Skip to contents

This function simulates upper and lower limits `lims$lower` and `lims$upper` such that: $$P({lims$lower[i] <= sum(unif(n) < 1/i) <= lims$upper[i]} for any i = 1, \ldots, K - 1) = 1 - alpha$$ For more information see "Graphical Test for Discrete Uniformity and its Applications in Goodness of Fit Evaluation and Multiple Sample Comparison" (Säilynoja, Bürkner, Vehtari).

Usage

get_lims(alpha, n, K)

Source

https://github.com/TeemuSailynoja/simultaneous-confidence-bands

Arguments

alpha

Confidence level between 0 and 1.

n

Sample size.

K

Granularity of the uniform partition of the unit interval.

Value

List containing the upper and lower simultaneous confidence bands evaluated at \(z_i = i / K\) for \(i = 1, \ldots, K - 1\).