Search results for "Biproportion"
showing 10 items of 11 documents
The biproportional factorial analysis
1993
Beyond the Factorial Analysis of Correspondences, the paper presents a newmethod of data analysis: the Biproportional Factorial Analysis. In the Factorial Analysis of Correspondences, the matrix to be diagonalised is the product o f the two matrices o f profiles, row and columns: this matrix is not symmetrical. In the Biproportional Factorial Analysis, the matrix to be diagonalised is the symmetrical product o f an intermediate matrix over itself; this intermediate matrix is calculated as the biproportion o f the data matrix over normalisedmargins. This provides a full symmetry between rows and columns. After recalling the Factorial Analysis of Correspondences, the paper recall what it is b…
Forecast Output Coincidence and Biproportion: Two Criteria to Determine the Orientation of an Economy. Comparison for France (1980-1997)
2002
International audience; The method of forecast output coincidence used to determine if sectors are demand-sided or supply-sided in an input-output framework mixes two effects, the structural effect (choosing between demand and supply side models) and the effect of an exogenous factor (final demand or added-value). The note recalls that another method is possible, the comparison of the stability of technical and allocation coefficients, generalized by the biproportional filter: if for a sector, after biproportional filtering, column coefficients are more stable than row coefficients, then this sector is declared as not supply-sided (but one cannot decide that it is demand-sided anyway), and …
Les méthodes biproportionnelles, un outil de reconstitution ou de comparaison de tableaux de contingence
2020
Un tableau de nombres dont on connaît le total de ses colonnes et lignes (ou « marges ») est appelé « tableau de contingence ». Un tel tableau se rencontre quand on étudie les échanges entre pays ou régions, les flux migratoires ou financiers, etc. Le premier problème qu’on étudie est la reconstitution du tableau quand on ne connaît que ses marges, mais pas les données du tableau elles-mêmes, sachant que celles-ci sont néanmoins proches de celles d’un autre tableau. C’est le cas par exemple quand on veut prévoir l’origine des échanges entre pays en connaissant seulement le total de ce qu’ils vont exporter et importer. Le deuxième problème étudié est l’évaluation de ce qui a changé entre deu…
Unicity of biproportion
1994
International audience; The biproportion of S on margins of M is called the intern composition law, K: (S,M) -> X = K(S,M) / X = A S B. A and B are diagonal matrices, algorithmically computed, providing the respect of margins of M. Biproportion is an empirical concept. In this paper, the author shows that any algorithm used to compute a biproportion leads to the me result. Then the concept is unique and no longer empirical. Some special properties are also indicated.
About the criteria of output coincidence for forecasts to determine the orientation of the economy (application for France, 1980-1997)
2000
This note indicates that the method of output coincidence for forecasts used to determine if sectors are demand-driven or supply-driven in an input-output framework mixes two effects, the structural effect (choosing between demand and supply driven models) and the effect of an exogenous factor (final demand or added-value). The note recalls that another method is possible, the comparison of the stability of technical and allocation coefficients, generalized by the biproportional filter: if for a sector, after biproportional filtering, column coefficients are more stable than row coefficients, then this sector is declared as not supply-driven (but one cannot decide that it is demand-driven a…
Bicausative matrices to measure structural change: Are they a good tool?
1999
The causative-matrix method to analyze temporal change assumes that a matrix transforms one Markovian transition matrix into another by a left multiplication of the first matrix; the method is demand-driven when applied to input-output economics. An extension is presented without assuming the demand-driven or supply-driven hypothesis. Starting from two flow matrices X and Y, two diagonal matrices are searched, one premultiplying and the second postmultiplying X, to obtain a result the closer as possible to Y by least squares. The paper proves that the method is deceptive because the diagonal matrices are unidentified and the interpretation of results is unclear. Keywords : Input-Output ; Ch…
A biproportional filter to compare technical and allocation coefficient variations
1997
International audience; In input-output analysis there are two alternate possibilities between Leontief's mechanism (fixed technical coefficients) and Ghosh's mechanism (fixed allocation coefficients). Testing the long term consistency of these mechanisms entails comparing input-output matrices over time. This paper challenges the value of proportional filters (separate comparison of column and row coefficients) and introduces the biproportional filter which allows simultaneous comparison of column and rows. An application is proposed using French input-output tables for 1980 and 1993. The stability of column coefficients cannot be taken for granted and generally, for any sector, both rows …
Biproportional methods of structural change analysis: A typological survey
2004
International audience; Analysts often are interested in learning how much an exchange system has changed over time or how two different exchange systems differ. Identifying structural difference in exchange matrices can be performed using either 'directed' or 'undirected' methods. Directed methods are based on the computation and comparison of column- or row-normalizations of the matrices. The choice of row or column for the normalization implies a specific direction of the exchanges, so that the column-wise normalized results should not be compared to the row-wise normalized results. In this category fall the simple comparison of coefficient matrices and the causative method. Undirected m…
Failure of the normalization of the RAS method : absorption and fabrication effects are still incorrect
2000
The r and s vectors of the RAS method of updating matrices are presented often as corresponding to an absorption effect and a fabrication effect. Here, it is proved that these vectors are not identified, so their interpretation in terms of fabrication and absorption effect is incorrect and even if a normalization was proposed to remove underidentification, this normalization fails and poses many difficulties.. Keywords : Input-Output ; RAS ; Biproportion
A Note on added information in the RAS Procedure: reexamination of some evidence
2006
International audience; An example in Miernyk (1977) presented a rather counterintuitive result, namely that introducing accurate exogenous information into an RAS matrix estimating procedure could lead to an estimate that was worse than one generated by RAS using no exogenous information at all. This became an oft-cited black mark against RAS. Miller and Blair (1985) included a different (and small) illustration of the same possibility. It was recently pointed out by one of us that the Miller/Blair numerical results are wrong. For that reason, we decided to reexamine all the empirical evidence we could find on the subject. While figures in both Miernyk and Miller/Blair appear to be wrong, …