The purpose of this research is to investigate dividend policy, including its impact on share prices of transportation providers and related service companies, by comparing generalized regression neural networks with conventional regressions. Our results using regressions reveal that for Europe and for the US and Canada the market-to-book-value, as a surrogate for growth opportunities, fulfils expectations of pressures on dividends leading to a negative association with dividend yields in accordance with the pecking order theory. Neural network analysis indicates a clear role for growth opportunities for the US and Canada pointing to an underlying confidence on the part of transportation companies in their own internal policies. Finally, risk is rewarded especially in Europe.
|Number of pages||18|
|Journal||Journal of International Financial Markets, Institutions and Money|
|Early online date||1 May 2012|
|Publication status||Published - Oct 2012|
- Dividend yield
- Market-to-book value
- Neural networks