The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

Fixed-sample power and sensitivity

library(anovapowersim)

power_achieved() and power_sensitivity() are experimental. They use the same balanced design construction, ANOVA fitting, covariance handling, and simulation controls as power_n().

Achieved power

Use power_achieved() when the sample size and partial eta squared are fixed. The n argument is the number of subjects per between-subject cell, or total N for a purely within-subject design.

power_achieved(
  between = c(group = 2),
  within = c(time = 2),
  term = "group:time",
  target_pes = 0.14,
  n = 20,
  n_sims = 5000,
  parallel = TRUE,
  seed = 123
)

The result reports simulated achieved power as the primary estimate and calculated power as a diagnostic.

Sensitivity

Use power_sensitivity() when the sample size is fixed and the minimum detectable partial eta squared is unknown. It simulates effect sizes until it finds a bracket around the requested power, then reports an explicitly simulated upper bracket as pes_needed.

power_sensitivity(
  between = c(group = 2),
  within = c(time = 2),
  term = "group:time",
  n = 20,
  power = 0.90,
  n_sims = 5000,
  pes_tol = 0.001,
  parallel = TRUE,
  seed = 123
)

Because simulated power has Monte Carlo variability, use enough simulations for the precision you need and inspect all visited effect sizes in $results.

Covariance and calculated-power alternatives

Both functions accept a within_covariance() object for repeated-measures designs. See Covariance and nonsphericity for cell naming, custom standard deviations and correlations, and Greenhouse–Geisser handling.

To skip simulations, use power_achieved_calc() or power_sensitivity_calc(). These are covered in the Calculated power guide.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.