Dear all,

Thank you for providing me with the assumptions of the Mann-Whitney U test. Yet, the responses I got were contradictory; one of you said that distributions do not matter, while the other one said they do...

Let me give you the design I want to apply it to:

It contains two groups with large, yet unequal, sample sizes; group one: 297, group two: 165. Variances are unequal, but the distributions (when looking at them with the bare eye) are roughly equal.

Do you think I can safely apply it here? In order to make the testing more accurate, I opted for the Monte Carlo approach of the MW test; with 10.000 times resampling. I hope you agree with me that this is a solid way of testing the differences between these independent samples.

Thanks in advance,

Marco

--- kornbrot <d.e.kornbrot@herts.ac.uk> wrote:

> be very careful > > it is a requirement of Mann-Whitney that both > populations have SAME > distribution > i will send you reference later > > this implies that MW is ok for unbounded measures > like reaction time or > income that tend to have similar skew and variance > for both > populations. that's waht it was designed for > if skew is different in 2 populations MW is flawed - > particulalry if > skews are in opposite direction > > MW is fatally flawed for ANY scale that has a small > discrete number of > possible responses, like Likert scales or number of > positive or > correct responses form small set. this is because > high means have > negtaive skews and low means positive skews. it is > also not v. good if > variances are different > > don't shoot the messenger > > diana > On 30 Jun 2005, at 12:21, Marco van de Ven wrote: > > > Hello everyone, > > > > I have a question concerning the Mann-Whitney > U-Test > > for two independent samples... > > > > Does anyone know what the assumptions are for this > > test?I looked on the internet, but found > contradictory > > information. Please add source if you can. > > > > Thanks in advance, > > > > Marco > > > > > > > > > ___________________________________________________________ > > How much free photo storage do you get? Store your > holiday > > snaps for FREE with Yahoo! Photos > http://uk.photos.yahoo.com > > > > > Professor Diana Kornbrot > Head of Health & Human Sciences Research Institute > University of Hertfordshire > College Lane, Hatfield, Hertfordshire AL10 9AB, UK > voice: +44 (0) 170 728 4626 > fax: +44 (0) 170 728 5073 > email: d.e.kornbrot@herts.ac.uk > http://www.psy.herts.ac.uk/pub/D.E.Kornbrot/hmpage.html >

___________________________________________________________ Yahoo! Messenger - NEW crystal clear PC to PC calling worldwide with voicemail http://uk.messenger.yahoo.com