Updating and estimating a social accounting matrix
1994, «Recovering information from incomplete or partial multisectoral economic data», The Review of Economics and Statistics, p.
1951, «On information and sufficiency», The annals of mathematical statistics, p.
In addition, an appendix includes a listing of the computer code in the GAMS language used in the procedure.
This work involves the construction of the 2013 Social Accounting Matrix for the D. Given the nature of these data, we have resorted to the bottom-up approach to the development of this SAM and methods of RAS and cross-entropy for its balancing. 1997, «Entropy optimisation methods for the estimation of tables», Classification, Data Analysis and Data Highways, p.
The paper describes the RAS procedure and “cross entropy” method, and compares the underlying “information theory” and classical statistical approaches to parameter estimation.The method is flexible and powerful when dealing with scattered and inconsistent data.It allows incorporating errors in variables, inequality constraints, and prior knowledge about any part of the SAM (not just row and column sums). 2002, «Balancing a social accounting matrix», Laval : Centre de Recherche en Économie et Finances Appliquées (CREFA) Université Laval. 1996, Maximum entropy econometrics : Robust estimation with limited data, Wiley New York.