Fiche du document
- handle: 10670/1.g81xuj
- hal: hal-00642732
- doi: 10.1016/j.jeconom.2008.12.019
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.jeconom.2008.12.019
Mots-clés
Independent Component Analysis Factor Analysis High-order moments Noisy ICA C - Mathematical and Quantitative Methods/C.C1 - Econometric and Statistical Methods and Methodology: General/C.C1.C14 - Semiparametric and Nonparametric Methods: GeneralSujets proches
Philosophy--Methodology Mistakes ICA (Independent component analysis)Citer ce document
Stéphane Bonhomme et al., « Consistent Noisy Independent Component Analysis », HAL-SHS : économie et finance, ID : 10.1016/j.jeconom.2008.12.019
Métriques
Partage / Export
Résumé
We study linear factor models under the assumptions that factors are mutually independent and independent of errors, and errors can be correlated to some extent. Under the factor non-Gaussianity, second-to-fourth-order moments are shown to yield full identification of the matrix of factor loadings. We develop a simple algorithm to estimate the matrix of factor loadings from these moments. We run Monte Carlo simulations and apply our methodology to data on cognitive test scores, and financial data on stock returns.