A Sensitivity Analysis of Circular Error Probable Approximation Techniques
Abstract
Several algebraic CEP estimates models were examined in this study. Each assumes that the crossrange and downrange miss distances of the sample data follow a bivariate normal distribution. The analysis determined the sensitivities of these models to changes in the parameters of sample size, bias, correlation, and ellipticity. The accuracy of each model is expressed in terms of relative error, and the parameter regions in which a certain method dominated as the most accurate were noted. In general, it was found that bias was the most significant parameter in determining the best CEP method. A simple method, based on the Rayleigh distribution dominated as the best when bias was 0, .25, .5, . 75, or 1, and the Grubbs-Patnaik/chi-square method dominated for the bias setting of 2 regardless of the settings of the other parameters. Levels of bias greater than 2 were not addressed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1992
- Accession Number
- ADA248105
Entities
People
- Peter Puhek
Organizations
- Air Force Institute of Technology