互相依賴的區分母體持續時間模型：農會信用部擠兌的應用

Interdependently Split Population Duration Model: An Application to Bank Runs of Credit Departments of Farmers’ Institutions

Schmidt 與Witte (1989) 提出的區分母體持續時間模型，將母體分成「是否」和「持續時間」兩部分；受限於積分沒有封閉式的限制，假設這兩部分的決定是互相獨立的。本文沿用Leung 與Yu (2002、2007) 的計量技巧，利用蒙地卡羅模擬估計法解決積分的限制，鬆綁「是否」部分和「持續時間」部分的決定是互相獨立的假設，提出互相依賴的區分母體持續時間模型。在此建構下，獨立的區分母體持續時間模型是互相依賴的區分母體持續時間模型的巢氏模型。我們將這個模型應用到探討農會信用部發生擠兌的問題上，以AIC 值、概似比檢定、t-檢定比較各種不同的持續時間模型，結果顯示互相依賴的區分母體持續時間模型優於其他模型。實證結果發現，融通資金比、逾放比率愈高者，發生擠兌機率愈高且愈早發生擠兌；流動性比率愈高者，發生擠兌機率愈低且愈晚發生擠兌。而平均存款利率較高者，擠兌危險率愈高，與Schumacher (2000) 的結果一致。

Schmidt and Witte (1989) present a split population duration model inwhich the decisions of whether and when to start an event must beindependent due to the absence of a closed-form result for theintegration. This paper following Leung and Yu (2002, 2007) develops aninterdependently split population duration model which allows theinterdependence of the decisions of whether and when to start an event.We apply the Monte Carlo simulation to resolve the integration problem.We show the independent split population duration model is hencenested in our interdependently split population duration model. Ourmodel is applied to investigate the bank runs events of the creditdepartments of farmers’ institutions. The results show the superiority ofour model to other duration models according to the criteria of AIC,likelihood ratio test, and t-ratio test. The empirical results show that boththe ratio of borrowing capital to total capital and the overdue ratio are positively correlated with the probability of runs and the hazard rate torun while the liquidity ratio is negatively correlated with them. Moreimportantly, our result shows banks with higher deposit interest rates areeasier to trigger runs, which is consistent with the finding of Schumacher(2000).