In this work experimental designs with functional responses which are linearly dependent on some real control variables are studied. The goal is to determine an optimum design for a precise estimation of the unknown parameters. In other words, the values for the control variables are fixed in order to minimize (in some sense) the covariance matrix of the parameter estimators. It is assumed that processes belong to a Sobolev space, and the functional BLUE and the functional OLS estimator of the model parameter are computed in this space. The estimate in the $L^2$ space is then obtained as a more simple case.
Optimal designs for linear models with functional responses / G. Aletti, C. May, C. Tommasi - In: Contributions in Infinite-Dimensional Statistics and Related Topics / [a cura di] E. G. Bongiorno, E. Salinelli, A. Goia, P. Vieu. - [s.l] : Società Editrice Esculapio, 2014. - ISBN 9788874887637. - pp. 19-24 (( Intervento presentato al 3. convegno International Workshop on Functional and Operatorial Statistics tenutosi a Stresa nel 2014 [10.15651/978-88-748-8763-7].
Optimal designs for linear models with functional responses
G. Aletti;C. May;C. Tommasi
2014
Abstract
In this work experimental designs with functional responses which are linearly dependent on some real control variables are studied. The goal is to determine an optimum design for a precise estimation of the unknown parameters. In other words, the values for the control variables are fixed in order to minimize (in some sense) the covariance matrix of the parameter estimators. It is assumed that processes belong to a Sobolev space, and the functional BLUE and the functional OLS estimator of the model parameter are computed in this space. The estimate in the $L^2$ space is then obtained as a more simple case.File | Dimensione | Formato | |
---|---|---|---|
iwfos14_AlettiMayTommasi.pdf
accesso riservato
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
126.7 kB
Formato
Adobe PDF
|
126.7 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.