boxM performs the Box's (1949) M-test for homogeneity of covariance matrices obtained from multivariate normal data according to one or more classification factors. The test compares the product of the log determinants of the separate covariance matrices to the log determinant of the pooled covariance matrix, analogous to a likelihood ratio test. The test statistic uses a chi-square approximation. Uses permutations to estimate the degrees of freedom under the null
Usage
boxM_fast(Y, group, method = c("pearson", "spearman"))Arguments
- Y
response variable matrix
- group
a factor defining groups, number of entries must equal nrow(Y)
- method
Specify type of correlation: "pearson", "spearman"
Examples
data(iris)
boxM_fast( as.matrix(iris[, 1:4]), iris[, "Species"])
#> $Si_logDet
#> [,1]
#> [1,] -1.040269
#> [2,] -2.481781
#> [3,] -1.984930
#>
#> $dfs
#> [,1]
#> [1,] 49
#> [2,] 49
#> [3,] 49
#>
#> $dfchi
#> [1] 20
#>
#> $pval
#> [1] 5.455647e-08
#>
#> $X2
#> [1] 73.1845
#>
#> $logdet
#> [1] -1.040269 -2.481781 -1.984930
#>
#> $stat_logdet
#> [1] NA
#>