Confidence intervals for (partial) eta-squared and omega-squared for linear models.

This function will convert a linear model object to a dataframe containing statistical details for all effects along with effect size measure and its confidence interval. For more details, see effectsize::eta_squared and effectsize::omega_squared.

lm_effsize_ci(object, effsize = "eta", partial = TRUE, conf.level = 0.95, ...)

Arguments

object	The linear model object (can be of class lm, aov, anova, or aovlist).
effsize	Character describing the effect size to be displayed: "eta" (default) or "omega".
partial	Logical that decides if partial eta-squared or omega-squared are returned (Default: TRUE). If FALSE, eta-squared or omega-squared will be returned. Valid only for objects of class lm, aov, anova, or aovlist.
conf.level	Numeric specifying Level of confidence for the confidence interval (Default: 0.95).
...	Ignored.

Value

A dataframe with results from stats::lm() with partial eta-squared, omega-squared, and bootstrapped confidence interval for the same.

Author

Indrajeet Patil

Examples

# for reproducibility
set.seed(123)

# model
mod <-
  stats::aov(
    formula = mpg ~ wt + qsec + Error(disp / am),
    data = mtcars
  )

# dataframe with effect size and confidence intervals
groupedstats::lm_effsize_ci(mod)
#> # A tibble: 2 x 12
#>   group  term  sumsq   df1 meansq F.value p.value   df2 estimate conf.level
#>   <chr>  <chr> <dbl> <dbl>  <dbl>   <dbl>   <dbl> <dbl>    <dbl>      <dbl>
#> 1 Within wt     87.2     1   87.2   12.0  0.00176    27    0.308       0.95
#> 2 Within qsec   34.2     1   34.2    4.72 0.0387     27    0.149       0.95
#> # … with 2 more variables: conf.low <dbl>, conf.high <dbl>