On the Inverse of the Sum of Matrices

By K. Miller. 1981

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Cross-Validation for Correlated Data (2019, background): “where the identity Cov ( y−k,y−k )−1 Cov ( y−k, yk ) = 1n−1ρ/ ( σ + ρ ( n − 1 )) is based on the result by Miller (1981). The intuition behind the biasedness of CV in this setting is that although GLS does not utilizes explicitly estimated random effect realizations, its estimated model coefficients”
The Econometrics of the Hodrick-Prescott Filter (2016, methodology): “Our strategy will be to use such a result, as obtained in Miller (1981), in order to obtain a tractable expression for τ̂Tt .”
Partial least squares discriminant analysis: taking the magic away (2014, background): “This simpli ﬁ es the preceding equation to However, the value of D for LDA is given by At this stage, we need a lemma [9] that states that if matrix A is invertible (as is X ′ X ) and matrix B is of rank 1 (which is the case for where g is the trace of BA (cid:1) 1 .”