Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/2153
Title: | A computationally efficient method for solving sur models with orthogonal regressor | Authors: | Foschi, Paolo Kontoghiorghes, Erricos John |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Keywords: | Least squares;Problem solving;Regression analysis | Issue Date: | 1-Sep-2004 | Source: | Linear Algebra and Its Applications, 2004, vol. 388, no. 1-3 SPEC. ISS., pp. 193-200 | Volume: | 388 | Issue: | 1-3 SPEC. ISS. | Start page: | 193 | End page: | 200 | Journal: | Linear Algebra and its Applications | Abstract: | A computationally efficient method to estimate seemingly unrelated regression equations models with orthogonal regressors is presented. The method considers the estimation problem as a generalized linear least squares problem (GLLSP). The basic tool for solving the GLLSP is the generalized QR decomposition of the block-diagonal exogenous matrix and Cholesky factor C⊗IT of the covariance matrix of the disturbances. Exploiting the orthogonality property of the regressors the estimation problem is reduced into smaller and independent GLLSPs. The solution of each of the smaller GLLSPs is obtained by a single-column modification of C. This reduces significantly the computational burden of the standard estimation procedure, especially when the iterative feasible estimator of the model is needed. The covariance matrix of the estimators is also derived. | URI: | https://hdl.handle.net/20.500.14279/2153 | ISSN: | 243795 | DOI: | http://dx.doi.org/10.1016/S0024-3795(02)00544-X | Rights: | © Elsevier | Type: | Article | Affiliation : | Université de Neuchâtel | Publication Type: | Peer Reviewed |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
SCOPUSTM
Citations
4
checked on Feb 13, 2018
Page view(s)
428
Last Week
0
0
Last month
2
2
checked on Nov 21, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License