Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Bastos, J. A. & Ramalho, J. J. S. (2016). Nonparametric models of financial leverage decisions. Bulletin of Economic Research. 68 (4), 348-366
Exportar Referência (IEEE) 
J. A. Bastos and J. J. Ramalho,  "Nonparametric models of financial leverage decisions", in Bulletin of Economic Research, vol. 68, no. 4, pp. 348-366, 2016
Exportar BibTeX 
@article{bastos2016_1732201802781,
	author = "Bastos, J. A. and Ramalho, J. J. S.",
	title = "Nonparametric models of financial leverage decisions",
	journal = "Bulletin of Economic Research",
	year = "2016",
	volume = "68",
	number = "4",
	doi = "10.1111/boer.12054",
	pages = "348-366",
	url = "http://onlinelibrary.wiley.com/doi/10.1111/boer.12054/abstract"
}
Exportar RIS 
TY  - JOUR
TI  - Nonparametric models of financial leverage decisions
T2  - Bulletin of Economic Research
VL  - 68
IS  - 4
AU  - Bastos, J. A.
AU  - Ramalho, J. J. S.
PY  - 2016
SP  - 348-366
SN  - 0307-3378
DO  - 10.1111/boer.12054
UR  - http://onlinelibrary.wiley.com/doi/10.1111/boer.12054/abstract
AB  - This paper applies nonparametric decision tree models to the analysis of financial leverage decisions. This approach presents three appealing features: (i) the relationship between leverage and explanatory variables is not predetermined but is derived from information provided by the data, (ii) the models respect the fractional nature of leverage ratios, and (iii) each covariate is allowed to influence in different ways the financial leverage decisions of firms automatically assigned to different groups. Based on a data set of Portuguese firms, decision trees are used to tackle both classification (the decision to issue debt) and regression (the decision on the amount of debt to be issued, conditional on using debt) problems. It is found that: (i) two-part models are the most appropriate specification for explaining the overall amount of debt used by firms, (ii) there are no drastic differences between the results produced by tree and parametric models, although some divergences may arise, and (iii) tree models suggest relationships between covariates and leverage that parametric models fail to capture, especially when the sample size is small.
ER  -