Title :
Percentiles of Pooled Estimates of Weibull Parameters
Author_Institution :
Department of Mathematics and Statistics; Wright State University; Dayton, OH 45435 USA.
fDate :
4/1/1983 12:00:00 AM
Abstract :
In fatigue testing of metals or composite materials under different levels of stress, the underlying distributions are often assumed to be Weibull with a common shape parameter. The problems of estimation and hypothesis tests of the common shape parameter and scale parameters in the Weibull distributions are considered in this paper. The results are: 1) the maximum likelihood equation for estimating the shape parameter, 2) a s-confidence interval and hypothesis test for the shape parameter, 3) s-bias factors and variances of the pooled estimator of shape parameter, and 4) s-confidence interval and hypothesis test for the scale parameters. Examples are given for composite material applications. Results are based on Monte Carlo simulation methods.
Keywords :
Composite materials; Fatigue; Life estimation; Maximum likelihood estimation; Parameter estimation; Shape; State estimation; Stress; Testing; Weibull distribution; Hypothesis test; Maximum likelihood estimation; Pooled estimation; Weibull distribution; s-Bias factor; s-Confidence interval;
Journal_Title :
Reliability, IEEE Transactions on
DOI :
10.1109/TR.1983.5221483