Premium
GENERALIZED INVERSES USED IN RECURSIVE ESTIMATION OF THE GENERAL LINEAR MODEL 1
Author(s) -
McGilchrist C. A.,
Sandland R. L.,
Hennessy J. L.
Publication year - 1983
Publication title -
australian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 0004-9581
DOI - 10.1111/j.1467-842x.1983.tb00385.x
Subject(s) - variable (mathematics) , mathematics , singularity , computer science , point (geometry) , estimation , linear regression , stability (learning theory) , variables , linear model , algorithm , calculus (dental) , mathematical optimization , statistics , machine learning , mathematical analysis , medicine , geometry , management , dentistry , economics
Summary Recursive methods in regression have proved useful in providing diagnostic tools for checking the model as well as checking the stability of the model over time. Such methods are now extended to deal with the problems of singularity that arise when one variable is completely confounded with previously fitted variables up to a particular time point. The problem is solved by setting it in the framework of the general linear model with dependent errors.