الفهرس | Only 14 pages are availabe for public view |
Abstract The progressive Type-II right censoring scheme is of great importance in life-testing experiments as it allows the experimenter to remove units from the experiment before its end, thus resulting in a saving in cost as well as experimental time. In this thesis, the progressively Type-II right censored samples for some useful distributions including the logistic, half-logistic and log-logistic distributions are considered. First, some new recurrence relations satisfied by the single and product moments of progressively censored sample are established for the underlying distributions. Some well known recurrence relations in literature are deduced as special cases from our results. The BLUE(s) and MLE(s) of the scale(location-scale) parameter(s), of the considered distributions are derived and discussed. To show the usefulness of our results in the thesis, Monte Carlo simulations are carried out. The performance of the proposed estimates is investigated by calculating the mean squared errors (MSEs) for the obtained estimates. Finally, we conclude with the following points: In the first chapter of the thesis, a method of censoring known as progressive Type-II censoring along with some special cases (order statistics, Type-I and Type-II censoring) are presented. Notations of the moments of order statistics and progressive Type-II censoring viii ix are given. Applications to inference, including BLUE and MLE are presented for any scale and location-scale family of distributions. BLUPs are also presented for any scale and location-scale family of distributions. In the second chapter of the thesis, we establish several recurrence relations for the single and product moments of progressively Type-II right censored order statistics from a logistic distribution. The use of these relations in a systematic manner allows us to compute all the means, variances and covariances of progressively Type-II right censored order statistics from the logistic distribution for all sample sizes n, effective sample sizes m, and all progressive censoring schemes (R1; ¢ ¢ ¢ ;Rm): The results established here generalize the corresponding results for the usual order statistics due to Shah (1966, 1970). These moments are then utilized to derive BLUEs of the location and scale parameters of the logistic distribution. A comparison of these estimators with the MLEs is then made. The BLUPs of censored failure times are briefly discussed. Finally, an illustrative example is presented. In the third chapter of the thesis, we establish several recurrence relations for the single and product moments of progressively Type-II right censored order statistics from a halflogistic distribution. The use of these relations in a systematic recursive manner would enable one to compute all the means, variances and covariances of progressively Type-II right censored order statistics from the half-logistic distribution for all sample sizes n, effective sample sizes m, and all progressive censoring schemes (R1; ¢ ¢ ¢ ;Rm). The results established here generalize the corresponding results for the usual order statistics due to Balakrishnan (1985). These moments are then utilized to derive BLUEs of the scale and x location-scale parameters of the half-logistic distribution. A comparison of these estimators with the MLEs is then made. The BLUPs of censored failure times are then briefly discussed. Finally, two numerical examples are presented to illustrate all the inferential methods developed here. In the fourth chapter of the thesis, we establish several recurrence relations for the single and product moments of progressively Type-II right censored order statistics from a log-logistic distribution. The use of these relations in a systematic recursive manner would enable the computation of all the means, variances and covariances of progressively Type- II right censored order statistics from the log-logistic distribution for all sample sizes n, effective sample sizes m, and all progressive censoring schemes (R1; ¢ ¢ ¢ ;Rm): The results established here generalize the corresponding results for the usual order statistics due to Balakrishnan and Malik (1987) and Balakrishnan et al. (1987). The moments so determined are then utilized to derive BLUEs for the scale and location-scale log-logistic distributions. A comparison of these estimates with the MLEs is made through Monte Carlo simulation. The BLUPs of progressively censored failure times are then briefly discussed. Finally, a numerical example is presented to illustrate all the methods of inference developed here. Finally, in the last chapter of the thesis, we conclude the work that have been done. Then, we suggest some ideas that could lead to future research. |