Search

Many postsocialist countries are run by an elite with links to the socialist legacy and often share similar challenges and issues. We investigate formal and informal factors shaping the role of mayors in accessing regional development funds in Albania, a postsocialist country. With data from one of the largest elite (mayors) survey, we analyze both channels of influence of the mayors: the number of applications and the success rate. We find that mayors bring their communities more funds using formal leadership qualities that intensify the number of submissions. On the other hand, informal leadership remains important in explaining the success rate, as by using networking channels leaders enhance the probability to get financed. Political power is also decisive in the process.

The authors replicate and extend the Monte Carlo experiment presented in Doz, Giannone and Reichlin (A Quasi-Maximum Likelihood Approach For Large, Approximate Dynamic Factor Models, Review of Economics and Statistics, 2012) on alternative (time-domain based) methods for extracting dynamic factors from large datasets; they employ open source software and consider a larger number of replications and a wider set of scenarios. Their narrow sense replication exercise fully confirms the results in the original article. As for their extended replication experiment, the authors examine the relative performance of competing estimators under a wider array of cases, including richer dynamics, and find that maximum likelihood (ML) is often the dominant method; moreover, the persistence characteristics of the observable series play a crucial role and correct specification of the underlying dynamics is of paramount importance.

We provide the analytical gradient of the full model likelihood for the Dynamic Conditional Correlation (DCC) specification by Engle (2002), the generalised version by Cappiello et al. (2006), and of the cDCC model by Aielli(2013). We discuss how the gradient might be further extended by introducing elements related to the conditional variance parameters, and discuss the issue arising from the estimation of constrained and/or reparametrised versions of the model. A computational simulation compares analytical versus numerical gradients, with a view to parameter estimation, we find that analytical differentiation yields more efficiency and improved accuracy.

In the last thirty years, migrant remittances have become a stable source of external finance for developing countries. In this paper, we investigate whether aggregate persistence can be traced back to individual remitting behaviour, as a result of migrants’ intertemporal choices. We propose a dynamic random-effects double hurdle model based on micro data from the German Socio-Economic Panel dataset. Our results show that there is significant state dependence in remitting behaviour, but in steady-state neither the probability to remit nor the transferred amounts are particularly large, thus suggesting that long-term intertemporal planning is rather sporadic. On these grounds, the medium-long term counterbalancing effect of remittances on the brain drain appears to be weak.

This paper is the first systematic attempt to investigate the factors affecting time persistence in individual remittance behaviour. By using micro-level longitudinal data from the German Socio-Economic Panel (SOEP), we apply a wide variety of discrete choice static and dynamic panel models to analyse the decision to remit. Our results provide evidence in favour of an intertemporal strategy. The persistence in remittance decisions is significantly influenced by “true state dependence”: migrants that remitted in the previous year have a significantly higher propensity to remit this year as well. We also show that remittance time patterns depend on both observable and unobservable individual socioeconomic characteristics, and in particular, that the household’s transnational composition plays an important role in determining remittance behaviour.

The commonly-used version of the double-hurdle model rests on a rather restrictive set of statistical assumptions, which are very seldom tested by practitioners, mainly because of the lack of a standard procedure for doing so, although violation of such assumptions can lead to serious modelling flaws. We propose here a bootstrap-corrected conditional moment portmanteau test which is simple to implement and has good size and power properties.

In this paper, we propose a test for bivariate normality in imperfectly observed models, based on the information matrix test for censored models with bootstrap critical values. In order to evaluate its properties, we run a comprehensive Monte Carlo experiment, in which we use the bivariate probit model and Heckman sample selection model as examples. We find that, while asymptotic critical values can be seriously misleading, the use of bootstrap critical values results in a test that has excellent size and power properties even in small samples. Since this procedure is relatively inexpensive from a computational viewpoint and is easy to generalise to models with arbitrary censoring schemes, we recommend it as an important and valuable testing tool.

We consider the estimation of linear models where the dependent variable is observed by intervals and some continuous regressors may be endogenous. Our approach, an IV version of the technique devised by Stewart (Rev Econ Stud 50(3):737–753, 1983), is fully parametric and two estimators are proposed: a two-step estimator and a limited-information maximum-likelihood estimator. The results can be summarized as follows: the two-step estimator has an intuitive appeal, and a Monte Carlo experiment suggests that its relative efficiency is rather satisfactory. The limited-information maximum-likelihood estimator, however, is probably simpler to implement and has the advantage of providing a framework in which several testing procedures are more straightforward to perform. The application of two-stage least squares to a proxy of the dependent variable built by taking midpoints, on the other hand, leads to inconsistent estimates; Monte Carlo evidence suggests that the bias arising from the “midpoint” technique is much worse than the effect of distributional misspecification. An example application is also included, which uses Australian data on migrants’ remittances; endogeneity effects are substantial and using conventional estimation methods leads to substantially misleading inference.

