ABSTRACT
Under the framework of time trend breaks, the popular BSADF (backward Sup-ADF) test easily misidentifies the bubble processes. As an extending analysis, we construct a t-statistic to further identify the data feature of the detected bubble periods in BSADF test. For the sake of application, we examine the bubble phenomenon related to recent stock market activity in China. We find that a bubble period estimated by the BSADF test is spurious; the rapid rise of stock market on this period is driven by trend changes and has a solid foundation.
Disclosure statement
No potential conflict of interest was reported by the authors.