A Study of Foutz's Multivariate Goodness-of-Fit Test.
Abstract
The empirical power of a new multivariate goodness-of-fit test proposed by Foutz (1980) is investigated. The test has been applied to Monte Carlo samples from bivariate and trivariate normal distributions with a variety of mean vectors and covariance matrices. The null hyposthesis tested is that the sample is from a multi-variate normal distribution with 0 mean vector and covariance matrix the identity I. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1982
- Accession Number
- ADA118198
Entities
People
- Richard John Linhart Jr
Organizations
- Naval Postgraduate School