Starting from the work by Campbell and Shiller (Campbell, J.Y. and Shiller, R.J. (1987). Cointegration and tests of present value models. Journal of Political Economy, 95(5):1062–1088.), empirical analysis of interest rates has been conducted in the framework of cointegration. However, parts of this approach have been questioned recently, as the adjustment mechanism may not follow a simple linear rule; another line of criticism points out that stationarity of the spreads is difficult to maintain empirically. In this paper, we analyse data on US bond yields by means of an augmented VAR specification which approximates a generic nonlinear adjustment model. We argue that nonlinearity captures macro information via the shape of the yield curve and thus provides an alternative explanation for some findings that recently appeared in the literature. Moreover, we show how conditional heteroskedasticity can be taken into account via GARCH specifications for the conditional variance, either univariate or multivariate.

The GNU/Linux operating system is rapidly gaining ground as an attractive alternative to the proprietary platforms particularly in academic institutions and government agencies. Here, we supply an assessment of this resource from the perspective of econometricians, discuss its benefits and disadvantages along with a basic overview of some of the popular free/libre and open source programs hosted by this platform for conducting research in economics. Copyright © 2008 John Wiley & Sons, Ltd.

Summary The issue of finite-sample inference in Generalised Autoregressive Conditional Heteroskedasticity (GARCH)-like models has seldom been explored in the theoretical literature, although its potential relevance for practitioners is obvious. In some cases, asymptotic theory may provide a very poor approximation to the actual distribution of the estimators in finite samples. The aim of this paper is to propose the application of the so-called double length regressions (DLR) to GARCH-in-mean models for inferential purposes. As an example, we focus on the issue of Lagrange Multiplier tests on the risk premium parameter. Simulation evidence suggests that DLR-based Lagrange Multiplier (LM) test statistics provide a much better testing framework than the more commonly used LM tests based on the outer product of gradients (OPG) in terms of actual test size, especially when the GARCH process exhibits high persistence in volatility. This result is consistent with previous studies on the subject.

In this paper, we carry out an econometric analysis on the adoption and effective use of Information and Communication Technologies (ICTs) among a sample of Italian SMEs. An important result is that, in order to understand the main factors that drive SMEs to the adoption of ICTs, it is useful to divide the available technologies according to a taxonomy based on their typical function. Along with general-use ICTs (e-mail and Internet access), we identify two groups of technologies (labelled production-integrating and market-oriented ICTs) the use of which is associated with different firm characteristics. In both cases, however, the availability of highly educated workers turns out to be a key factor. Policy implications are also discussed.

A naive GMM approach to estimating QR (logit and probit) models with endogenous explanatory variables can lead to inconsistent estimators. This result was previously shown by Dagenais via simulation. In this paper, a special case is presented for which an analytical proof is possible; it turns out that the estimator is indeed inconsistent, but the framework analysed here can be useful for hypothesis testing. Un approccio GMM `naive' per la stima di modelli QR con regressori endogeni porta a stimatori inconsistenti. Questo risultato, ottenuto via simulazione da Dagenais, viene qui provato analiticamente in un caso particolare. Si ha che lo stimatore in effetti inconsitente, ma pu essere di una qualche utilit per la prova di ipotesi.

Multivariate GARCH models constitute the workhorse of empirical applications in several fields, a notable example being financial econometrics. Unfortunately, ML (or quasi-ML) estimation of such models, although relatively straightforward in theory, is often made difficult by the fact that available software relies on numerical methods for computing the first derivatives of the log-likelihood; the fact that these models often include a large number of parameters makes it impractical to estimate even medium-sized models. In this paper, closed-form expressions for the score of the BEKK model of Engle and Kroner (1995) are obtained, and strategies for efficient computation are discussed.

Inference for ARFIMA processes is more complicated than that for ordinary ARMA models. This has limited the application of these processes in the practice of modelling economic time series. In this paper, a procedure of indirect estimation for fractionally integrated processes is proposed and discussed. A Monte Carlo experiment shows that indirect estimators are not inferior to other estimators proposed in the literature, and could provide a reliable framework for extending fractionally integrated models in new directions and widen their applicability.

