Permanent Breaks and Temporary Shocks in a Time Series

초록

A new stochastic time-series process is proposed to describe both permanent shocks related to structural breaks and temporary shocks. A permanent break is captured by a Poisson-jump or a Bernoulli-jump process, and a temporary shock is represented by a white noise process. Data on US nominal gross domestic product, total unemployment rate and velocity of money are chosen to estimate the proposed model. The parameters, the probability and size of permanent breaks as well as the size of temporary shocks, are estimated using generalized method of moments estimation. Most shocks are permanent shocks. The Kalman filter is used as a convenient way to obtain forecasts. Lastly, a calibration test is conducted that shows that the proposed model is better calibrated than a competitor model-the autoregressive integrated moving average with outliers.

키워드