A Smooth Transition Autoregressive Conditional Duration Model
-
Min-Hsien Chiang
This study presents a novel model for analyzing duration data, called the smooth transition autoregressive conditional duration model of price and duration, which considers past price changes and durations. The model enables the process of the conditional expected duration to switch in a smooth transition way, broadening the autoregressive conditional duration (ACD) model in Engle and Russell (1998). The model is applied to empirical data, and estimation results indicate that the process of the expected duration is nonlinear. The expected trade duration behavior on the market opening is affected by past trade durations, while the expected trade duration behavior during the trading hours is affected by past price changes and trade durations. Expected trade durations are much more persistent in the upward market compared to the downward market. Shocks to trade durations are more persistent on the market opening and gradually decrease in the downward market.
©2011 Walter de Gruyter GmbH & Co. KG, Berlin/Boston
Artikel in diesem Heft
- Article
- Spurious Inference in the GARCH (1,1) Model When It Is Weakly Identified
- Gains from Synchronization
- Time Series Models for Forecasting: Testing or Combining?
- Short-Run Patience and Wealth Inequality
- A Smooth Transition Autoregressive Conditional Duration Model
- Fractionally Integrated Long Horizon Regressions
- A New Application of Exact Nonparametric Methods to Long-Horizon Predictability Tests
Artikel in diesem Heft
- Article
- Spurious Inference in the GARCH (1,1) Model When It Is Weakly Identified
- Gains from Synchronization
- Time Series Models for Forecasting: Testing or Combining?
- Short-Run Patience and Wealth Inequality
- A Smooth Transition Autoregressive Conditional Duration Model
- Fractionally Integrated Long Horizon Regressions
- A New Application of Exact Nonparametric Methods to Long-Horizon Predictability Tests
