Boosting and bagging are two widely used ensemble methods for classification. Their common goal is to improve the accuracy of a classifier combining single classifiers which are slightly better than random guessing. Among the family of boosting algorithms, AdaBoost (adaptive boosting) is the best known, although it is suitable only for dichotomous tasks. AdaBoost.M1 and SAMME (stagewise additive modeling using a multi-class exponential loss function) are two easy and natural extensions to the general case of two or more classes. In this paper, the adabag R package is introduced. This version implements AdaBoost.M1, SAMME and bagging algorithms with classification trees as base classifiers. Once the ensembles have been trained, they can be used to predict the class of new samples. The accuracy of these classifiers can be estimated in a separated data set or through cross validation. Moreover, the evolution of the error as the ensemble grows can be analysed and the ensemble can be pruned. In addition, the margin in the class prediction and the probability of each class for the observations can be calculated. Finally, several classic examples in classification literature are shown to illustrate the use of this package.
The impact of crises on the long-term sustainability of small and medium-sized enterprises (SMEs) has been attracting growing interest in the literature and from governments due to the significance of such companies with respect to economic growth, innovation, and employment. Although failure prediction models have been proposed based on accounting and other qualitative information, little is known regarding the influence of stakeholders on the failure process of SMEs. From the perspective of long-term sustainability, this article analyzes the role of the financial influence of stakeholders on the likelihood of business failure. An empirical study was carried out on a sample of 2352 Spanish SMEs, examining the differences between failed and non-failed SMEs and using a classification tree methodology to investigate the role played by each type of stakeholder in overcoming crisis events. The study provides empirical evidence regarding the relative importance of stakeholders to SMEs under conditions of financial distress, and proposes their categorization on the basis of their control over firms’ financial resources. Specifically, the analysis reveals that the capacity of the firm to generate sustainable wealth over time and to overcome critical situations is dependent on the most critical stakeholders. Workers, customers, and suppliers are the most important in ensuring the long-term sustainability of SMEs during the first stages of a crisis. Following the initial operational problems, other creditors (financial institutions) become relevant. In this sense, the results of this study encourage firms and governments to develop cooperation strategies with stakeholders (co-responsibility) in line with the proposed conceptual models of business sustainability.
Purpose
The purpose of this paper is to explore the effects of mergers and acquisitions (M&As) on innovation and profitability in large European firms.
Design/methodology/approach
Using information from a unique micro-longitudinal database of top European R&D investors and information from the European Commission (EC) Merger Control Authority, dynamic panel estimations with firm-level fixed effects are performed. Moreover, the paper presents a qualitative case study of a merger in the European electronic and electrical equipment industry.
Findings
The analysis of a sample of 562 M&As authorized by the EC Merger Control Authority shows that mergers positively influence the R&D intensity and profitability of top companies in the European Union over the period 2004–2012. Furthermore, empirical evidence shows that the timing and magnitude of these effects differs. In particular, the positive effect of mergers on R&D intensity is found for the short and large term while they influence profitability only in the large term.
Originality/value
This paper makes several contributions. First, unlike other studies on this topic, it investigates the effects of M&As using firm-level panel data on the top 1,000 European R&D companies instead of only examining a case study. Second, a unique data set has been used, which collects information on large European firms from the European Industrial R&D Investment Scoreboard and the EC antitrust authority. Finally, the paper accounts for the casual link between innovation effort and profitability when evaluating the potential effect of M&As on the R&D intensity and profitability of large European firms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.