The Serbian Banking System: Recent Development and Major Players

The paper analyzes the banking system of Serbia. First, we briefly overview the institutional and legal framework of the banking system and describe the main structural features of the sector. Then we discuss the evolution in traditional banking intermediation, and outline the main features of the banking competitive environment, focusing on the transformations in ownership structure of banks, especially on the increasing importance of foreign ownership, and summarising the key characteristics of major players.     

Labour Migration and Competitiveness in the European Union

The study is about the characteristics and phenomena of the labour migration that fluxes from, through, and into the East Central European region. The typical groups of migrant workers are emphasized, like the qualified employees, the commuters, the illegal workers, or the migrants according to the family's income optimization. The brain drain is analyzed as a problem of the absence of experts in the region. The tools and possibilities of migration policy are discussed, too, to find suggestions for the state how to turn the direction of migration to the desired way. Through this topic, the countries of destination are introduced with the competitive position of the eastern migrants. The study also reflects on the problem of asymmetric flux of labour out of the region.     

Community and anti-poverty targeting

The standard theory of anti-poverty targeting assumes individual incomes cannot be observed, but statistical properties of income distribution in broadly defined groups are known. ‘Indicator targeting’ rules are then derived for the forms of transfers conditioned on group membership of individuals. In this literature the motivating notion of a ‘group’ is purely statistical, even when it is groups such as localities and ethnicities. We focus instead on groups which are ‘communities’, meaning thereby collections of individuals who have access to community-specific public goods, from which non-members are excluded. Such differential access constitutes a source of inequality among poor individuals belonging to different communities, which is not captured by monetary earnings. We show that this formulation of what constitutes a group changes many of the basic results of the indicator targeting literature. Optimal targeting for poverty alleviation leads to seemingly paradoxical rules, such as targeting transfers to the community that is richer. Total wealth of non-poor members of a community and its distribution both become relevant for specifying optimal indicator targeting rules. In addition, a poverty measure that is sensitive to the community identities of poor individuals, yet defined on nominal incomes, may be incompatible with some of the basic axioms in the standard literature on poverty measurement.     

A ``European Consensus' on the Growth Agenda? A Discussion of the Sapir Report

This paper offers a discussion of An Agenda for a Growing Europe: Making the Economic System Deliver, a report to the President of the European Commission prepared by a group of independent experts. The paper reflects the results of the 3rd Milan European Economy Workshop (May 28–29, 2004) and my personal views. The workshop was organised by the Department of Economics, University of Milan and the Jean Monnet Chair of Economics of European Integration, with the participation of more than twenty distinguished speakers from several institutions across the European Union.     

Costs and Financing of Maritime Education and Training in Europe: Analysis and Policy Implications

The paper reports some findings of an extensive European research project carried out on costs and funds of MET (maritime education and training) systems. The need to improve the quality of the European MET systems is a relevant political and scientific issue which strongly impacts the competitiveness of the shipping sector in Europe. However, MET is quite an expensive ET system since it requires high investments and incurs in high running costs. The situation is also acerbated by the decreasing number of students at MET institutions. There is then the need of having a closer look at the financial aspects of MET so as to come up with some policy recommendations for improving the current situation in terms of optimal use of resources. In the paper a questionnaire-based methodology is employed aiming at identifying and analyzing different cost and funds structures of MET institutions in Europe (cost models). Then, by considering some policy-sensitive variables of the cost models, some policy recommendations are drawn up to improve the efficiency of current systems. They basically refer to the need to concentrate and integrate resources in order to exploit some degree of economies of scale, on top of achieving some economies of scope and pursuing quality in MET. Finally, further lines of research are indicated.     

Bayesian neural networks for nonlinear time series forecasting

In this article, we apply Bayesian neural networks (BNNs) to time series analysis, and propose a Monte Carlo algorithm for BNN training. In addition, we go a step further in BNN model selection by putting a prior on network connections instead of hidden units as done by other authors. This allows us to treat the selection of hidden units and the selection of input variables uniformly. The BNN model is compared to a number of competitors, such as the Box-Jenkins model, bilinear model, threshold autoregressive model, and traditional neural network model, on a number of popular and challenging data sets. Numerical results show that the BNN model has achieved a consistent improvement over the competitors in forecasting future values. Insights on how to improve the generalization ability of BNNs are revealed in many respects of our implementation, such as the selection of input variables, the specification of prior distributions, and the treatment of outliers.     

Series evaluation of Tweedie exponential dispersion model densities

Exponential dispersion models, which are linear exponential families with a dispersion parameter, are the prototype response distributions for generalized linear models. The Tweedie family comprises those exponential dispersion models with power mean-variance relationships. The normal, Poisson, gamma and inverse Gaussian distributions belong to theTweedie family. Apart from these special cases, Tweedie distributions do not have density functions which can be written in closed form. Instead, the densities can be represented as infinite summations derived from series expansions. This article describes how the series expansions can be summed in an numerically efficient fashion. The usefulness of the approach is demonstrated, but full machine accuracy is shown not to be obtainable using the series expansion method for all parameter values. Derivatives of the density with respect to the dispersion parameter are also derived to facilitate maximum likelihood estimation. The methods are demonstrated on two data examples and compared with with Box-Cox transformations and extended quasi-likelihoood.     

Semiparametric Methods for Clustered Recurrent Event Data

In biomedical studies, the event of interest is often recurrent and within-subject events cannot usually be assumed independent. In addition, individuals within a cluster might not be independent; for example, in multi-center or familial studies, subjects from the same center or family might be correlated. We propose methods of estimating parameters in two semi-parametric proportional rates/means models for clustered recurrent event data. The first model contains a baseline rate function which is common across clusters, while the second model features cluster-specific baseline rates. Dependence structures for patients-within-cluster and events-within-patient are both unspecified. Estimating equations are derived for the regression parameters. For the common baseline model, an estimator of the baseline mean function is proposed. The asymptotic distributions of the model parameters are derived, while finite-sample properties are assessed through a simulation study. Using data from a national organ failure registry, the proposed methods are applied to the analysis of technique failures among Canadian dialysis patients.     

Marginal Regression of Multivariate Event Times Based on Linear Transformation Models

Multivariate event time data are common in medical studies and have received much attention recently. In such data, each study subject may potentially experience several types of events or recurrences of the same type of event, or event times may be clustered. Marginal distributions are specified for the multivariate event times in multiple events and clustered events data, and for the gap times in recurrent events data, using the semiparametric linear transformation models while leaving the dependence structures for related events unspecified. We propose several estimating equations for simultaneous estimation of the regression parameters and the transformation function. It is shown that the resulting regression estimators are asymptotically normal, with variance–covariance matrix that has a closed form and can be consistently estimated by the usual plug-in method. Simulation studies show that the proposed approach is appropriate for practical use. An application to the well-known bladder cancer tumor recurrences data is also given to illustrate the methodology.     

Multilevel Mixed Linear Models for Survival Data

For the analysis of correlated survival data mixed linear models are useful alternatives to frailty models. By their use the survival times can be directly modelled, so that the interpretation of the fixed and random effects is straightforward. However, because of intractable integration involved with the use of marginal likelihood the class of models in use has been severely restricted. Such a difficulty can be avoided by using hierarchical-likelihood, which provides a statistically efficient and fast fitting algorithm for multilevel models. The proposed method is illustrated using the chronic granulomatous disease data. A simulation study is carried out to evaluate the performance.