Detectors for multinomial input
Abstract
The binary detection problem is considered. Under an arbitrary noise environment, the input sample space can be transformed into a multinominal vector. Based on observations of this vector, the NeymanPearson optimal detector is developed for a known signal. When the signal strength is unknown, the likelihood ratio principle is followed to obtain consistent tests which use the Pearson's chisquare statistic. The resulting detectors are compared to others in terms of asymptotic relative efficiency under some actual noise distributions.
 Publication:

IEEE Transactions on Aerospace Electronic Systems
 Pub Date:
 March 1983
 DOI:
 10.1109/TAES.1983.309448
 Bibcode:
 1983ITAES..19..288L
 Keywords:

 Binary Data;
 Input;
 Polynomials;
 Signal Detection;
 Statistical Analysis;
 Optimization;
 Pearson Distributions;
 Vector Analysis;
 Communications and Radar