write_manual() generates copy-pasteable base R code that
reproduces a powerrules calculation using the paper’s constants (2.5 for
80% power, 3.3 for 95% power, 1.64 for the critical value with 90% CIs).
This lets researchers verify the computation without any dependencies
beyond base R.
Running the pipeline
Suppose we plan to replicate Ahler and Sood (2018), who find that correcting respondents’ misperceptions of their out-party reduces affective polarization. The standard deviation of feeling thermometer responses in the 2020 ANES is 20.8. We plan to recruit 500 respondents per condition and assume a treatment effect of 3 points (the lower bound of Ahler and Sood’s 95% confidence interval).
library(powerrules)
result <- from_sd(sd_y = 20.8) |>
find_power(n = 500, tau = 3)#> -- Power Analysis ------------------------------------------------------
#> Design: balanced, between-subjects
#> Source: reference population SD
#> CI level: 90% (size-0.05 test of directional hypothesis)
#>
#> Inputs:
#> SD(Y) = 20.8
#> n = 500 per condition (1,000 total)
#> tau = 3
#>
#> Predicted SE = 2 * 20.8 / sqrt(2 * 500) = 1.32 [Rule 3]
#> tau / SE = 3 / 1.32 = 2.28
#> Power = 1 - pnorm(1.64 - 2.28) = 74% [Rule 2]
#>
#> -- Manuscript sentence (edit as needed) --------------------------------
#> For a balanced, between-subjects design with 500 respondents per
#> condition (1,000 total), assuming a standard deviation of 20.8, the
#> predicted standard error is 1.32. Using a one-sided test at the 0.05
#> level, the experiment has 74% power to detect a treatment effect of 3
#> units.Generating the manual calculation code
write_manual() takes the result and prints a
self-contained base R script:
write_manual(result)#> -- Manual Calculation --------------------------------------------------
#>
#> # Manual power calculation
#>
#> # --- Inputs ---
#> sd_y <- 20.8 # SD of outcome in reference population
#> n <- 500 # respondents per condition
#> tau <- 3 # assumed treatment effect
#>
#> # --- Predicted SE (Rule 3) ---
#> se <- 2 * sd_y / sqrt(2 * n)
#>
#> # --- Power (Rule 2) ---
#> power <- 1 - pnorm(1.64 - tau / se)
#>
#> cat("Predicted SE: ", round(se, 2), "\n")
#> cat("tau / SE: ", round(tau / se, 2), "\n")
#> cat("Power: ", round(power * 100), "%\n")Running the generated code
The generated code computes the predicted SE and power using base R only. The result matches the analytical 74% from powerrules.
# Manual power calculation
# --- Inputs ---
sd_y <- 20.8 # SD of outcome in reference population
n <- 500 # respondents per condition
tau <- 3 # assumed treatment effect
# --- Predicted SE (Rule 3) ---
se <- 2 * sd_y / sqrt(2 * n)
# --- Power (Rule 2) ---
power <- 1 - pnorm(1.64 - tau / se)
cat("Predicted SE: ", round(se, 2), "\n")#> Predicted SE: 1.32#> tau / SE: 2.28#> Power: 74 %