On Some Goodness of Fit Tests for the Weibull Distribution with Estimated Parameters.
Abstract
This note considers some test statistics based on the sample distribution function for testing the null hypothesis that a random sample belongs to a Weibull distribution with unknown scale and shape parameters. A foundation for testing such a hypothesis is provided by the fact that the logarithm of a Weibull random variable has an extreme value distribution with a location and a scale parameter, and by results which pertain to the weak convergence of an associated empirical stochastic process, under the null hypothesis. The asymptotic distribution of the empirical process serves as a basis for Monte Carlo studies for determining the appropriate critical points of the test statistics.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 14, 1977
- Accession Number
- ADA046630
Entities
People
- Mahesh Chandra
- Nozer Singpurwalla
Organizations
- George Washington University