Sequential probability ratio test

About: Sequential probability ratio test is a research topic. Over the lifetime, 1248 publications have been published within this topic receiving 22355 citations.

Some sequential analogs of Stein's two-stage test

Abstract: : Several sequential analogs of Stein's two-stage test procedure are presented for testing hypotheses about the mean of a normal population with unknown variance and with specified error probabilities When sequential experimentation is feasible, they provide alternatives to the sequential normal test (variance known) or the sequential t-test If the variance is assumed known, the procedures may still be recommended since the added cost may be only a very few additional observations on the average, and the performance of the tests does not depend on the validity of any assumption about the variance Unlike the t-test, these procedures do not require that the alternative hypothesis be specified in standard deviation units

Locally most powerful sequential tests

Abstract: are discussed. In all cases considered, the stopping rule is the first time a certain random walk leaves a bounded interval. (Thus various inequalities and approximations due to Wald can be utilized in obtaining properties of these tests.) For models in a one-parameter exponential family, each LMP sequential test is shown to be a Wald SPRT for a family of paired (conjugate) simple hypotheses.

Shiryayev sequential probability ratio test for redundancy management

Abstract: An essential aspect in the design of fault-tolerant digital flight control systems is the design of failure detection and redundancy management systems. A decision rule, the Shiryayev sequential probability ratio test (SPRT), is derived from a dynamic programming approach and is used to detect failures between similar instruments, as well as between dissimilar instruments through analytic redundancy. Unlike the Wald SPRT, which tests for the presence of failure or no failure in all of the data sequence, the Shiryayev SPRT detects the occurrence of a fault in the data sequence in minimum time if certain conditions are met. The performance of the Shiryayev SPRT in detecting a failure between two rate gyros as compared to standard fixed interval schemes is presented, as well as the performance of a single accelerometer failure using translational kinematic equations to form a parity relation for analytic redundancy.

Enhanced robust cooperative spectrum sensing in cognitive radio

Abstract: As wireless spectrum resources become more scarce while some portions of frequency bands suffer from low utilization, the design of cognitive radio (CR) has recently been urged, which allows opportunistic usage of licensed bands for secondary users without interference with primary users. Spectrum sensing is fundamental for a secondary user to find a specific available spectrum hole. Cooperative spectrum sensing is more accurate and more widely used since it obtains helpful reports from nodes in different locations. However, if some nodes are compromised and report false sensing data to the fusion center on purpose, the accuracy of decisions made by the fusion center can be heavily impaired. Weighted sequential probability ratio test (WSPRT), based on a credit evaluation system to restrict damage caused by malicious nodes, was proposed to address such a spectrum sensing data falsification (SSDF) attack at the price of introducing four times more sampling numbers. In this paper, we propose two new schemes, named enhanced weighted sequential probability ratio test (EWSPRT) and enhanced weighted sequential zero/one test (EWSZOT), which are robust against SSDF attack. By incorporating a new weight module and a new test module, both schemes have much less sampling numbers than WSPRT. Simulation results show that when holding comparable error rates, the numbers of EWSPRT and EWSZOT are 40% and 75% lower than WSPRT, respectively. We also provide theoretical analysis models to support the performance improvement estimates of the new schemes.