Date of Award

1-1-2010

Thesis Type

Masters

Document Type

Dissertation

Divisions

Faculty of Science

Department

Institute of Mathematical Sciences

Institution

Universiti Malaya

Abstract

In obtaining confidence interval for the survivor function using Greenwood’s formula and in performing log-rank test for comparing the survivor functions of two groups of individuals, only the information given by the first two moments of the relevant statistics are used. Presently we show that by incorporating the information given by the third and fourth moments of the statistics, the performance of the confidence interval and statistical test can be improved.

When the survivor function can be described by the Weibull distribution, the knowledge regarding the survivor function can be obtained through the estimation of the Weibull scale and shape parameters and the Weibull quantiles. In the present work we use the method based on hypothesis testing to construct confidence intervals for these parameters. In implementing the procedure based on hypothesis testing, we have made use of the distribution of the relevant statistic evaluated at a value of the parameter vector which satisfies the conditions under the null hypothesis and yet is nearest to the estimated parameter vector. It is found that compared to the bootstrap confidence intervals, the confidence intervals based on hypothesis testing tend to perform better.

Comments

Dissertation (M.A) – Faculty of Science, Universiti Malaya, 2010.

Additional Information

khm

Creative Commons License

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.

Download

Share

COinS