eptest

Epps-Pulley test for normality
16 Downloads
Updated 15 Jun 2024

View License

Function eptest performs Epps-Pulley test for normality.
[h,stat,stat_crit] = eptest(X,alpha)
Input arguments:
INPUT:
X - numerical row vector of real values, N>=8, where N=numel(X);
alpha - significance level, alpha = 0.05 by default.
Must be 0.01 <= alpha <= 0.15.
OUTPUT:
h - test result at significance level alpha, 0 - not rejected, 1 - rejected;
stat - Epps-Pulley statistics value;
stat_crit - interp. tabular critical value for Epps-Pulley statistics for 8<=N<=1000, interp. with beta-function III kind for N>1000.
EXAMPLE:
%Mechanical strength of viscose filament
%(Table 5 in [1])
X = [147,186,141,183,190,123,155,164,183,150,134,170,144,...
99,156,176,160,174,153,162,167,179,78,173,168];
[h,stat,stat_crit] = eptest(X,0.01)
%h = 1
%stat = 0.6115
%stat_crit = 0.5700
%Null hypothesis rejected.
%Convert X to normal distribution
X = log(204-X);
%Repeat test
[h,stat,stat_crit] = eptest(X,0.01)
%h = 0
%stat = 0.0058
%stat_crit = 0.5700
%Null hypothesis not rejected.

Cite As

Tipikin A.A., Prusakov A.A., Timoshenko N.A. Software Implementation of the Epps-Pulley Criterion in Matlab Modeling Environment. Open Education. 2024;28(2):59-72. (In Russ.) https://doi.org/10.21686/1818-4243-2024-2-59-72

MATLAB Release Compatibility
Created with R2023b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.0.1

Updated citation

1.0.0