The use of statistical image classification techniques for the assessment of measured antenna pattern functions

Attempts to produce robust, objective, quantitative measures of similarity between antenna pattern data sets using statistical methods have been widely reported in the open literature. This paper presents an introduction to the physical validity and use of generalised statistical analysis along with specialist statistical image classification concepts as applied to the assessment of antenna pattern functions. Before presenting results the paper describes some of the more recent developments in the field relating to, nominal, ordinal, interval and the more usual ratio type levels of measurement data available within near-field measurement data sets. Finally the paper describes how these assessment techniques could be implemented in a formal gage repeatability and reproducibility (R&R) numerical quality analysis of a measurement system.