Estimating Test Statistic Distributions for Multiple Hypothesis Testing in Sensor Networks
A4 Artikkeli konferenssijulkaisussa
2022 56th Annual Conference on Information Sciences and Systems, CISS 2022
AbstractWe recently proposed a novel approach to perform spatial inference using large-scale sensor networks and multiple hypothesis testing . It identifies the regions in which a spatial phenomenon of interest exhibits different behavior from its nominal statistical model. To reduce the intra-sensor-network communication overhead, the raw data is pre-processed at the sensors locally and a summary statistic is send to the cloud or fusion center where the actual spatial inference using multiple hypothesis testing and false discovery control takes place. Local false discovery rates (lfdrs) are estimated to express local believes in the state of the spatial signal. In this work, we extend our approach by proposing two novel lfdr estimators stemming from the Expectation-Maximization method. The estimation bias is considered to explain the differences in performance among the compared lfdr estimators.
Funding Information: The work of M. Gölz is supported by the German Research Foundation (DFG) under grant ZO 215/17-2. Author for correspondence: M. Gölz. Publisher Copyright: © 2022 IEEE.
density estimation, information fusion, Large-scale inference, local false discovery rate, sensor networks
Golz , M , Zoubir , A M & Koivunen , V 2022 , Estimating Test Statistic Distributions for Multiple Hypothesis Testing in Sensor Networks . in 2022 56th Annual Conference on Information Sciences and Systems, CISS 2022 . IEEE , pp. 90-95 , Conference on Information Sciences and Systems , Princeton , New Jersey , United States , 09/03/2022 . https://doi.org/10.1109/CISS53076.2022.9751186