本研究以中國上市公司之上海和深圳證券交易所之A股為研究對象，以cascaded logistic model建構財務危機預警模型，並以absorbing Markov chain推估危機時程，預測企業由發生危機到退市與發生危機到恢復正常交易所需的時程。本研究先以cascaded logistic model所估計出的機率，將公司分為五群，應用absorbing Markov chain求算ST公司退市或撤銷ST前，停留在ST股的時間。本研究發現在推估撤銷ST公司部份，absorbing Markov chain對於停留時程的估計有一定的準確率。在估算退市公司部份，考量危機機率分佈狀況之模型對於退市公司停留時程之估算有較好的效果。

The paper uses the companies of the A-share in the stock market of Shanghai and Shenzhen as a sample. And uses Cascaded logistic model to construct prediction model and uses absorbing Markov chain to estimate enterprises distress time. The research uses cascaded logistic model to estimate probability and uses the probability to classify five groups and applies absorbing Markov chain to estimate enterprises distress time. The research finds uses absorbing Markov chain to estimate distress time is good.