using MCMC algorithms. Moreover, computing small-area multivariate estimators, and above all, estimates of their MSE, could prove difficult within a frequentist context.

The availability of reliable estimates of income distribution parameters at a sub-national level is essential for the study of regional disparities. For European Union, countries the estimation of income parameters can be obtained from the European Community Household Panel, that provides reliable estimates for large areas within countries. The aim of this work is to find a suitable small area estimator of the average income at a smaller geographical scale, based on data from this survey. Since it is a panel survey, we suggest some different specifications of unit level Linear Mixed Models leading to small area estimators that borrow strength across both areas and times. In the Small Area Estimation context, full time series and “time series and cross-sectional” aggregate models have been applied in the literature, while small area unit level models for panel data have not been studied extensively. We compare the estimators performance by a Monte Carlo simulation study. Results show a significant gain in efficiency of estimators connected to models that take into account units autocorrelation.

Linear Mixed Models used in small area estimation usually rely on normality for the estimation of the variance components and the Mean Square Error of predictions. Nevertheless, normality is often inadequate when the target variable is income. For this reason, in this paper we consider Linear Mixed Models for the log-transformed income (which require back-transformation for prediction of means and totals on the variable’s original scale) and a Generalized Linear Mixed Model based on the Gamma distribution. Various prediction methods are compared by means of a simulation study based on the ECHP data. Standard predictors obtained from Linear Mixed Model for the untrasformed income are shown to be preferable to the considered alternatives, confirming their robustness with respect to the failure of the normality assumption.