pp_f2: Power plot for Cohen's f2

In the-mad-statter/washu: Helpful Functions for WashU Statistical Consultations

Power plot for Cohen's f2

Description

Power plot for Cohen's f2

Usage

pp_f2(
  data,
  N,
  u1 = 1,
  u2 = 0,
  sig.level = 0.05,
  min_pwr = NULL,
  effect = .data$f2,
  labels = .data$f2
)

Arguments

data	tibble of effect size data
N	total sample sizes for which to compute power
u1	degrees of freedom for effect generator
u2	degrees of freedom for other predictors (1 + u1 + u2 + v = N)
sig.level	significance level (Type I error probability)
min_pwr	minimum desirable power to label (NULL for no label)
effect	variable in data representing the effect sizes
labels	effect labels to be used for legend

Value

object of class "ggplot"

Note

The effect variable is converted to factor in the given order and labels applied respectively.

References

Cohen, J. (1988). Statistical power analysis for the behavioral sciences (2nd ed.). Hillsdale,NJ: Lawrence Erlbaum.

See Also

ggplot, pwr.f2.test

Examples

## Exercise 9.1 P. 424 from Cohen (1988)
dplyr::tibble(
  f2 = 0.1 / (1 - 0.1),
  y = "sales",
  x = "demographics",
  source = "Cohen (1988)"
) %>%
  pp_f2(85:105,
    u1 = 5,
    labels = sprintf("%s %s", format(round(f2, 2), nsmall = 2), source)
  )

the-mad-statter/washu documentation built on May 5, 2024, 10:26 a.m.