Mean estimation in highly skewed samples [electronic resource].
- Washington, D.C. : United States. Dept. of Energy, 1991. and Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy.
- Physical Description:
- Pages: (8 pages) : digital, PDF file
- Additional Creators:
- Los Alamos National Laboratory, United States. Department of Energy, and United States. Department of Energy. Office of Scientific and Technical Information
- The problem of inference for the mean of a highly asymmetric distribution is considered. Even with large sample sizes, usual asymptotics based on normal theory give poor answers, as the right-hand tail of the distribution is often under-sampled. This paper attempts to improve performance in two ways. First, modifications of the standard confidence interval procedure are examined. Second, diagnostics are proposed to indicate whether or not inferential procedures are likely to be valid. The problems are illustrated with data simulated from an absolute value Cauchy distribution. 4 refs., 2 figs., 1 tab.
- Published through SciTech Connect., 09/01/1991., "la-12114-ms", "DE91018513", and Pederson, S P.
- Funding Information:
View MARC record | catkey: 14355844