NMSE ofˆ(ofˆ ofˆ(, ,) for the AR(1) covariance model in (35) with = (0.2, 0.3, 0.4, 0.5), = (25, 50, 75, 100), dimension = 200, and sampling from MVT distributions with = 8 d.o.f.

Source publication

Fig. 1: The graphs of MSE, squared bias and the variance of a shrinkage...

Fig. 2: Limiting NMSE in (28) as a function of limiting sphericity 0...

Fig. 5: NMSE ofˆ(ofˆ ofˆ(, ,) for the AR(1) covariance model in (35)...

Fig. 9: Estimated d.o.f. parameter of MVT distribution for OMX Helsinki...

Linear shrinkage of sample covariance matrix or matrices under elliptical distributions: a review

Preprint

Full-text available

Aug 2023

Esa Ollila

This chapter reviews methods for linear shrinkage of the sample covariance matrix (SCM) and matrices (SCM-s) under elliptical distributions in single and multiple populations settings, respectively. In the single sample setting a popular linear shrinkage estimator is defined as a linear combination of the sample covariance matrix (SCM) with a scale...