David Middleton

Abstract: Methods of determining the first-order parameters of both the approximate and exact Class A and B models are derived, for both the ideal case of infinite sample data the practical cases of finite data samples. It is shown that all (first order) parameters of these models can, in principle, be obtained, exactly or approximately, from the ideal or practical measurements [All first-order parameters of Class A but only the (first-order) even moments of the Class B models are exactly obtainable in the ideal case.] Procedures for establishing meaningful measures of the accuracy of the parameter estimates in the practical cases are identified: suitably adjusted, non parametric, small-sample tests of “goodness-of-fit” (such as Kolmogorov-Smirnov tests) provide the principal techniques for establishing accuracy, at an appropriately selected significance level(αo). The roles of robustness and stability of the parameters and their estimators are also discussed.

Keywords: noise model; interference models; statistical parameter estimate

Disclaimer: Certain commercial equipment, components, and software may be identified in this report to specify adequately the technical aspects of the reported results. In no case does such identification imply recommendation or endorsement by the National Telecommunications and Information Administration, nor does it imply that the equipment or software identified is necessarily the best available for the particular application or uses.

For questions or information on this or any other NTIA scientific publication, contact the ITS Publications Office at ITSinfo@ntia.gov or 303-497-3572.

Back to Search Results