Search

According to a recent trend of research, there is a growing interest in applications of machine learning techniques to business analytics. In this work, both supervised and unsupervised machine learning techniques are applied to the analysis of a dataset made of both family and non-family firms. This is worth investigating, because the two kinds of firms typically differ in some aspects related to performance, which can be reflected in balance sheet data. First, binary classification techniques are applied to discriminate the two kinds of firms, by combining an unlabeled dataset with the labels provided by a survey. The most important features for performing such binary classification are identified. Then, clustering is applied to highlight why supervised learning can be effective in the previous task, by showing that most of the largest clusters found are quite unequally populated by the two classes.

The present book is concerned with spatial interaction modelling. In particular, it aims to illustrate, through a collection of methodological and empirical studies, how estimation approaches in this field recently developed, by including the tools typical of spatial statistics and spatial econometrics (Anselin 1988; Cressie 1993; Arbia 2006, 2014), into what LeSage and Pace (2009) deemed as ‘spatial econometric interaction models’.

The present volume showcased a series of papers related to some of the most recent developments in the field of spatial econometric methods applied to spatial interaction modelling. In particular, this book was motivated by the need to testify, through a collection of methodological and empirical studies, how the various approaches that have been present in this field in the last decades have recently developed, by including tools that are typical of spatial statistics and spatial econometrics, giving birth to a somewhat novel discipline characterized by a body of methods and techniques known under the heading of spatial econometric interaction models (LeSage and Pace 2009).

This study attempts to replicate the original Le Clerc et al’s (1988, 1994) work on foreign branding effects in the context of a developing Latinamerican country, such as Chile. We extend the original study and existing research by including two foreign languages: French and English, plus the country language: Spanish. In general, we found consistent results with the original Le Clerc et al. studies (1988, 1994), confirming that foreign branding can have an impact on brand evaluations. Also, this study shows that the effects of particular foreign branding strategies (i.e. French or English) do vary depending on the particular product category (within the hedonic product type). For example, English branding can generate more positive evaluations for fountain pens, and French can generate better evaluations for perfumes. Another interesting finding, is that foreign branding effects are sensitive to the market context and the native language. English, in the context of a Spanish-speaking country such as Chile, appears to generate better results than French over all product categories (hedonic and utilitarian). English branding, can also generate similar brand evaluations than domestic branding (Spanish) in the case of utilitarian products. Therefore, English branding appears to be a safer and effective branding strategy for global marketers.

Recently, an investigation of unobserved and time-varying multilateral resistance and omitted trade determinants has assumed a prominent role in order to precisely measure the Euro effects on trade. We implement two methodologies: the factor-based gravity model by Serlenga and Shin (The Euro Effect on Intra-EU Trade: Evidence from the Cross Sectionally Dependent Panel Gravity Models, Mimeo, University of York, 2013) and the spatial-based techniques by Behrens et al. (J Appl Econ 27:773–794, 2012), both of which allow trade flows and error terms to be cross-sectionally correlated. Applying these approaches to the dataset over 1960–2008 for 190 country-pairs of 14 EU and six non-EU OECD countries, we find that the Euro impact estimated by the factor-based model amounts to only 4–5 %, far less than the 20 % estimated by the spatial-based model. The cross-section dependency test results also confirm that the factor-based model is more appropriate in accommodating correlation between regressors, and unobserved individual and time effects. Overall we may conclude that the trade-creating effects of the Euro should be viewed in the proper historical and multilateral perspective rather than in terms of the formation of a monetary union as an isolated event.

This paper applies spatial dynamic panel data models to analyse the labor market dimension of interregional population flows among German federal states in the period 1993–2009. Making use of recent improvements in the estimation of space-time dynamic panel data models and the computation of meaningful scalar summary measures for the obtained regression coefficients, the empirical results show that the network of German interregional gross migration flows is subject to serial and spatial autocorrelation patterns, which affect the interpretation of the considered regional labor market signals. Using a time-dynamic spatial Durbin model as preferred empirical specification, the results indicate that regional differences in real income growth, the labor participation rate and real-estate prices impact on interregional out-migration flows. The estimated coefficients signs of the obtained space-time summary measures thereby hint at the validity of the neoclassical migration model in predicting gross out-migration flows. In order to take a closer look at the dynamic evolution the direct and indirect network effects over time, cumulative multipliers for a time horizon of up to 10 years have been computed for each variable. The results show that the speed of adjustment of the migration response towards the long-run impact of labor market signals is fast and mostly occurs within the first 3 years. Regarding the interplay of the direct and indirect effects, the estimation results uniformly hint at additive linkages for all variables. Overall, the obtained results underline the importance of a decomposition of the total effects of labor market signals on interregional migration flows by means of their spatial and temporal network dynamics.