Abstract
Behavioral ecologists are often faced with a situation where they need to compare the central tendencies of two samples. The standard tools of the t test and Mann–Whitney U test (equivalent to the Wilcoxon rank-sum test) are unreliable when the variances of the groups are different. The problem is particularly severe when sample sizes are different between groups. The unequal-variance t test (Welch test) may not be suitable for nonnormal data. Here, we propose the use of Brunner and Munzel’s generalized Wilcoxon test followed by randomization to allow for small sample sizes. This tests whether the probability of an individual from one population being bigger than an individual from the other deviates from random expectation. This probability may sometimes be a more clear and informative measure of difference between the groups than a difference in more commonly used measures of central tendency (such as the mean). We provide a recipe for carrying out a statistical test of the null hypothesis that this probability is 50% and demonstrate the effectiveness of this technique for sample sizes typical in behavioral ecology. Although the test is not available in any commercial software package, it is relatively straightforward to implement for anyone with some programming ability. Furthermore, implementations in R and SAS are freely available on the internet.
Similar content being viewed by others
References
Bauer DF (1972) Constructing confidence sets using rank statistics. J Am Stat Assoc 67:687–690
Brunner E, Munzel U (2000) The nonparametric Behrens–Fisher problem: asymptotic theory and a small sample approximation. Biom J 42:17–25
Brunner E, Munzel U (2002) Nichtparametrische Datenanalyse. Springer, Berlin
Brunner E, Dette H, Munk A (1997) Box-type approximations in nonparametric factorial designs. J Am Stat Assoc 92:1494–1502
Büning H (1997) Robust analysis of variance. J Appl Stat 24:319–332
Chu PS, Wang J (1997) Tropical cyclone occurrences in the vicinity of Hawaii: are the differences between El Niño and non-El Niño years significant? J Climate 10:2683–2689
Cliff N (1996) Ordinal methods for behavioral data. Erlbaum, Mahway
Day RW, Quinn GP (1989) Comparison of treatments after an analysis of variance in ecology. Ecol Monogr 59:433–463
Delaney HD, Vargha A (2002) Comparing several robust tests of stochastic equality with ordinally scaled variables and small to moderate sized samples. Psychol Methods 7:485–503
Gould SJ (1996) Full house: the spread of excellence from Plato to Darwin. Harmony Books, New York
Huang Y, Xu H, Calian V, Hsu JC (2006) To permute or not to permute. Bioinformatics 22:2244–2248
Janssen A (1997) Studentized permutation tests for non-i.i.d. hypotheses and the generalized Behrens–Fisher problem. Stat Probab Lett 36:9–21
Julious SA (2005) Why do we use pooled variance analysis of variance. Pharm Stat 4:3–5
Kasuya E (2001) Mann–Whitney U test when variances are unequal. Anim Behav 61:1247–1249
Manly BFJ (2007) Randomization, bootstrap and Monte Carlo methods in biology, 3rd edn. Chapman & Hall, Boca Raton
Margolis LG, Esch W, Holmes JC, Kuris AM, Shad GA (1982) The use of ecological terms in parasitology (report of an ad hoc committee of the American Society of Parasitologists). J Parasitol 68:131–133
McArdle BH, Anderson MJ (2004) Variance heterogeneity, transformations, and models of species abundance: a cautionary tale. Can J Fish Aquat Sci 61:1294–1302
Milton RC (1970) Rank-order probabilities: two-sample normal shift alternatives. Wiley, New York
Munzel U, Hauschke D (2003) A nonparametric test for proving noninferiority in clinical trials with ordered categorical data. Pharm Stat 2:31–37
Neubert K, Brunner E (2007) A studentized permutation test for the non-parametric Behrens–Fisher problem. Comput Stat Data Analysis 51:5192–5204
Neuhäuser M (2002) Two-sample tests when variances are unequal. Anim Behav 63:823–825
Neuhäuser M, Lam FC (2004) Nonparametric approaches to detecting differentially expressed genes in replicated microarray experiments. In: Chen Y-PP (ed) Conferences in research and practice in information technology, vol 29. Australian Computer Society, Adelaide, Australia
Neuhäuser M, Poulin R (2004) Comparing parasite numbers between samples of hosts. J Parasitol 90:689–691
Neuhäuser M, Lösch C, Jöckel KH (2007) The Chen-Luo test in case of heteroscedasticity. Comput Stat Data Analysis 51:5055–5060
Reiczigel J, Zakarias I, Rózsa L (2005) A bootstrap test of stochastic equality of two populations. Am Stat 59:156–161
Rice WR, Gaines SD (1989) One-way analysis of variance with unequal variances. Proc Natl Acad Sci USA 86:8183–8184
Ruxton GD (2006) The unequal variance t-test is an underused alternative to Student’s t-test and the Mann–Whitney U test. Behav Ecol 17:688–690
Sawilowsky SS, Blair RC (1992) A more realistic look at the robustness and type II error properties of the t test to departures from population normality. Psychol Bull 111:352–360
Troendle JF (2002) A likelihood ratio test for the nonparametric Behrens–Fisher problem. Biom J 44:813–824
Troendle JF (2005) Letter to the editor. Am Stat 59:279
Wilcox RR (2003) Applying contemporary statistical techniques. Elsevier Academic, San Diego
Wilcox RR (2005) Introduction to robust estimation and hypothesis testing, 2nd edn. Elsevier Academic, San Diego
Wilson JB (2007) Priorities in statistics, the sensitive feet of elephants and don’t transform data. Folia Geobot 42:161–167
Zimmerman DW, Zumbo BN (1993) Rank transformations and the power of the Student t-test and Welch t-test for non-normal populations. Can J Exp Psychol 47:523–539
Acknowledgment
We thank two reviewers for very useful comments on a previous draft.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by L.Z. Garamszegi
Rights and permissions
About this article
Cite this article
Neuhäuser, M., Ruxton, G.D. Distribution-free two-sample comparisons in the case of heterogeneous variances. Behav Ecol Sociobiol 63, 617–623 (2009). https://doi.org/10.1007/s00265-008-0683-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00265-008-0683-4