Canonne_power: Canonne Power

View source: R/Canonne_implementation.R

Canonne_powerR Documentation

Canonne Power

Description

Determines the power of the test proposed by Canonne et al. by simulation.

Usage

Canonne_power(
  eff,
  n,
  n_zeros,
  d,
  epsilon,
  delta,
  alpha,
  nsims,
  mc.cores = detectCores() - 1,
  PC = FALSE
)

Arguments

eff

Determines the mean of the alternate distribution (which will be 'd - n_zeros' repetitions of 'eff').

n

Number of observations (number of rows of the database).

n_zeros

Number of dimensions (out of 'd') with no effect.

d

Number of dimensions (number of columns of the database).

epsilon

The privacy parameter.

delta

The privacy parameter.

alpha

As in the paper, this is the effect size the test should be able to detect. THIS IS NOT THE SIGNIFICANCE LEVEL!

nsims

The number of times to run the test.

mc.cores

Number of cores used for parallelization.

PC

flag for whether or not computation is on a PC

Value

A double between 0 and 1.


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