Running analysis of variance (aov) across multiple grouping variables.

grouped_aov(
  data,
  grouping.vars,
  formula,
  effsize = "eta",
  output = "tidy",
  ...
)

Arguments

data	A data frame in which the variables specified in the formula will be found. If missing, the variables are searched for in the standard way.
grouping.vars	Grouping variables.
formula	A formula specifying the model.
effsize	Character describing the effect size to be displayed: `"eta"` (default) or `"omega"`.
output	A character describing what output is expected. Two possible options: `"tidy"` (default), which will return the results, or `"tukey"`, which will return results from Tukey's Honest Significant Differences method for post hoc comparisons. The `"glance"` method to get model summary is currently not supported for this function.
...	Currently ignored.

Examples


# uses dataset included in the `groupedstats` package
set.seed(123)
library(groupedstats)

# effect size
groupedstats::grouped_aov(
  formula = wt ~ mpg,
  data = mtcars,
  grouping.vars = am,
  effsize = "eta"
)
#> For one-way between subjects designs, partial eta squared is equivalent to eta squared.
#> Returning eta squared.
#> For one-way between subjects designs, partial eta squared is equivalent to eta squared.
#> Returning eta squared.
#> # A tibble: 2 x 13
#>      am term  sumsq   df1 meansq F.value   p.value   df2 estimate conf.level
#>   <dbl> <chr> <dbl> <dbl>  <dbl>   <dbl>     <dbl> <dbl>    <dbl>      <dbl>
#> 1     1 mpg    3.77     1   3.77    52.3 0.0000169    11    0.826       0.95
#> 2     0 mpg    6.41     1   6.41    24.4 0.000125     17    0.589       0.95
#> # … with 3 more variables: conf.low <dbl>, conf.high <dbl>, significance <chr>