LISREL: Gradient and Hessian of the fitting function

H Neudecker and A Satorra

No 293133, University of Amsterdam, Actuarial Science and Econometrics Archive from University of Amsterdam, Faculty of Economics and Business

Abstract: Latent-variable models are nowadays frequently used in economic, social and behavioral studies to analyze relationships among variables. The LISREL model is a general model that integrates the classical simultaneous-equation model developed in econometrics with the factor-analysis model developed by psychometricians. The classical "errors-in-variables" model is also a particular case of LISREL. In this paper we obtain the hessian of a general type of fitting function for the LISREL model. Although the expressions of the first derivatives are known and widely used, the expressions obtained for the second derivatives are a novelty and may have practical implications. For instance, the expressions for the hessian would be needed to implement true Newton fitting algorithms, or when using observed hessians (instead of expected) in evaluating the asymptotic distribution of statistics of interest.

Keywords: Research; Methods/Statistical; Methods (search for similar items in EconPapers)
Pages: 12
Date: 1989-05
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ageconsearch.umn.edu/record/293133/files/amsterdam076.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ags:amstas:293133

DOI: 10.22004/ag.econ.293133

Access Statistics for this paper

More papers in University of Amsterdam, Actuarial Science and Econometrics Archive from University of Amsterdam, Faculty of Economics and Business Contact information at EDIRC.
Bibliographic data for series maintained by AgEcon Search ().