近年來，有許多研究致力於分析不同港口間的經營效率，然而，相關研究中，對於決策單位太少的問題與計算效率分數時使用之投入與產出權重的限制問題卻缺少深入探討。本研究利用資料包絡分析法 (DEA)之區域保證 (AR) 模式，探討臺灣主要港口的技術效率及純粹技術效率。 DEA是一種無母數的分析方法，與傳統上使用產品情況來估計效率作比較，此法只需一個以上的產出資料，也不需事先明確界定投入與產出之間的關係，因此，相當適 合應用於評估港口效率。AR模式則可以克服傳統 DEA模式中投入和產出項目之虛擬乘數過於自由所衍生的問題。本研究利用 4項投入及 3項產出來評估港口的經營效率。研究結果顯示，在假定固定與變動規模報酬的情況下，基隆港相對於高雄及臺中二港而言，顯得最不具經營效率。主要原因在於基隆港投入之員工人數、港埠支出、船席空間及拖船噸位具有龐大的差額所致。本研究亦對港口當局提出一些政策上的建議及未來研究的方向。

Recently, considerable attention has been focused on the performance of various ports in terms of efficiency. However, available studies have not provided a satisfactory answer to the problem of few decision-making units (DMU) and a priori specification of input and output weights. Data envelopment analysis (DEA) and assurance region (AR) models were used in this paper to investigate the technical efficiency and pure technical efficiency of the major ports in Taiwan. The DEA technique is useful in resolving the measurement of port efficiency because the calculations are non-parametric, can handle more than one output and do not require explicit a priori determination of relationships between outputs and inputs, a(an ) s is required for conventional estimation of efficiency using production functions. The AR approach overcomes the issues caused by free running of input and output weights in basic DEA models. Efficiency measures in this study were based on four inputs and three outputs. The results show the Keelung Port (KLG) is the most inefficient port among the three samples based on constant and variable returns to scale assumptions, mainly due to the enormous slack in their number of labours, total expense, ship berths and tons of tug boats. This study also draws some policy implications for ports and recommends certain areas for future research.