Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/2132
Title: Computing 3sls solutions of simultaneous equation models with a possible singular variance-covariance matrix
Authors: Dinenis, Elias 
Kontoghiorghes, Erricos John 
metadata.dc.contributor.other: Κοντογιώργης, Έρρικος Γιάννης
Major Field of Science: Social Sciences
Keywords: Parallel algorithms;Algorithms;Least squares;Analysis of covariance
Issue Date: Aug-1997
Source: Computational Economics, 1997, vol. 10, no. 3, pp. 231-250
Volume: 10
Issue: 3
Start page: 231
End page: 250
Journal: Computational Economics 
Abstract: Algorithms for computing the three-stage least squares (3SLS) estimator usually require the disturbance covariance matrix to be non-singular. However, the solution of a reformulated simultaneous equation model (SEM) results into the redundancy of this condition. Having as a basic tool the QR decomposition, the 3SLS estimator, its dispersion matrix and methods for estimating the singular disturbance covariance matrix are derived. Expressions revealing linear combinations between the observations which become redundant have also been presented. Algorithms for computing the 3SLS estimator after the SEM has been modified by deleting or adding new observations or variables are found not to be very efficient, due to the necessity of removing the endogeneity of the new data or by re-estimating the disturbance covariance matrix. Three methods have been described for solving SEMs subject to separable linear equalities constraints. The first method considers the constraints as additional precise observations while the other two methods reparameterized the constraints to solve reduced unconstrained SEMs. Methods for computing the main matrix factorizations illustrate the basic principles to be adopted for solving SEMs on serial or parallel computers.
URI: https://hdl.handle.net/20.500.14279/2132
ISSN: 15729974
DOI: 10.1023/A:1008617207791
Rights: © Kluwer Academic
Type: Article
Affiliation: Institut d'Informatique, Université de Neuchâtel, Switzerland 
Affiliation : Université de Neuchâtel 
City, University of London 
Appears in Collections:Άρθρα/Articles

CORE Recommender
Show full item record

SCOPUSTM   
Citations

17
checked on Nov 9, 2023

Page view(s) 20

469
Last Week
0
Last month
1
checked on Nov 8, 2024

Google ScholarTM

Check

Altmetric


Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.