Abstract: We have developed a procedure for identifying continuous time, self-exciting, threshold, autoregressive models and applied the procedure to several real data sets. The performance of the fitted threshold models to real data is discussed and compared with that of the fitted linear models.
Key words and phrases: Continuous time models, dissolved oxygen content, Hang Seng Index, IBM stock price, Kalman filter, lynx, self-exciting threshold autoregression, state space, unequally spaced data.