Unimodularity of network representations of time-series for unbiased parameter estimation

Authors Florian Sobieczky
Editors R. Moreno-Díaz
F. Pichler
A. Quesada-Arencibia
Title Unimodularity of network representations of time-series for unbiased parameter estimation
Booktitle Computer Aided Systems Theory – Proc. EUROCAST 2019, Part I
Type in proceedings
Publisher Springer
Series Lecture Notes in Computer Science
Volume 12013
ISBN 978-3-030-45092-2
DOI 10.1007/978-3-030-45093-9_21
Month April
Year 2020
Pages 167-175
SCCH ID# 18090
Abstract

 

For the problem of parameter estimation in time-series models of a stream of physical measurements under potential local quality impairments (indicated by an additional binary variable), a lamplighter-graph representation is introduced. This representation makes conditional estimation using large samples conditioned on specific degrees of quality impairment possible. Due to the unimodularity of the network representation, there are unbiased estimators.