在本文中,我們收集國內股票上市公司的產業效應變數(industry effects;Chava and Jarrow,2004)、市場導出變數(market-driven variables;Shumway,2001)、以及財務比率變數(financial ratios),將其應用至離散型模式(discrete-time model;Allison,1982),以建立財務危機模式。我們應用最大概似法(maximum likelihood method)估計模式的參數值,導出參數估計式的漸近常態分配(asymptotic normal distribution)。實證研究結果顯示,本文所介紹的離散型財務危機模式(discrete-time financial distress model),對公司財務危機的預測,比羅吉特模式(logit model;Ohlson,1980)以及機率單位模式(probit model;Zmijewski,1984),有更好的樣本外(out-of-sample)預測能力。
In this paper, the discrete-time model (Allison, 1982) is applied to predict financial distress using industry effects (Chava and Jarrow, 2004), market-driven variables (Shumway, 2001), and financial ratios for companies listed in Taiwan Stock Exchange. The maximum likelihood method is employed to estimate the values of parameters of the discrete-time financial distress model. The resulting estimates are analyzed through their asymptotic normal distributions. Empirical studies demonstrate that our strategy developed from the discrete-time financial distress model can yield more accurate out-of-sample forecasts than alternatives based on the logit model of Ohlson (1980) and the probit model of Zmijewski (1984).