臺灣博碩士論文加值系統

　　隨著社會環境不斷的變遷與資訊的快速流通，使得投資理財不再是銀行理財人員的專利，一般投資大眾也能透過許多的公開資訊來擬定投資策略。民國八十六年發生亞洲金融風暴，使得國內連續爆發因財務危機而導致公司瓦解的情形發生。近年來國內在全球性的不景氣下，更有許多公司無法承受景氣低迷而宣佈倒閉，這種種的跡象說明了公司經營績效的重要性。至於要如何評估上市公司的經營績效並非易事。本研究希望透過上市公司公開的財務報表，來瞭解上市公司的營運狀況，並利用多重比較程序的方法來評比企業的經營績效。在實驗設計的範疇中，當研究人員發現處理間的效應不相等時，接著會進行兩兩處理間的多重比較。然而在實際的問題中，研究人員更感興趣的是多個處理與最佳處理間的多重比較，或多個處理與平均處理間的多重比較。而這些多重比較程序均是假設處理為來自常態母體，且具有相同的母體變異數。而當處理間的母體變異數不相等時，本研究將利用一階段抽樣法來改善母體變異數不等時的多重比較程序。因此，本研究透過更佳的多重比較程序，來達到下列目的：
1. 篩選出最佳整體經營績效之上市公司，或與最佳整體經營績效之上市公司接近的上市公司。
2. 篩選出整體經營績效在平均水準之上的上市公司，並排除整體經營績效在平均水準之下的上市公司。
3. 綜合以上結果，提出經營績效優良之上市公司供投資大眾參考。

　　Under the any economic environment, the enterprises should evaluate their operation structures and nancial situations more frequently. According to the AREMOS Economics and Statistics Data Base, there are 638 listed companies on Taiwan stock market. However, how to objectively evaluate the performance of these listed companies is not an easy job. In this study, the investigator tries to utilize the company-published nancial statements to analyze the operations of the listed companies
and use multiple comparsion procedures to evaluate their performance. In the real world problem, it is often of primary interest to do multiple comparisons with the best and/or multiple comparisons with the average within its industry. In this study, since company's nancial data have di erent variabilities among them, the investigator will use one-stage sampling procedure to extend various multiple comparison procedures and then apply them to identify those superior companies.
In particular, the objectives of this study include:
1. Selecting the companies which have the best performance or those close to the best performance.
2. Selecting the companies which are better than the average performance, and ignoring those worse than the average performance.
3. Recommending listed companies with superior performance to potential investors.

1 緒論 9
1.1 研究背景 9
1.2 研究動機 9
1.3 研究目的 10
1.4 整合結論 10

2 文獻探討 13
2.1 與控制母體的多重比較程序 13
2.2 與最佳母體的多重比較程序 16
2.3 與平均數的多重比較程序 19
2.4 二階段抽樣法 23

3 研究方法 27
3.1 研究對象 27
3.2 評估變數之選取 27
3.3 一階段抽樣法 30
3.4 修正與最佳母體之多重比較 33
3.5 修正與平均數之多重比較 37

4 研究結果 41
4.1 評量指標之建立 41
4.2 單項指標之評量 43
4.3 整體評量指標之建立 58

5 結論與建議 101
5.1 結論與建議 101
5.2 後續研究方向 108

Bo nger, E. (1992). Multiple comparsions with 'Best' for Multivariate normal populations. Communications in Statistics - Theory and Methods, 21(4), 915-941.

Chen, H. J. and Lam, K. (1989). Single-stage interval estimation of the largest
normal mean under heteroscedasticity. Communications in Statistics - Theory
and Methods, 18(10), 3703-3718.

Dantzig, G. B. (1940). On the non-existence of tests of "student's t" hypothesis
having power functions independent of 2. Annals of Mathematical Statistics,
11, 186-192.

Donald, G. E. and Hsu, J. C. (1983). Multiple comparsions with the best treatment. Journal of American Statistical Association, 78, 965-971.

Dudewicz, E. J. and Dalal, S.R. (1975). Allocation of observations in ranking and
selection with unequal variances. Sankhya Ser. B, 37, 28-78.

Dunnett, C. W. (1955). A multiple comparsion procedure for comparsing several
treatments with a control. Journal of American Statistical Association, 50, 1096-
1121.

Dunnett, C. W. (1964). New tables for multiple comparsions with a control.
Biometrics, 20, 482-491.

Gupta, S. S. (1956). On a decision rule for a problem in ranking means. Mimeograph Series No. 150, Institute of Statistics, University of North Carolina, Chapel Hill, N. C.

Higazi, S. M. F. and Dayton, C. M. (1984). Comparing several experimental groups
with a control in the multivariate case. Communications in Statistics-Simulation
and Computation, 13(2), 227-242.

Hsu, J. C. (1981). Simultaneous con dence intervals for all distances from the best. Annals of Statistics, 9, 1026-1034.

Hsu, J. C. (1984a). Constrained simultaneous con dence intervals for multiple comparsions with the best. Annals of Statistics, 12, 1136-1144.

Hsu, J. C. (1984b). Ranking and selection and multiple comparsions with the best.
In Santner, T. J. and Tamhane, A. C. (eds), Design of Experiments: Ranking
and Selection. Marcel Dekker, New York.

Nelson, L. S. (1983). Exact critical values for use with the analysis of means. Journal of Quality Technology, 15, 40-44.

Nelson, P. R. (1982a). Exact critical points for analysis of means. Communications in Statistics-Theory and Methods, 11, 699-709.

Nelson, P. R. (1982b). Multivariate normal and t distributions with jk = i j .
Communications in Statistics-Simulation and Computation, 11(2), 239-248.

Nelson, P. R. (1993). Additional uses for the analysis of means and extended tables of critical values. Technometrics, 35, 61-71.

Stein, C. (1945). A two-sample test for a linear hypothesis whose power is independent of the variance. Annals of Mathematical Statistics, 16, 243-258.

Wen, M. J. and Chen, H. J. (1994). Single-stage multiple comparsion procedures
under heteroscedasticity. American Journal of Mathematical and Management
Sciences, 14(1,2), 1-48.

Wu, S. F. and Chen, H. J. (1994). Multiple comparsion procedures with the average, normal means. Technical Report number 94-29, Department of Statistics, The University of Georgia, Athens, GA 30602, USA.

Wu, S. F and Chen, H. J. (1998). Multiple comparsions with the average for normal
distributions. American Journal of Mathematical and Management Sciences, 18,
193-218.

溫敏杰和杜宜軒 (2001). Stein定理與相關定理之證明及其在排序及擇優選取上之應用.
中國統計學報, 第39卷, 第57-71頁.

梁德馨、黃綺年和陳平山 (2001). 人壽保險公司顧客滿意度及經營績效之比較研究~
以國泰人壽及安泰人壽為研究主體. 民意研究季刊, 第216卷, 第90-122頁.