objective_matrix: Calculation of Objective Function

In ssMRCD: Spatially Smoothed MRCD Estimator

Calculation of Objective Function

Description

Calculation of the value of the objective function for the ssMRCD for a given list of matrices, lambda and a weighting matrix according to formula (3) in Puchhammer and Filzmoser (2023).

Usage

objective_matrix(matrix_list, lambda, weights)

Arguments

matrix_list	a list of matrices K_i
lambda	scalar smoothing parameter
weights	matrix of weights

Value

Returns the value of the objective function using matrices K_i.

References

Puchhammer P. and Filzmoser P. (2023): Spatially smoothed robust covariance estimation for local outlier detection. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.48550/arXiv.2305.05371")}

Examples

# construct matrices
k1 = matrix(c(1,2,3,4), nrow = 2)
k2 = matrix(c(1,3,5,7), nrow = 2)

# construct weighting matrix
W = matrix(c(0, 1, 1, 0), nrow = 2)

objective_matrix(list(k1, k2), 0.5, W)

ssMRCD documentation built on Sept. 11, 2024, 5:14 p.m.