In this paper, we use data from the German Socio-Economic Panel (SOEP) in the 1997-2009 period for a large sample of migrants from 84 countries in order to develop an empirical model for the propensity by migrants to remit. Our model takes into full account the intertemporal aspects of the problem, which has been ignored by a large part of the applied literature, despite its theoretical and empirical importance. We find that most results already established in the empirical literature are confirmed; however, the intertemporal nature of the remittance behaviour emerges very clearly, giving rise to individual patterns which are difficult to synthesize by a simple description. Building on our framework, we find also support for theoretical models which predict different remittance time paths between return and permanent migrants.

We estimate a remittance model in which we address endogeneity and reverse causality relationships between immigrants' remittances, pre-transfer income and consumption. In order to take into account the fact that a large share of individuals do not remit, instrumental variable variants of the double-hurdle and Heckit selection models are proposed and estimated by Limited Information ML; semiparametric extensions are considered as robustness checks. Our results for a sample of recent immigrants to Australia show that endogeneity is substantial and that estimates obtained by the methods previously employed in the literature may be misleading if given a behavioral interpretation.

We estimate a behavioural model of household’s remittances to investigate to what extent the level of financial development in the home country affects decisions on whether and how much to remit.

In this paper, we run a Monte Carlo analysis of the finite-sample performance of an Information Matrix Test put forward by Smith (1985) for bivariate censored models. We use the bivariate probit model and Heckman selection model as examples.;Approximating the finite-sample distribution of this test statistic by its asymptotic distribution can lead to very misleading results: its size is severely distorted even in samples that common practice would judge to be perfectly adequate for asymptotics. This is especially true when the correlation coefficient is far from zero.;Power properties of the test statistic are investigated by using bivariate t(6) and x2(1) alternatives. The test has very low power against leptokurtosis, especially in the bivariate probit case, while power against asymmetry appears to be much more satisfactory.;In general, the performance of the Information Matrix test seems to be related to the amount of information on the latent variables which survives the censoring mechanism. A somewhat improved version of the test can be obtained, in some cases, by a careful choice of the moment conditions to employ.

We consider the estimation of linear models where the dependent variable is observed by intervals and some continuous regressors may be endogenous. Our approach is fully parametric and two estimators are proposed: a two-step estimator and a limited-information maximum-likelihood estimator. The results can be summarised as follows: the two-step estimator may offer some computational advantages over the LIML (Limited Information Maximum Likelihood) estimator, and a Monte Carlo experiment suggests that its relative efficiency is rather satisfactory. The LIML estimator, however, is probably simpler to implement and has the advantage of providing a framework in which several testing procedures are more straightforward to perform. The application of TSLS (Two-Stage Least Squares) to a proxy of the dependent variable built by taking midpoints, on the other hand, leads to inconsistent estimates. An example application is also included, which uses Australian data on migrants' remittances.

For many countries, remittance behaviour by migrants is an important component of their overall international financial flows. To date, the empirical literature has analysed the propensity to remit as a function of migrants' socio-economic characteristics. However, no studies have fully addressed the empirical implications of remittance behaviour being determined in the broader context of migrants' labour, income and consumption allocation strategy. On the contrary, the migrant's income has almost always been treated as exogenous in this context. The aim of this study is to estimate a remittance equation that detects the main determinants of remittance behaviour while addressing endogeneity and reverse causality relationships between remittances, income, consumption and savings. Moreover, since a large share of individuals do not remit money at all, an instrumental variable variant of the double-hurdle selection model is proposed and estimated by LIML.;A sending country perspective is adopted in the empirical analysis by considering the first cohort of the Longitudinal Survey of Immigrants to Australia. We find that endogeneity is substantial and that estimates obtained by the methods previously employed in the literature may be very misleading if given a behavioural interpretation. Our results confirm some theoretical predictions and shed light on others; notably, we show that "selfish" motives in remitters are at least as important as "altruistic" motives.

Forecasting models for bond yields often use macro data to improve their properties. Unfortunately, macro data are not available at frequencies higher than monthly. In order to mitigate this problem, we propose a nonlinear VEC model with conditional heteroskedasticity (NECH) and find that such model has superior in-sample performance than models which fail to encompass nonlinearities and/or GARCH-type effects. Out-of-sample forecasts by our model are marginally superior to competing models; however, the data points we used for evaluating forecasts refer to a period of relative tranquillity on the financial markets, whereas we argue that our model should display superior performance under "unusual" circumstances.

