Skip to main content
. Author manuscript; available in PMC: 2016 Jun 10.
Published in final edited form as: J Comput Graph Stat. 2015 Dec 10;24(4):975–993. doi: 10.1080/10618600.2014.948179

Figure 1.

Figure 1

True and estimated covariance matrix eigenvalues based on the hard- and soft-thresholding methods for a simulated data set with d = 1000 and n = 50. This shows that some eigenvalues are highly over-estimated by the hard thresholding method. The soft thresholding method gives major improvement for this example.