Margherita Gerolimetto

Testing structural breaks versus long memory with the Box–Pierce statistics: a Monte Carlo study

Several studies have found that occasional-break processes may produce realizations with slowly decaying autocorrelations, which is hardly distinguished from the long memory phenomenon. In this paper we suggest the use of the Box–Pierce statistics to discriminate long memory and occasional-break processes. We conduct an extensive Monte Carlo experiment to examine the finite sample properties of the Box–Pierce and other simple tests statistics in this framework. The results allow us to infer important guidelines for applied statistics in practice.

An Empirical Strategy to Detect Spurious Effects in Long Memory and Occasional-Break Processes

Long-range dependence and structural changes in level are intimely related phenomena and it is very difficult to separate the two effects. In this article, we present an empirical procedure to distinguish between long-memory and occasional-break processes. An extensive Monte Carlo experiment illustrates the performance of the procedure and an application to real data is also included.

Business cycle dynamics across the US states

Abstract The analysis of synchronization among regional or national business cycles has recently been attracting a growing interest within the economic literature. Far less attention has instead been devoted to a closely related issue: given a certain level of synchronization, some economies might be systematically ahead of others along the swings of the business cycle. We analyze this issue within a system of economies and show that leading (or lagging behind) is a feature that does not occur at random across the economies. In addition, we investigate the economic drivers that could explain this behavior. To do so, we employ data for 48 conterminous US states between 1990 and 2009.

Instrumental variables estimation of stationary and non‐stationary cointegrating regressions

Instrumental variables estimation is classically employed to avoid simultaneous equations bias in a stable environment. Here we use it to improve upon ordinary least squares estimation of cointegrating regressions between nonstationary and/or long memory stationary variables where the integration orders of regressor and disturbance sum to less than 1, as happens always for stationary regressors, and sometimes for mean-reverting nonstationary ones. Unlike in the classical situation, instruments can be correlated with disturbances and/or uncorrelated with regressors. The approach can also be used in traditional non-fractional cointegrating relations. Various choices of instrument are proposed. Finite sample performance is examined.

Nonparametric Regression with Spatially Dependent Data

In this paper we present a new procedure for nonparametric regression in case of spatially dependent data. In particular, we extend usual local linear regression (along the lines of Martins-Filho and Yao, 2009) and propose a two-step method where information on spatial dependence is incorporated in the error covariance matrix, estimated nonparametrically. The finite sample performance of our proposed procedure is then shown via Monte Carlo simulations for various data generating processes.

Regional Convergence and Aggregate Business Cycle in the United States

Magrini S., Gerolimetto M. and Engin Duran H. Regional convergence and aggregate business cycle in the United States, Regional Studies. The existing literature on convergence largely ignores the effect of aggregate fluctuations on the evolution of income disparities. However, if regional disparities follow a distinct cyclical pattern in the short run, the period of analysis should be chosen with great care to avoid distortions in the results. By analysing convergence among forty-eight conterminous US states through the distribution dynamics approach, it is shown that these distortions could be quite sizeable. Moreover, when convergence is analysed over an appropriate period that includes only complete cycles (1989–2007), results show that regional disparities exhibit a pro-cyclical behaviour and that the underlying long-run tendency is towards divergence.

A Novel Look at Long-run Convergence Dynamics in the United States

When regional disparities follow a cyclical short-run pattern, convergence analysis results can be sizably distorted. To tackle this issue, we propose a method based on the extraction of the trend from regional income time series that eschews misleading results when the nature of the cyclical pattern changes over time. Using real per capita personal income data for forty-eight conterminous US states and the distribution dynamics approach, we identify the following three distinct consecutive phases: strong convergence (1930–1970), substantial persistence (1971–1980), and divergence (1981–2010).

Analysing Wine Demand With Artificial Neural Networks

In this paper we analyse wine demand in Italy with microdata. Instead of estimating a parametric model, we study the demand following a non parametric approach by means of Artificial Neural Networks. The input set includes the usual economic variables (price and income) and some sociodemographic factors that are also shown to be relevant for demand analysis. We compute price elasticities using two different nonparametric procedures. (JEL Classification: C14, C21, Q11, Q13)

Struttura ed evoluzione delle esportazioni italiane di vino da tavola e a denominazione di origine

In the last decades the Italian wine market is experiencing a strong transformation as well as an intense and continuous process of internationalisation. The contribute of Italian wines in the international market is very relevant. In 2005 Italy is the second exporting country: the exports’ value is more than 3 billions dollars, the market share is 18% (Unioncamere, 2007). Wine is one of the most important products of the Italian agrifood trade balance, its incidence is around 15% of Italian agrifood exports (inea, 2005). The intense evolution of the trade reflects the need of different frequency and place to consume the product. At the same time, demand is more and more segmented and open to high quality wine. Given the relevance of the changes in the international trade, the objective is to study, by means of time series analysis methods, structure and dynamics of Italian exports of wine for different product typologies, considering both white and red wines and their classification in table and do wine. The data set (istat/ice) consists of monthly observations of world exports for all kinds of wine relatively to 13 years (January 1996 - December 2007). 13 product categories have been identified for the analysis on the basis of wine typology (vqprd or other wines), colour (white, red or rose) and container (smaller or greater than 2 litres).

A test for fractional cointegration using the sieve bootstrap

The concept of fractional cointegration (Cheung and Lai in J Bus Econ Stat 11:103–112, 1993) has been introduced to generalize traditional cointegration (Engle and Granger in Econometrica 55:251–276, 1987) to the long memory framework. In this work we propose a test for fractional cointegration with the sieve bootstrap and compare by simulations the performance of our proposal with other semiparametric methods existing in literature: the three steps technique of Marinucci and Robinson (J Econom 105:225–247, 2001) and the procedure to determine the fractional cointegration rank of Robinson and Yajima (J Econom 106:217–241, 2002).