Computes the (centered) log-ratio covariance matrix (see below).
Usage
covariance(x, ...)
# S4 method for CompositionMatrix
covariance(x, center = TRUE, method = "pearson")
# S4 method for ALR
covariance(x, method = "pearson")
# S4 method for CLR
covariance(x, method = "pearson")Arguments
- x
A
CompositionMatrixobject.- ...
Currently not used.
- center
A
logicalscalar: should the centered log-ratio covariance matrix be computed?- method
A
characterstring indicating which covariance is to be computed (seestats::cov()).
Value
A matrix.
Methods (by class)
covariance(ALR): Computes the log-ratio covariance matrix (Aitchison 1986, definition 4.5).covariance(CLR): Computes the centered log-ratio covariance matrix (Aitchison 1986, definition 4.6).
References
Aitchison, J. (1986). The Statistical Analysis of Compositional Data. London: Chapman and Hall, p. 64-91.
Greenacre, M. J. (2019). Compositional Data Analysis in Practice. Boca Raton: CRC Press.
See also
Other statistics:
aggregate(),
dist,
mahalanobis(),
margin(),
mean(),
metric_var(),
quantile(),
scale(),
variation()
Examples
## Data from Aitchison 1986
data("hongite")
## Coerce to compositional data
coda <- as_composition(hongite)
## Log-ratio covariance matrix
## (Aitchison 1986, definition 4.5)
covariance(coda, center = FALSE)
#> A_E B_E C_E D_E
#> A_E 0.1385604 0.2641498 -0.2233304 0.1214018
#> B_E 0.2641498 0.6490135 -0.7020147 0.1444000
#> C_E -0.2233304 -0.7020147 0.9476375 0.0116220
#> D_E 0.1214018 0.1444000 0.0116220 0.1870579
## Centered log-ratio covariance matrix
## (Aitchison 1986, definition 4.6)
covariance(coda, center = TRUE)
#> A B C D E
#> A 0.06443676 0.17907284 -0.24408053 0.01453821 -0.01396727
#> B 0.17907284 0.55298309 -0.73371823 0.02658296 -0.02492066
#> C -0.24408053 -0.73371823 0.98026080 -0.04186819 0.03940616
#> D 0.01453821 0.02658296 -0.04186819 0.04745430 -0.04670728
#> E -0.01396727 -0.02492066 0.03940616 -0.04670728 0.04618906