Choosing the number of factors in independent factor analysis model

Viroli, Cinzia (author)

Independent Factor Analysis (IFA) has recently been proposed in the signal processing literature as a way to model a set of observed variables through linear combinations of hidden independent ones plus a noise term. Despite the peculiarity of its origin the method can be framed within the latent variable model domain and some parallels with the ordinary Factor Analysis can be drawn. If no prior information on the latent structure is available a relevantissue concerns the correct specification of the model. In this work some methods to detect the number of significant latent variables are investigated. Moreover, since the method defines a probability density function for the latent variables by mixtures of gaussians, the correct numberof mixture components must also be determined. This issue will be treated according to two main approaches. The first one amounts to carry out alikelihood ratio test. The other one is based on a penalized form of the likelihood, that leads to the so called information criteria. Some simulationsand empirical results on real data sets are finally presented.

• Language: English
• Work type: Not categorized
• Typology: 1.01 - Original Scientific Article
• Organization: FDV - Faculty of Social Sciences
• Year: 2005
• Number of pages: Str. 219-229
• Numbering: Vol. 2, no. 2
• PID: 20.500.12556/RUL-22453
• UDC: 303
• ISSN on article: 1854-0023
• COBISS.SI-ID: 24315485
• Publication date in RUL: 11.07.2014

Record is a part of a journal

• Title: Advances in methodology and statistics
• Shortened title: Metodol. zv.
• Publisher: Fakulteta za družbene vede
• ISSN: 1854-0023
• COBISS.SI-ID: 215795712