The issue of identification of covariance structures, which arises in a number of different contexts, has been so far linked to conditions on the true parameters to be estimated. In this paper, this limitation is removed.As done by Johansen (1995, Journal of Econometrics 69, 112–132) in the context of linear models, the present paper provides necessary and sufficient conditions for the identification of a covariance structure that depends only on the constraints and can therefore be checked independently of estimated parameters.A structure condition is developed, which only depends on the structure of the constraints. It is shown that this condition, if coupled with the familiar order condition, provides a sufficient condition for identification. In practice, because the structure condition holds if and only if a certain matrix, constructed from the constraint matrices, is invertible, automatic software checking for identification is feasible even for large-scale systems.Most of the paper focuses on structural vector autoregressions, but extensions to other statistical models are also briefly discussed.I thank all the participants at the meeting held in Pavia on June 11, 2004, in honor of Carlo Giannini for their comments; it goes without saying that Carlo himself provided not only acute observations on the day but also the main inspiration for this piece of work. Sadly, Carlo passed away on September 11, 2004, and this paper is dedicated to his memory. Par Osterholm spotted several mistakes in an earlier version and helped me clarify some implementation details. Thanks are also due to Gianni Amisano, Bruce Hansen, Giulio Palomba, Paolo Paruolo, and two anonymous referees. The usual disclaimer obviously applies.

This paper provides an estimate of the relationships between wages, working hours and the use of computers at the workplace for the Italian labour market. On the methodological side, we other a contribution on the appropriate procedure for estimating the above effects: it is shown that the simultaneity between wages and hours must be taken into account when specifying the statistical model for the data and, furthermore, that the interactions between explanatory variables plays a significant role that cannot be neglected. Our empirical findings are also of interest: by controlling for computer skill, workers' ability and many other covariates, we found that only for higher-level white collars the average wage premium associated with computer usage is in the same order of magnitude as the one estimated for the US, Germany and France, while the effect vanishes for lower qualifications. The use of computers at work increases the number of hours worked, although this effect is small and much lower than that estimated for the US. Moreover, since hourly wages have a negative impact on hours worked, computers seem to exert little, if any, impact on working time.

The adoption of Information and Communication Technologies (ICTs) among small and medium sized enterprises (SMEs) is a phenomenon that has been the object of increasing interest by the academic literature and the policy makers. In this paper, we carry out an econometric analysis of a sample of 168 enterprises located in the Ancona Province (Central Italy). An important result is that, in order to understand the main factor that drive SMEs to the adoption of ICTs, it is useful to divide the available technologies according to a taxonomy based on their typical use. In all cases, however, the availability of highly educated workers turns out to be a key factor. Policy implications are also discussed.

This paper offers a methodological contribution to the empirical analysis of the relationships between banking and economic growth by suggesting a new indicator for the state of development of the banking system based on a measure of bank microeconomic efficiency. This choice helps to overcome the problem of causality and to capture the effects of the banks' allocative activity. This new approach is then applied to analyse the relationship between the banking system and economic growth in the Italian regions, through a dynamic panel technique. The empirical results show the existence of an independent effect exerted by the efficiency of banks on regional growth.

In questo lavoro si oltre un contributo metodologico all'analisi empirica dei rapporti tra sistema bancario e crescita economica, proponendo una nuova proxy per lo sviluppo del sistema bancario che consente di catturare la funzione allocativa delle banche e di superare in parte il problema della causalità. A questo scopo, dopo aver elaborato un indicatore di inefficienza dei sistemi bancari regionali per il periodo 1982-1991 sulla base di microdati, presentiamo delle stime panel dinamiche sull'evoluzione del valore aggiunto pro capite. Da queste ultime emerge che l'efficienza del sistema bancario svolge un ruolo non trascurabile nel determinare l'impulso che il credito dà alla crescita delle regioni.

Multivariate GARCH models constitute the workhorse of empirical applications in several fields, a notable example being financial econometrics. Unfortunately, ML (or quasi-ML) estimation of such models, although relatively straightforward in theory, is often made difficult by the fact that available software relies on numerical methods for computing the first derivatives of the log-likelihood; the fact that these models often include several dozens of parameters makes it impractical to estimate even medium-sized models. In this paper, closed-form expressions for the score of the BEKK model of Engle and Kroner (1995) are obtained, and strategies for efficient computation are discussed.

