Abstract
Two characterizations of a normal distribution with an unknown variance based on the corresponding UMVU estimators of the density functions are given, depending on whether its mean is known, or unknown. Applications of these characterization results in the procedures to construct empirical distribution function (EDF) goodness-of-fit tests for normal distributions are mentioned.
Similar content being viewed by others
Author information
Authors and Affiliations
Corresponding authors
Additional information
Received April 2000/Revised April 2002
Rights and permissions
About this article
Cite this article
Nguyen, T.T., Dinh, K.T. Characterizations of normal distributions and EDF goodness-of-fit tests. Metrika 58, 149–157 (2003). https://doi.org/10.1007/s001840200233
Issue Date:
DOI: https://doi.org/10.1007/s001840200233