Returns the (partial) eta-squared, (partial) omega-squared statistic or Cohen's F for all terms in an anovas. anova_stats() returns a tidy summary, including all these statistics and power for each term.

eta_sq(model, partial = FALSE, ci.lvl = NULL, n = 1000)

omega_sq(model, partial = FALSE, ci.lvl = NULL, n = 1000)

cohens_f(model)

anova_stats(model, digits = 3)

Arguments

model

A fitted anova-model of class aov or anova. Other models are coerced to anova.

partial

Logical, if TRUE, the partial eta-squared is returned.

ci.lvl

Scalar between 0 and 1. If not NULL, returns a data frame with effect sizes including lower and upper confidence intervals.

n

Number of bootstraps to be generated.

digits

Number of decimal points in the returned data frame.

Value

A data frame with the term name(s) and effect size statistics; if ci.lvl is not NULL, a data frame including lower and upper confidence intervals is returned. For anova_stats(), a tidy data frame with all statistics is returned (excluding confidence intervals).

Details

For eta_sq() (with partial = FALSE), due to non-symmetry, confidence intervals are based on bootstrap-methods. In this case, n indicates the number of bootstrap samples to be drawn to compute the confidence intervals.

For partial eta-squared (eta_sq() with partial = TRUE), confidence intervals are based on get.ci.partial.eta.squared and for omega-squared, confidence intervals are based on conf.limits.ncf. Confidence intervals for partial omega-squared is also based on bootstrapping.

References

Levine TR, Hullett CR (2002): Eta Squared, Partial Eta Squared, and Misreporting of Effect Size in Communication Research (pdf)

Tippey K, Longnecker MT (2016): An Ad Hoc Method for Computing Pseudo-Effect Size for Mixed Model. (pdf)

Examples

# load sample data data(efc) # fit linear model fit <- aov( c12hour ~ as.factor(e42dep) + as.factor(c172code) + c160age, data = efc ) eta_sq(fit)
#> # A tibble: 3 x 2 #> term etasq #> <chr> <dbl> #> 1 as.factor(e42dep) 0.266 #> 2 as.factor(c172code) 0.00540 #> 3 c160age 0.0484
omega_sq(fit)
#> # A tibble: 3 x 2 #> term omegasq #> <chr> <dbl> #> 1 as.factor(e42dep) 0.263 #> 2 as.factor(c172code) 0.00377 #> 3 c160age 0.0476
eta_sq(fit, partial = TRUE)
#> # A tibble: 3 x 2 #> term partial.etasq #> <chr> <dbl> #> 1 as.factor(e42dep) 0.281 #> 2 as.factor(c172code) 0.00788 #> 3 c160age 0.0665
# CI for eta-squared requires apaTables packages
# NOT RUN { if (requireNamespace("apaTables", quietly = TRUE)) { eta_sq(fit, partial = TRUE, ci.lvl = .8) } # }
anova_stats(car::Anova(fit, type = 2))
#> # A tibble: 4 x 12 #> term sumsq meansq df statistic p.value etasq partial.etasq omegasq #> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> #> 1 as.factor~ 4.26e5 1.42e5 3 80.3 0 0.212 0.224 0.209 #> 2 as.factor~ 7.35e3 3.68e3 2 2.08 0.126 0.004 0.005 0.002 #> 3 c160age 1.05e5 1.05e5 1 59.4 0 0.052 0.066 0.051 #> 4 Residuals 1.48e6 1.77e3 834 NA NA NA NA NA #> # ... with 3 more variables: partial.omegasq <dbl>, cohens.f <dbl>, power <dbl>