Sri Ramachandra Institute of Higher Education and Research
Question
Asked 8 March 2014
How can I calculate the effect sizes of small samples (<20) for non-parametric tests Wilcoxon and Mann-Whitney U?
I want to calculate the effect sizes of Wilcoxon and Mann-Whitney tests. Can I use the formula r=Z/sqrt(N) when the samples are smaller than 20 (where N is all the observations) ?
Most recent answer
very useful thread,thanks to all who shared their ideas here
Popular answers (1)
Royal College of Surgeons in Ireland
To add to Jochen's reply, effect size is indeed defined for the Wilcoxon Mann-Whitney test. The underlying test statistic, U, can easily be rescaled to give the probability that an observation from one group will be higher than an observation from the other. This measure of effect size is variously known as the common language effect size, the area under the ROC curve, Harrel's c (though C is a special case) etc.
But it is a very useful measure of effect size indeed - in a clinical trial, for example, it corresponds to the probability that a person on the new treatment will do better than a person on the comparison treatment.
To calculate it, simply divide U by its maximum value, which is the product of the Ns for the two groups
I've a little paper on this, which is no longer behind a paywall, but will pretty soon go free. http://www.stata-journal.com/article.html?article=st0253
11 Recommendations
All Answers (19)
Justus-Liebig-Universität Gießen
"effect size" is not defined when you abandon the data and use the ranks. If you need this for detemining the sample size required to achieve a power for the test (of a location shift), then you can use bootstap methods (there cannnot be a general solution since there is no general distributional model that could be used!). Thus you have to have pilot data for the distribution under H0.
Possibly read:
Biometrics. 1988 Sep;44(3):847-60.
Estimating the power of the two-sample Wilcoxon test for location shift.
Collings BJ1, Hamilton MA.
8 Recommendations
You may calculate effect size via r = z/√N (r: effect size; z: z value; N: Observation number). You should divide z value to square root of observation number for getting effect size. You can find z value on the output case -at the end of the Wilcoxon and Mann-Whitney tests-.
2 Recommendations
Royal College of Surgeons in Ireland
To add to Jochen's reply, effect size is indeed defined for the Wilcoxon Mann-Whitney test. The underlying test statistic, U, can easily be rescaled to give the probability that an observation from one group will be higher than an observation from the other. This measure of effect size is variously known as the common language effect size, the area under the ROC curve, Harrel's c (though C is a special case) etc.
But it is a very useful measure of effect size indeed - in a clinical trial, for example, it corresponds to the probability that a person on the new treatment will do better than a person on the comparison treatment.
To calculate it, simply divide U by its maximum value, which is the product of the Ns for the two groups
I've a little paper on this, which is no longer behind a paywall, but will pretty soon go free. http://www.stata-journal.com/article.html?article=st0253
11 Recommendations
Lakehead University Thunder Bay Campus
Although I've not read them yet, I see that Robert Newcombe's book on confidence intervals for proportions & related measures (http://www.crcpress.com/product/isbn/9781439812785) has a chapter called "Generalised Mann-Whitney Measure" and another called "Generalised Wilcoxon Measure" (chapters 15 & 16 respectively). The original poster may find chapter 15 useful.
1 Recommendation
Justus-Liebig-Universität Gießen
Thank you! It is an entirely different kind of "effect". Mathematically this is perfectly fine (I think), I am only a little itchy about the fact that probabilities itself are used as effect-size measure (this is related to the meaning of probability, what is not so clear, though).
Republic Polytechnic
May I know the meaning of the "negative sign" of the effect size? e.g. r = -0.57
Justus-Liebig-Universität Gießen
it means that the expected value for the response decreases for higher vaues of the predictor.
Republic Polytechnic
e.g.
I'm comparing between two independent groups (control and Treatment), the treatment has higher mean ranks compared to control group. Can I say a significant effect of Group (The mean ranks of control and treatment group were 5.2 and 9.3, respectively)", p < 0.05, r= -.57. There is a medium effect observed of the intervention on treatment group.
The Ohio State University
r=Z/sq.root of N abs(r) works fine. Note Small=.1 moderate=.3 large=.5
4 Recommendations
George Washington University
I realize this thread is a little dated but so glad I stumbled upon it. Many thanks Dr. Conroy, the article is really helpful.
1 Recommendation
University of Mohaghegh Ardabili
According to Fritz, Morris, and Richler (2011) we can calculate effect size for the Mann-Whitney U-test using the the mentioned formula. The following website is realy helpful:
Hogeschool Fontys
can anyone tell me iof the effect size in the calculation of the Wilcoxcon Signed Rank Test can be a negative outcome?
i've got (-2,005/ sqare of 146) and the outcome is -0.17)
how do I report this APA?
thnx!
Azarbaijan Shahid Madani University
use the G power analysis ,tests, independent two groups (Mann‐Whitney test), the Determine Effect size section Or the following formula that has similar results:
Mean difference between the two groups (M2-M1) / mean standard deviation
Royal College of Surgeons in Ireland
Azam Zarneshan The effect sizes in G*Power depend on the data following a known distribution. They are based on Cohen's d, which measures effect based on the difference between means. However, the Wilcoxon Mann-Whitney test does not test a difference between means (or medians), so the effect size is inappropriate to the test.
4 Recommendations
Similar questions and discussions
Related Publications
El trabajo está enfocado en el análisis de los datos realizados por el laboratorio de la Empresa Nicaragüense de Acueductos y Alcantarillados en el período 1993 – 2002. Se demuestra que los registros de análisis hidroquímicos de los pozos perforados de Managua, tienen calidad para establecer mejores criterios de decisión que apoyen los planes de mo...
Physical education teaching achievement is a direct reflection of the sporting quality of teaching is good or bad, and the statistical analysis of the results of the Physical Education is an important part of the process of physical education, teachers can draw through statistical analysis of the results, the effect of their teaching and student le...
Los actuales paquetes estadísticos que son empleados en la formación profesional e investigativa de los estudiantes (Statwin y SPSS) han sido diseñados de acuerdo a determinados intereses en el orden científico, de ahí que en ciertas circunstancias comprometa su fácil empleo para algunos propósitos educativos. El presente trabajo responde a un dise...