In this paper we test the hypothesis formulated in previous work, according to which the relation-ships between small and large firms are the results of two opposite forces. On one hand, the large firms can work as local development multipliers, as from theoretically and practically well built propagation models. On the other hand, the same large firms, mainly in weak regional sectors and contexts can grind local supply, especially by recruiting as employees the potential small entrepre-neurs. In general we cannot predict exactly which of the two forces is going to overcome, but we can analyse different periods, sectors and territorial contexts. The topic is relevant in the Italian public policies, in particular for the role given to the large firms by the regional development poli-cies, and according to the restructuring processes that they are interested in. The so-called planning contracts, for example, are part of these policies in Italy and they were adopted by the Government to promote industrial development in least favoured areas of the country. We do not intend to give a final answer to the issue, but try to suggest a methodology that could be further developed. We built up a database for this analysis. In particular, the census data were col-lected from 1951 to 1991, with coverage of half century of national economic history. Our empiri-cal model shows clearly different patterns in North and Centre Italy, versus the Mezzogiorno.

Italian Abstract Questo lavoro presenta una verifica dell'ipotesi formulata in Florio (1991, 1996) secondo cui le relazioni fra grandi e piccole imprese sono la risultante di due forze opposte. Da un lato le grandi imprese possono agire come propulsori di sviluppo locale secondo modelli di propagazione ben studiati dal punto di vista teorico ed empirico. D'altro canto le stesse grandi imprese, soprattutto in settori e contesti ambientali deboli, possono avere effetti di spiazzamento dell'offerta locale in particolare attraverso il reclutamento come dipendenti di potenziali piccoli imprenditori. Quale delle due forze prevalga non puo essere detto in generale, ma va esaminato in diversi periodi, settori, contesti regionali. Il tema ha particolare rilevanza nel caso italiano sotto il profilo delle politiche pubbliche, in particolare del ruolo che le politiche di sviluppo regionale e per l'occupazione dovrebbero assegnare alle grandi imprese, anche in considerazione dei processi di ristrutturazione che le coinvolgono (Giunta, 1997). Fra queste politiche in Italia, ad esempio, vi sono i contratti di programma con i quali lo Stato sussidia grandi progetti industriali in aree depresse (Florio, Giunta, 1998). Il presente testo non intende rispondere in modo definitivo alla questione proposta, ma suggerisce una metodologia che potra essere ulteriormente sviluppata. Per lo svolgimento dell'analisi e stata costruita una base-dati che comprende dati censuari e dati Inps a base provinciale. In particolare i dati dei censimenti sono stati raccolti dal 1951 al 1991, con una copertura quindi pari a mezzo secolo di storia economica nazionale, aggiornando e migliorando un analogo esercizio presentato in Florio (1991). English Abstract: This paper presents a verification of the hypothesis formulated in Florio (1991, 1996) according to which the relationships between large and small enterprises are the result of two opposing forces. On the one hand, large companies can act as drivers of local development according to well-studied propagation models from a theoretical and empirical point of view. On the other hand, the same large companies, especially in sectors and weak environmental contexts, can have a displacement effect on local supply, in particular through recruitment as employees of potential small entrepreneurs. Which of the two forces prevails can not be said in general, but must be examined in different periods, sectors, regional contexts. The issue is particularly relevant in the Italian case in terms of public policies, in particular the role that regional development and employment policies should assign to large companies, also in consideration of the restructuring processes that involve them. Among these policies in Italy, for example, there are the program contracts with which the State subsidizes large industrial projects in depressed areas. This text does not intend to respond definitively to the proposed question, but suggests a methodology that can be further developed. For the conduct of the analysis was built a database that includes census data and provincial-based INPS data. In particular i census data were collected from 1951 to 1991, thus covering half a century of national economic history, updating and improving a similar exercise presented in Florio.

In questo lavoro si propone una analisi empirica dei flussi lordi nel mercato del lavoro, basata sui dati individuali dell'indagine sui bilanci delle famiglie italiane nel 1993 proposta dalla Banca d'Italia. Per le stime delle probabilita' di transizione tra stati (occupato, disoccupato, non forza di lavoro) ci serviamo di un modello markoviano, quindi utilizziamo un modello logit multinomiale per illustrare la dipendenza di tali probabilita' dalle caratteristiche individuali.

This paper presents the Gretl function package DPB for estimating dynamic binary models with panel data. The package contains routines for the estimation of the random-effects dynamic probit model proposed by Heckman (1981b) and its generalisation by Hyslop (1999) and Keane and Sauer (2009) to accommodate AR(1) disturbances. The fixed-effects estimator by Bartolucci and Nigro (2010) is also implemented. DPB is available on the Gretl function packages archive. Gretl function package, Random-Effects Dynamic Probit model, Quadratic Exponential model, Gauss-Hermite quadrature, simulated Maximum Likelihood, Conditional Maximum Likelihood