Test Statistic Auto- and Cross-correlation Effects on Monitor False Alert and Missed Detection Probabilities

Boris Pervan, Samer Khanafseh, and Jaymin Patel

Peer Reviewed

Abstract: This paper investigates the influence of the autocorrelations of monitor test statistics over time and their cross-correlations across monitors on false alert and missed detection probabilities. General analysis methods are developed for the two problems. It is shown that cross-correlation across pairs of monitors directly influences the joint probability of missed detection, P_MD. This is in contrast to the effect of time auto-correlation, which primarily influences the probability of false alert, P_FA. The new methods are applied to the example problem of Ground Based Augmentation System (GBAS) ionospheric front monitoring.
Published in: Proceedings of the 2017 International Technical Meeting of The Institute of Navigation
January 30 - 2, 2017
Hyatt Regency Monterey
Monterey, California
Pages: 562 - 590
Cite this article: Pervan, Boris, Khanafseh, Samer, Patel, Jaymin, "Test Statistic Auto- and Cross-correlation Effects on Monitor False Alert and Missed Detection Probabilities," Proceedings of the 2017 International Technical Meeting of The Institute of Navigation, Monterey, California, January 2017, pp. 562-590. https://doi.org/10.33012/2017.14874
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In