19.2: Power Curves — Read — Invisible Network

From LibreTexts, under CC BY-NC 4.0, as the source states it; its equations are written in TeX, which the PDF shows typeset. This page at LibreTexts.

We can also create plots that can show us how the power to find an effect varies as a function of effect size and sample size. We willl use the crossing() function from the tidyr package to help with this. This function takes in two vectors, and returns a tibble that contains all possible combinations of those values.

effect_sizes <- c(0.2, 0.5, 0.8) 
sample_sizes = seq(10, 500, 10)

#
input_df <- crossing(effect_sizes,sample_sizes)
glimpse(input_df)

## Observations: 150
## Variables: 2
## $ effect_sizes <dbl> 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0.2, 0…
## $ sample_sizes <dbl> 10, 20, 30, 40, 50, 60, 70, 80, 90, …

Using this, we can then perform a power analysis for each combination of effect size and sample size to create our power curves. In this case, let’s say that we wish to perform a two-sample t-test.

# create a function get the power value and
# return as a tibble
get_power <- function(df){
  power_result <- pwr.t.test(n=df$sample_sizes, 
                             d=df$effect_sizes,
                             type='two.sample')
  df$power=power_result$power
  return(df)
}

# run get_power for each combination of effect size 
# and sample size

power_curves <- input_df %>%
  do(get_power(.)) %>%
  mutate(effect_sizes = as.factor(effect_sizes))

Now we can plot the power curves, using a separate line for each effect size.

ggplot(power_curves, 
       aes(x=sample_sizes,
           y=power, 
           linetype=effect_sizes)) + 
  geom_line() + 
  geom_hline(yintercept = 0.8, 
             linetype='dotdash')

This page titled 19.2: Power Curves was last modified on Mon, 11 Jan 2021 05:14:05 GMT and is shared under a CC BY-NC 4.0 license and was authored, remixed, and/or curated by Russell A. Poldrack via source content that was edited to the style and standards of the LibreTexts platform.

Contents

Text