This function extends leveneTest to a multivariate
response setting. It performs the Levene test of homogeneity of variances
for each of a set of response variables, and prints a compact summary.
Arguments
- y
A data frame or matrix of numeric response variables in a multivariate linear model.
- group
a vector or factor object giving the group for the corresponding elements of the rows of
y- center
The name of a function to compute the center of each group;
meangives the original Levene's (1960) test; the default,median, provides a more robust test suggested by Brown and Forsythe (1974).- ...
other arguments, passed to
leveneTest
Value
An object of classes "anova" and "data.frame", with one observation
for each response variable in y.
References
Levene, H. (1960). Robust Tests for Equality of Variances. In Olkin, I. et al. (Eds.), Contributions to Probability and Statistics: Essays in Honor of Harold Hotelling, Stanford University Press, 278-292.
Brown, M. B. & Forsythe, A. B. (1974). Robust Tests For Equality Of Variances Journal of the American Statistical Association, 69, 364-367.
Examples
leveneTests(iris[,1:4], iris$Species)
#> Levene's Tests for Homogeneity of Variance (center = median)
#>
#> df1 df2 F value Pr(>F)
#> Sepal.Length 2 147 6.3527 0.002259 **
#> Sepal.Width 2 147 0.5902 0.555518
#> Petal.Length 2 147 19.4803 3.129e-08 ***
#> Petal.Width 2 147 19.8924 2.261e-08 ***
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# handle a 1-column response?
leveneTests(iris[,1, drop=FALSE], iris$Species)
#> Levene's Tests for Homogeneity of Variance (center = median)
#>
#> df1 df2 F value Pr(>F)
#> Sepal.Length 2 147 6.3527 0.002259 **
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
data(Skulls, package="heplots")
leveneTests(Skulls[,-1], Skulls$epoch)
#> Levene's Tests for Homogeneity of Variance (center = median)
#>
#> df1 df2 F value Pr(>F)
#> mb 4 145 1.0367 0.3905
#> bh 4 145 0.7171 0.5816
#> bl 4 145 0.6797 0.6071
#> nh 4 145 1.0418 0.3878