practical_pars_ANOVA: Find practical values of the parameters for an ANOVA

View source: R/theoretical_power.R

practical_pars_ANOVAR Documentation

Find practical values of the parameters for an ANOVA

Description

Performs a binary search to find the parameter values that reach power rho at the smallest effect size. If no effect sizes are sufficient to reach power rho, returns the parameters for the largest effect size in input grid.

Usage

practical_pars_ANOVA(
  effect_size_grid,
  epsilon,
  n,
  rho = 0.8,
  alpha = 0.05,
  groups = 3,
  M_start = min(12, floor(n/2/groups)),
  alpha0_start = 0.2,
  M_max = floor(n/2/groups)
)

Arguments

effect_size_grid

Grid of effect sizes to search over

epsilon

The privacy parameter.

n

The number of observations (number of rows in the database).

rho

The desired power threshold

alpha

The significance level. Defaults to 0.05.

groups

The number of groups in each subsample for ANOVA.

M_start

Starting value of M

alpha0_start

Starting value of alpha0

M_max

The maximum M to search over.

Value

The output will be a list with the achievable power, the corresponding two parameter values, and the minimum effect size


diff-priv-ht/nonpmRegPkg documentation built on Feb. 6, 2023, 5:22 p.m.