A second-moment regime-switching regression, which considers not only a switching intercept and a switching slope, but a switching error variance is applied to investigate the impacts of the exchange rate uncertainty (ERU) on the corporate values (CVs) for the industries concerned in Taiwan. Two different regimes of a strong-impact and a weak-impact are identified. However, the dominant power varies from industry to industry. The Wald statistics for the null of equality are mixed, which shows that if the Markov-switching (MS) model is appropriate, the ERU might not be the major factor but other factors, which could switch the CVs of Taiwan's industries. Nonetheless, for the model's volatility influence, the data of eight industries are shown to fit a two-state model when the volatility is stimulated. Finally, based on the 10% significant level, a two-state first-order MS model is appropriate for the "goodness of fit" analysis.
2002年國立台灣大學財務金融國際研討會論文集=Proceedings of 2002 NTU International Conference on Finance，25頁