Estimate power for differences between proportion conflict effects using monte-carlo simulation

pc_modulation_power_fast(
  subjects,
  design,
  A_mc_c_nmst,
  A_mc_nc_nmst,
  A_mnc_c_nmst,
  A_mnc_nc_nmst,
  B_mc_c_nmst,
  B_mc_nc_nmst,
  B_mnc_c_nmst,
  B_mnc_nc_nmst,
  num_sims = 1000,
  alpha = 0.05
)

Arguments

subjects

A number for the number of subjects in simulated experiment

design

A string set to "paired" or "between"

A_mc_c_nmst

A vector for mostly conflict (mc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

A_mc_nc_nmst

A vector for mostly conflict (mc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

A_mnc_c_nmst

A vector for mostly no-conflict (mnc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

A_mnc_nc_nmst

A vector for mostly no-conflict (mnc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

B_mc_c_nmst

A vector for mostly conflict (mc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

B_mc_nc_nmst

A vector for mostly conflict (mc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

B_mnc_c_nmst

A vector for mostly no-conflict (mnc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

B_mnc_nc_nmst

A vector for mostly no-conflict (mnc), conflict trials (c) containing the parameters for an ex-gaussian distribution, c(n, mu, sigma, tau), where n is the number of trials.

num_sims

A number, simulations to run

alpha

A number, alpha criterion

Value

A number, power: the proportion of simulated experiments that returned a p-value less than the alpha criterion for the conflict effect

Details

This function uses monte-carlo simulation to determine statistical power associated for detecting a modulation to a proportion conflict effect, specifically a difference between two proportion conflict effects.

Power is the proportion of simulated experiments that return p-values less than the defined alpha criterion.

Examples

pc_modulation_power_fast(subjects=20,
  design ="paired",
  A_mc_c_nmst = c(80,550,100,100),
  A_mc_nc_nmst = c(20,500,100,100),
  A_mnc_c_nmst = c(20,570,100,100),
  A_mnc_nc_nmst = c(80,500,100,100),
  B_mc_c_nmst = c(80,530,100,100),
  B_mc_nc_nmst = c(20,500,100,100),
  B_mnc_c_nmst = c(20,570,100,100),
  B_mnc_nc_nmst = c(80,500,100,100),
  num_sims = 1000,
  alpha = .05)
#> [1] 0.218