韋伯分配在存活分析和可靠度分析中是常被使用到的分配，而循序性設限資料在其中更是不可或缺的資料型態之一，因此本文以韋伯分配下的循序性設限資料為模型。再利用 EM演算法及其延伸ECM演算法和ECME演算法來做估計，並利用其參數之變異數及收斂速度矩陣的特徵值大小來比較其之間的優劣。在模擬結果中，發現ECME的收斂速度總是比EM的收斂速度快，且ECME的變異數都比EM的變異數來得小，因此ECME整體而言是較好的。

Weibull distribution is a distribution often used in survival analysis and reliability analysis. And progresssive censored data is a vital one of data types. In this article, the model we take is the progressive censored data in Weibull distribution. And we use the EM algorithm and it's extension, ECM and ECME, to estimate the parameters. Final, we compare EM and ECME by using the variances of parameters and the e-igenvalues of matr-
ix speed of convergence. In the simulation, we can find the speed of convergence of ECME is always faster than this of ECM. And the variance of ECME is smaller than the variance of EM, so ECME is the better method.

1. Balakrishnan, N. and Aggarwala, R. (2000).Progresssive Censoring Theory, Methods and Applications, Birkhauser, Boston.
2. Balakrishnan, N. and Basu, A.P. (1996).The Exponential Distribution: Theory, Methods and Applications, Gordon and Breach, Singapore.
3. Dempster, A.P., Laird, N.M., and Rubin, D.B. (1977). Maximum likelihood from incomplete data via the EM algorithm (with discussion)
.Journal of the Royal Statistical Society B, 39, 1-38.
4. Fisher, R.A. and Tippett, L.H.C. (1950). Limiting Forms of the Frequency Distribution of the Largest or Smallest Member of a Sample, Reprint in R.A. Fisher, Contributions to Mathematical Statistics, John Whiley, New York.
5. Johnson, N.L. and Kotz, S. (1969). Distributions in Statistics: Contin-
uous Univariate Distributions, Vol Ⅰ, Wiley, New York.
6. Liu, C., and Rubin, D.B. (1994).The ECME algorithm: a simple extension of EM and ECM with faster monotone convergence. Biometrika, 81, 633-648.
7. McLachlan, G.J. and Krishnan, T. (1997).The EM algorithm and extensions. John Wiley and Sons, New York.
8. Meng, X.L., and Rubin, D.B. (1993).Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika, 80, 267-278.
9. Meng, X.L., and Rubin, D.B. (1994).On the global and componentwise rates of convergence of the EM algorithm. Linear Algebra and its Applications, 199, 413-425.
10. Meng, X.L., and van Dyk, D. (1995).The EM algorithm─An old folk song sung to a fast new tune. J. R. Statist. Soc., Ser. B, 59, 511-567
11. Murthy, D. N. P., Xie, M.M.. and Jiang, R.(2004).Weibull Models. John Wiley and Sons, Hoboken, New Jersey.
12. Ng, H.K.T., Chan, P.S., and Balakrishnan, N. (2002).Estimation of parameters from progressively censored data using EM algorithm. Computational Statistics and Data Analysis, 39, 371-386.
13. Stephens, M.A. (1977). Goodness of fit for the extreme value distribution. Biometrika,64, 583-588
14. Weibull,W.(1939).A statistical theory of the strength of material, Ingeniors Vetenskapa Acadmiens Handligar,151,1-45
15. Wu, C.F.J.(1983). On the convergence properties of the EM algorithm. Annals of Statistics, 11, 95-103.