New results in matrix algebra applied to the fundamental bordered matrix of linear estimation theory pave the way towards obtaining additional and informative closed-form expressions for the best linear unbiased estimator (BLUE). The results prove significant in several respects. Indeed, more light is shed on the BLUE structure and on the working of the OLS estimator under nonsphericalness in (possibly) singular models.
Faliva, M., Zoia, M., New insights into best linear unbiased estimation and the optimality of least-squares, <<JOURNAL OF MULTIVARIATE ANALYSIS>>, 2006; (97): 575-585. [doi:10.1016/j.jmva.2005.07.001] [http://hdl.handle.net/10807/4675]
New insights into best linear unbiased estimation and the optimality of least-squares
Faliva, Mario;Zoia, Maria
2006
Abstract
New results in matrix algebra applied to the fundamental bordered matrix of linear estimation theory pave the way towards obtaining additional and informative closed-form expressions for the best linear unbiased estimator (BLUE). The results prove significant in several respects. Indeed, more light is shed on the BLUE structure and on the working of the OLS estimator under nonsphericalness in (possibly) singular models.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
