On BIC's Selection Consistency for Discriminant Analysis
15 Pages Posted: 24 Nov 2008 Last revised: 13 Oct 2009
Date Written: October 21, 2008
Abstract
Linear and/or quadratic discriminant analysis (based on finite Gaussian mixture) is one of the most useful classification methods, for which the problem of variable selection is poorly understood. To fill this important theoretical gap, a novel BIC-type selection criterion in conjunction with a backward elimination procedure is proposed. We show theoretically that the new method is able to identify the true Gaussian structure consistently, even with a heteroscedastic covariance structure. Numerical studies are presented to demonstrate the new method's usefulness.
Keywords: BIC, Discriminant Analysis, Gaussian Mixture
JEL Classification: C52, C14
Suggested Citation: Suggested Citation
Do you want regular updates from SSRN on Twitter?
Recommended Papers
-
Portfolio Selection and Asset Pricing Models
By Lubos Pastor
-
A Test for the Number of Factors in an Approximate Factor Model
-
Comparing Asset Pricing Models: an Investment Perspective
By Lubos Pastor and Robert F. Stambaugh
-
Risk Reduction in Large Portfolios: Why Imposing the Wrong Constraints Helps
By Tongshu Ma and Ravi Jagannathan
-
On Portfolio Optimization: Forecasting Covariances and Choosing the Risk Model
By Louis K.c. Chan, Jason J. Karceski, ...
-
Honey, I Shrunk the Sample Covariance Matrix
By Olivier Ledoit and Michael Wolf
-
Portfolio Selection with Parameter and Model Uncertainty: A Multi-Prior Approach
By Lorenzo Garlappi, Tan Wang, ...
-
Portfolio Selection with Parameter and Model Uncertainty: A Multi-Prior Approach
By Lorenzo Garlappi, Tan Wang, ...
-
Portfolio Constraints and the Fundamental Law of Active Management