Variance Homogeneity Tests — stat_hov

Tests the equality of variances across the levels of group: Levene (via car::leveneTest, centering on median or mean), Bartlett (assumes normality), or the two-level F test.

Usage

stat_hov_test(
  data,
  .cols,
  group,
  .by = NULL,
  method = c("levene", "bartlett", "f"),
  center = c("median", "mean")
)

Arguments

data: A data frame.
.cols: <tidy-select> Numeric response column(s); each column is analysed separately.
group: <tidy-select> Single factor column.
.by: <tidy-select> Optional slice columns.
method: "levene", "bartlett", or "f".
center: For Levene: "median" (Brown-Forsythe, default) or "mean".

Value

A tibble with class stat_infer: variable, .by identifiers, n_used, statistic, df, df2, p.value, sig, method.

Examples

stat_hov_test(ToothGrowth, .cols = len, group = supp)
#> Variance homogeneity test 
#> # A tibble: 1 × 8
#>   variable n_used statistic    df   df2 p.value method                     sig  
#> * <chr>     <int>     <dbl> <int> <int>   <dbl> <chr>                      <chr>
#> 1 len          60      1.21     1    58   0.275 median-centered Levene te… ""   
stat_hov_test(mtcars, .cols = mpg, group = cyl, method = "bartlett")
#> Variance homogeneity test 
#> # A tibble: 1 × 8
#>   variable n_used statistic    df   df2 p.value method                     sig  
#> * <chr>     <int>     <dbl> <dbl> <dbl>   <dbl> <chr>                      <chr>
#> 1 mpg          32      8.39     2    NA  0.0150 Bartlett test of homogene… *