Mann whitney test, Advanced Statistics

Mann Whitney test is a distribution free test which is used as an alternative to the Student's t-test for assessing that whether the two populations have the same median. The test statistic U is calculated from comparing each pair of the values, that is one from each group, scoring these pairs 1 or 0 depending upon whether the first group observation is higher or lower than the from the second group and summing the resulting scores over all the pairs. In the case of no ties then the following g case could be seen
869_Mann Whitney test.png 

here n is the number of observations in the smaller group and W is the rank sum statistic associated with the Wilcoxon's rank sum test. The two tests are hence equivalent. Tables giving critical values of test statistic are available, and for the moderate and large sample sizes, a normal approximation can be taken in use.

Posted Date: 7/30/2012 2:56:17 AM | Location : United States







Related Discussions:- Mann whitney test, Assignment Help, Ask Question on Mann whitney test, Get Answer, Expert's Help, Mann whitney test Discussions

Write discussion on Mann whitney test
Your posts are moderated
Related Questions

The term used when the aggregated data (for instance, aggregated over different areas) are analysed and the results supposed to apply to the relationships at the individual level.

Lattice distribution : A class of probability distributions to which most of the distributions for discrete random variables used in statistics belongs. In such type of distributio

Tracking is the term sometimes used in the discussions of data from the longitudinal study, to describe the ability to predict the subsequent observations from previous values. In

Regression line drawn as y= c+ 1075x ,when x was2, and y was 239,given that y intercept was 11. Calculate the residual ?


A standard IQ test has a mean of 98 and a standard deviation of 16. We want to be 99% certain that we are within 8 IQ points of the true mean. Determine the sample size

Nuisance parameter : The parameter of the model in which there is no scienti?c interest but whose values are generally required (but in usual are unknown) to make inferences about

A test for equality of the variances of the two populations having normal distributions, based on the ratio of the variances of the sample of observations taken from each. Most fre

Marginal matching is the matching of the treatment groups in terms of means or other summary characteristics of matching variables. This has been shown to be almost as efficient a