Journal article | Zeitschriftenartikel

Consistent noisy independent component analysis

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 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.

Consistent noisy independent component analysis

Urheber*in: Bonhomme, Stéphane; Robin, Jean-Marc

Free access - no reuse

Extent
Seite(n): 12-25
Language
Englisch
Notes
Status: Postprint; begutachtet (peer reviewed)

Bibliographic citation
Journal of Econometrics, 149(1)

Subject
Wirtschaft
Sozialwissenschaften, Soziologie
Erhebungstechniken und Analysetechniken der Sozialwissenschaften
Wirtschaftsstatistik, Ökonometrie, Wirtschaftsinformatik
Faktorenanalyse
lineares Modell

Event
Geistige Schöpfung
(who)
Bonhomme, Stéphane
Robin, Jean-Marc
Event
Veröffentlichung
(where)
Niederlande
(when)
2009

DOI
URN
urn:nbn:de:0168-ssoar-214088
Rights
GESIS - Leibniz-Institut für Sozialwissenschaften. Bibliothek Köln
Last update
21.06.2024, 4:26 PM CEST

Data provider

This object is provided by:
GESIS - Leibniz-Institut für Sozialwissenschaften. Bibliothek Köln. If you have any questions about the object, please contact the data provider.

Object type

  • Zeitschriftenartikel

Associated

  • Bonhomme, Stéphane
  • Robin, Jean-Marc

Time of origin

  • 2009

Other Objects (12)