Testing for bivariate normality using the empirical distribution function
Author:
- 1 January 1979
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 8 (7) , 699-712
Abstract
The problem of testing for bivariate normality using the empirical distribution function is considered. A Cramér-von Mises type statistic is defined and asymptotic percentage points for this statistic given. This involves solving a two-dimensional homogeneous integral equation. Unfortunately the Cramér-von Mises statistic is not invariant under orthogonal transformations of the data so that an invariant statistic is developed. Approximations for the distribution of this statistic are found by Monte Carlo. Applications of the statistics are given. It is shown that the statistics are particularly sensitive to certain kinds of pattern in the data and they could be useful in data analysis apart from providing a formal test of bivariate normalityKeywords
This publication has 7 references indexed in Scilit:
- Asymptotic Results for Goodness-of-Fit Statistics with Unknown ParametersThe Annals of Statistics, 1976
- Components of Cramér-Von Mises Statistics. IiJournal of the Royal Statistical Society Series B: Statistical Methodology, 1975
- Methods for Assessing Multivariate Normality1973
- Fredholm Determinant of a Positive Definite Kernel of a Special Type and Its ApplicationThe Annals of Mathematical Statistics, 1972
- On Tests of Normality and Other Tests of Goodness of Fit Based on Distance MethodsThe Annals of Mathematical Statistics, 1955
- The Cramer-Smirnov Test in the Parametric CaseThe Annals of Mathematical Statistics, 1955
- TESTS OF SIGNIFICANCE IN MULTIVARIATE ANALYSISBiometrika, 1948