Showing 1 - 10 of 21
We study the effects of ARCH errors on the performance of the commonly used lag length selection criteria. The most important finding of this study is that SIC, FPE, HQC and BIC perform considerably well in estimating the true autoregressive lag length, even in the presence of ARCH errors. Thus,...
Persistent link: https://www.econbiz.de/10010835834
The Japanese stock market has important linkages with stock markets worldwide. This note examines whether the Japanese stock market is efficient in the past two decades. The profitability of various time-series model based trading rules is evaluated. It is found that most of these trading rules...
Persistent link: https://www.econbiz.de/10010835883
Consider a simple change-point model with a binary regressor. We examine the consistency of the change-point estimator when the regressor is subject to misclassification. It is found that the time of change can always be identified. Further, special cases where the structural parameters can also...
Persistent link: https://www.econbiz.de/10010836009
Conventional two-sided matching game is a one-period game. In this note, we contribute to the existing literature by examining a multi-period two-sided matching problem allowing for the possibility of a divorce. We assume that the matching game is played repeatedly and the payoff matrix changes...
Persistent link: https://www.econbiz.de/10010836109
This paper examines the impact of the 1997 Asian Financial Crisis on the linkages between the Singapore and five Asian-Pacific stock markets. We show that the interdependence between these markets has intensified after the crisis. Before the crisis, only the Malaysian stock market is found to be...
Persistent link: https://www.econbiz.de/10005110594
This paper studies the profitability of the Moving Average Convergence-Divergence (MACD) trading rule under three different crossing rules: the MACD zero line, the 9-day and 14-day signal lines. It is found that the trading rules perform well in the stock markets of Germany and Hong Kong. Our...
Persistent link: https://www.econbiz.de/10005110776
This note examines a new problem in the structural-change literature. A fractionally integrated model is assumed to experience a change in the differencing parameter at an unknown time. We develop consistent estimators of the change point and the pre- and post-shift differencing parameters.
Persistent link: https://www.econbiz.de/10005110924
The Japanese stock market has important linkages with stock markets worldwide. This note examines whether the Japanese stock market is efficient in the past two decades. The profitability of various time-series model based trading rules is evaluated. It is found that most of these trading rules...
Persistent link: https://www.econbiz.de/10005196487
Most of the existing structural-change models presume that the impact of a change is instantaneous and occurs at the same time for all individuals. In this paper, we develop a new structural-change model to measure the lag length between the time when an economic crisis breaks out and the time...
Persistent link: https://www.econbiz.de/10005094656
We study the effects of ARCH errors on the performance of the commonly used lag length selection criteria. The most important finding of this study is that SIC, FPE, HQC and BIC perform considerably well in estimating the true autoregressive lag length, even in the presence of ARCH errors. Thus,...
Persistent link: https://www.econbiz.de/10005416837