COMPARING DISTRIBUTIONS: THE TWO-SAMPLE ANDERSON-DARLING TEST AS AN ALTERNATIVE TO THE KOLMOGOROV-SMIRNOFF TEST

Journal Title: Journal of Applied Quantitative Methods - Year 2011, Vol 6, Issue 3

Abstract

This paper introduces the two-sample Anderson-Darling (AD) test of goodness of fit as a tool for comparing distributions, response time distributions in particular. We discuss the problematic use of pooling response times across participants, and alternative tests of distributions, the most common being the Kolmogorov-Smirnoff (KS) test. We compare the KS test and the AD test, presenting conclusive evidence that the AD test is more powerful: when comparing two distributions that vary (1) in shift only, (2) in scale only, (3) in symmetry only, or (4) that have the same mean and standard deviation but differ on the tail ends only, the AD test proves to detect differences better than the KS test. In addition, the AD test has a type I error rate corresponding to alpha whereas the KS test is overly conservative. Finally, the AD test requires less data than the KS test to reach sufficient statistical power.

Authors and Affiliations

Sonja ENGMANN, Denis COUSINEAU

Keywords

Related Articles

Specialisation and Concentration Patterns in the Romanian Economy

The economic specialisation of the regions and the spatial concentration of the economic activities are reflecting the same reality from two different perspectives. Our research is an attempt to capture the main patterns...

On Measuring Software Complexity

In this paper we measure one internal measure of software products, namely software complexity. We present one method to determine the software complexity proposed in literature and we try to validate the method empirica...

Methods of Portfolio Management for Listed Shares. Some Features for the Romanian Private Pension Funds

Recently, Romania put into practice the private pension system, which includes compulsory pensions and voluntary ones, as alternatives to statutory (public) pension scheme. According to the Romanian laws, private pension...

MEASURING PASSENGER SATISFACTION: A STRATEGY BASED ON RASCH ANALYSIS AND THE ANOM

Measuring passenger satisfaction presents several difficulties since customer satisfaction in the public transport sector is subject to different conditions which are different than those that affect other sectors. In th...

Logistic Regression to Describe How the Relationship between Social Connection and Self-Rated Health Varies by Gender

Social Scientists and health researchers have allocated a great deal of time trying to understand the social correlates of health outcomes, some in the question of the association between social relationships and such ou...

Download PDF file
  • EP ID EP162123
  • DOI -
  • Views 64
  • Downloads 0

How To Cite

Sonja ENGMANN, Denis COUSINEAU (2011). COMPARING DISTRIBUTIONS: THE TWO-SAMPLE ANDERSON-DARLING TEST AS AN ALTERNATIVE TO THE KOLMOGOROV-SMIRNOFF TEST. Journal of Applied Quantitative Methods, 6(3), 1-17. https://europub.co.uk/articles/-A-162123