我們往往會對於一個來自某分配的資料作參數的估計,以利作統計決策.而在做參數區間估計的時候,我們總是希望這區間能越小越好.在本文中,我們對岡帕氏分配在完全資料型態和型-Ⅱ右邊單一設限型態去做討論,可顯見概似比檢定近似法所求出來的信賴區域會比確切法來的小很多,不過概似比檢定近似法則須較大的樣本數.在樣本數大小和信賴區域大小之間該如何的取捨,讓統計決策者可以根據自身的條件去權衡考量.

　　We tend to form an estimate of the data from a certain distribution in order to make statistic decision, and when estimating confidence region
of parameters, we hope that this region can be as little as possible. In the study, for the discussion of gompertz distribution in complete data and type II singly right censored data, it is clear that the trusted section confidence region from likelihood ratio test approximation is much smaller than that from exact, but likelihood ratio test approximation needs the bigger sampling. How to make an option between the size of sampling and trusted section confidence region offers a chance for the statistical decision-makers to measure and consider according to their own condition.

Anton, Howard(1987). Elementary Linear Algebra, John Wiley and Sons, New
York.
Arnold, Barry C and Shavelle, Robert M (1998). Joint confidence sets for the mean
and variance of a normal distribution, The American Statistician,Vol.52,
No.2, 133-140.
Balakrishnan, N. and Basu, Asit P. (1995). The Exponential Distribution
: Theory, Methods and Applications, AW, Amsterdam, Netherlands.
Cohen, A.C. (1991) Truncated and Censored Samples: Theory and Applica-
tions, Marcel Dekker, New York.
Cramer, H. (1951). Mathematical Methods of Statistics, Princeton University Press,
Princeton.
Douglas, J.B. (1993). Confidence region for parameter pairs, The American
Statistician, 47, 43-45.
Epstein, B. and Sobel, M. (1954). Some theorems relevant to life testing from
an exponential distribution, Annals of Mathematical Statistics, 25, 373-381.
Flury, Bernard (1997). A First Course in Multivariate Statistics, Springer, New
York.
Lu, Hai-Lin (2002). Statistical inference on the Weibull and related distribution,
National Cheng Kung University, Techincal Report.
Johnson, N.L, Kotz, S. , and Balakrishnan, N. (1994). Continuous Univariate
Distribution , Vol.1, 2nd edition. Wiley, New York.
Kendall, M. and Stuart, A. (eds.) (1979). The Advanced Theory of Stayis-
tics: Vol.2, Inference and Relationship(4th ed), Charles Griffin ＆ Company
Ltd, London.
Kunimura, Dennis (1998). The Gompertz distribution - estimation of paramete-
rs, Actuarial Research Clearing House, Vol.2, 65-75.
Meeker, W.Q. , and Escobar, L.A. (1995). Teaching about approximate confid-
ence region based on maximum likelihood estimation, The American
Statistician, 49, 48-53.
Thomas, D.R. and Wilson, W.M. (1972). Linear order statistic estimation for the
two-parameter Weibull and extreme value distribution from type-Ⅱ
progressively censored samples, Technometrics, 14, 679-691.
Wu, Shuo-Jye (2002). Estimation of the parameters of the Weibull distribution
with progressively censored data. Journal of the Japan Statistical Society,
Vol.32, No.2, 155-163.