Abbas Pak - Department of Computer Sciences, Faculty of Mathematical Sciences, Shahrekord University, P. O. Box 115, Shahrekord, Iran
Nayereh Bagheri Khoolenjani - Department of Statistics, University of Isfahan, Isfahan, Iran.

For manufacturers, assessing the reliability of an existing product is a fundamental task for improving the product’sreliability or quality. Conventional reliability estimation methods for Weibull distribution are based on preciselifetime data. However, in real world situations, the results of the experimental performance cannot always berecorded or measured precisely, but each observable event may only be identified with a fuzzy subset of the samplespace. In this paper the model properties and reliability measures of Weibull distribution are derived and studiedwhen the observations are fuzzy. For the estimation purposes of the parameter and other reliability characteristicsmaximum likelihood and Bayes approaches are used. Monte Carlo simulation study is conducted to compare theperformance of the various estimates developed. In view of cost and time constraints, type II censored sample dataare used in estimation.

Imprecise observation; Fuzzy data; Statistical inference; Weibull distribution; type II censoring