ps.1sz: Estimate the power of a one-sample z test by simulation

In mdedge/stfspack: Functions to Support Statistical Thinking from Scratch

Description

Simulates nsims normal samples with expectations differing from a value specified by the null hypothesis by d (known) standard deviations. For each sample, the null hypothesis is tested by a one-sample z test, and the p value is compared with the specified significance level.

Usage

ps.1sz(d, n, level = 0.05, nsim = 10000)

Arguments

d	An effect size: the number of (known) standard deviations by which the expectation of the sampled data differs from a hypothesized expectation.
n	The size of each simulated sample.
level	The significance level of the one-sample z-test.
nsim	The number of simulated samples to run.

Value

The proportion of p values less than the specified level (i.e. the power).

Examples

ps.1sz(d = 0.5, n = 20)

mdedge/stfspack documentation built on May 9, 2019, 8:17 a.m.