On the variance of identified SIMO systems with spatially correlated output noise

G. Bottegal, Håkan Hjalmarsson

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review


In this paper, we study the problem of evaluating the accuracy of identified linear single-input multi-output (SIMO) dynamical models, where the disturbances affecting the output measurements are spatially correlated. Assuming that the input is an observed white noise sequence, we provide an expression for the covariance matrix of the parameter estimates when weighted least-squares (WLS) are adopted to identify the parameters. Then, we show that, by describing one of the subsystems composing the SIMO structure using less parameters than the other subsystems, substantial improvement on the accuracy of the estimates of some parameters can be obtained. The amount of such an improvement depends critically on the covariance matrix of the output noise and we provide a condition on the noise correlation structure under which the mentioned model parametrization gives the lowest variance in the identified model. We illustrate the derived results through some numerical experiments.
Original languageEnglish
Title of host publication2014 IEEE 53rd Annual Conference on Decision and Control (CDC), 15-17 December 2014, Los Angeles, California
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)978-1-4673-6090-6
ISBN (Print)978-1-4799-7746-8
Publication statusPublished - 2014
Externally publishedYes
Event53rd IEEE Conference on Decision and Control, CDC 2014 - "J.W. Marriott Hotel", Los Angeles, United States
Duration: 15 Dec 201417 Dec 2014
Conference number: 53


Conference53rd IEEE Conference on Decision and Control, CDC 2014
Abbreviated titleCDC
Country/TerritoryUnited States
CityLos Angeles
Internet address


Dive into the research topics of 'On the variance of identified SIMO systems with spatially correlated output noise'. Together they form a unique fingerprint.

Cite this