scores.OD: Orthogonal Distances for PCAloc

In ssMRCD: Spatially Smoothed MRCD Estimator

Orthogonal Distances for PCAloc

Description

Orthogonal Distances for PCAloc

Usage

scores.OD(X, PC, groups, ssMRCD)

Arguments

X	data matrix of observations.
PC	loadings of sparse local PCA.
groups	grouping vector for locality.
ssMRCD	ssMRCD object used for PCA calculation.

Value

Returns vector of orthogonal distances of observations.

See Also

scores, scores.SD, sparsePCAloc, scale_ssMRCD

Examples

# create data set
x1 = matrix(runif(200), ncol = 2)
x2 = matrix(rnorm(200), ncol = 2)
x = list(x1, x2)

# create weighting matrix
W = matrix(c(0, 1, 1, 0), ncol = 2)

# calculate ssMRCD
loccovs = ssMRCD(x, weights = W, lambda = 0.5)

# calculate PCA
pca = sparsePCAloc(eta = 1, gamma = 0.5, cor = FALSE,
                   COVS = loccovs$MRCDcov,
                   increase_rho = list(FALSE, 20, 1))

# calculate scores
scores.OD(X = rbind(x1, x2), PC = pca$PC,
          groups = rep(c(1,2), each = 100), ssMRCD = loccovs)

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