Is the prediction accuracy affected by the method used in the ensemble of the classifiers? This paper is a sequel of our experiment in order to find an answer for such question. Previously, we had conducted an experiment by using single classifiers in the machine learning against traditional statistical methods. The results showed that single classifiers in machine learning perform well compared to the traditional statistical methods. Still, we believe that there is another way to increase the prediction accuracy of these classifiers. In this paper, we conducted another experiment by combining these classifiers in predicting currency crisis of 25 countries. The combined classifiers are support vector machine with k-nearest neighbor, logistic regression with k-nearest neighbor and finally LADTree with knearest neighbor. These three combined classifiers are tested on 13 chosen macroeconomic indicators which the data is taken from first quarter 1980 to third quarter 2012. The results of this experiment showed that these three different combined classifiers averagely have same higher accuracy and quite comparable. Our proposed method, nearest neighbor tree has the highest area under ROC curve number among these three combined classifiers although in terms of computational time it took longer running times than the others.

No abstract

This paper investigates the degree of volatility and asymmetric behavior of real exchange rates in East Asian. Exponential generalized autoregressive heteroskedasticity (EGARCH) is deployed to estimate the volatility of the exchange rate returns before and after the 1997 Asian financial crisis. We found that the EGARCH (1,1) specification fits the monthly currency series of the Asian currencies well, suggesting that volatility in exchange rates is time varying and asymmetric. The results show that before the crisis, only three currencies displayed evidence of asymmetries in their conditional variance. After the sharp fall in their currencies, all but one showed a significant increase in volatility and asymmetric effect. We conclude that the crisis caused a contagion that spread through the currency markets. The results of this study underline the importance of economic and political stability in the member countries for the stability of the regional economy.

This study examines the moderating effect of country governance on the relationship between firm governance and firm performance in emerging countries. We employ a panel regression model on 21 emerging countries over the period 2007 to 2016. We find that poor firm governance is negatively linked to Tobin's Q, but positively linked to return on assets (ROA) and return on equity (ROE), while country governance has a consistent positive moderating effect on all three performance variables. Specific country governance dimensions include voice and accountability, government effectiveness, regulatory quality, the rule of law and control of corruption also have significant positive moderating effects. We further find that only a strong legal environment can compensate for the ineffectiveness of firm governance but not in a weak legal environment and only countries with strong country governance can positively affect firm value.

No abstract