Applied Econometrics with EViews: A Complete Guide to Factor Analysis скачать в хорошем качестве

Applied Econometrics with EViews: A Complete Guide to Factor Analysis

Factor Analysis is a powerful multivariate statistical method used to overcome the "curse of dimensionality" by explaining the covariance structure of a large set of observed variables in terms of a smaller number of unobserved variables, termed factors. This method helps summarize data and identify hidden structures, making it highly useful in economic and financial analysis. In EViews, exploratory factor analysis is carried out using the Factor object. To begin, you can highlight the desired series, right-click and select Open / as Factor, or from a Group object, select Proc / Make Factor... The Factor Specification dialog will appear with two main tabs. The Data tab allows you to specify whether to fit a correlation or covariance matrix. The Estimation tab provides various extraction methods such as Maximum Likelihood (ML), Generalized Least Squares (GLS), or Principal Factors. A crucial step is determining the number of factors to retain. EViews supports numerous automatic selection criteria, including MAP (the default), Kaiser-Guttman, Bai & Ng, or Ahn & Horenstein. Following estimation, users typically perform Factor Rotation via Proc / Rotate..., utilizing orthogonal or oblique methods like Varimax or Promax to achieve a simpler factor structure for easier interpretation. Finally, you can estimate and save the factor scores into your workfile using the Proc / Make Scores... command.