The Mann-Whitney test is a non-parametric rank test to assess "whether one of two samples of independent observations tends to have larger values than the other" [Wikipedia].

learn more… | top users | synonyms

0
votes
0answers
21 views

Comparing Likert-scale data to a uniform distrithbution — what size uniform distribution should I use?

Disclaimer: I'm not an expert in statistics, so if I've got something very wrong somewhere please point it out kindly :) I just ran a study and got some 5-point Likert item responses. The study ...
0
votes
0answers
18 views

How to approach a between-subject comparison where only within-subject comparison is valid?

This is a rather odd situation, I'm guessing. I am interested in investigating a between-subjects factor and a within-subjects factor. However, the variable of interest is not one that can be validly ...
2
votes
1answer
46 views

Normality, and when to use t-test vs. Mann-Whitney U-test?

I am looking for a few rules of thumb of when to determine that my data is 'normal enough' to use a t-test vs. a Mann-Whitney U-test. From what I have read, most real world data sets are non-normal, ...
0
votes
0answers
49 views

Choosing right test to compare two populations

I have two populations whose size is 36 and whose values I want to compare. Example ...
0
votes
0answers
64 views

Kruskal Wallis: Effect size

I analyse 4 algorithms and 3 sets of metrics for each algorithm in which I apply the non-parametric Kruskal-Wallis test for each metric to detect any differences in performance between these ...
0
votes
0answers
13 views

Correlations and follow up tests

I am employing non parametric statistics because my research questions are exploratory. I have a mixture of dichotomous variables (age, gender), continous (height, weight), categorical (autism: ...
3
votes
0answers
30 views

Manually computed Mann–Whitney U-test differs from R's output

I found a sketchy lecture notes about Mann–Whitney U-test. There where were given data X: 30 32 33 33 36 37 40 44 Y: 27 29 31 34 34 35 41 It was computed that ...
0
votes
0answers
21 views

Comparison of observations in subgroups?

I have two groups, group A and group B. Each group is composed of subgroups, say A1, ..., An and B1, ..., Bm. Within each subgroup we have a different number of observations, say A1 would contain ...
0
votes
0answers
20 views

Comparing two groups of ordinal survey data?

I am trying to compare two (theoretical) independent groups of surveys with a 5 point ordinal scale (1 - greatly disagree, 5 - greatly agree). Both group A and group B received the same 10 questions ...
2
votes
1answer
80 views

How can a paired test less powerful than unpaired test?

I'm using wilcox.test to compare two timepoints as such: a <- c(1,2,3,4,5) b <- c(2,3,4,5,6) wilcox.test(a, b) The ...
2
votes
0answers
65 views

Reporting Mann Whitney test rejecting the null hypothesis, but samples have equal medians

I'm using the Mann Whitney test to verify if two population samples are equal. If the p-value is less than alpha (in this case, 0.05) I reject the null hypothesis and use the median of each population ...
0
votes
0answers
38 views

Comparing means between two groups if dependent variable is a percentage

I have data on recovery rates from several hospitals across the country. The recovery rates are in percentages. I want to compare the mean recovery rate between two groups of hospitals, one that uses ...
2
votes
1answer
28 views

What test to use to compare these two populations

I have two sets of data. The first one contains the proportion of farmers that own land in 22 different towns. The other contains the proportion of craftsmen that own land in the same 22 towns. I ...
3
votes
2answers
113 views

Mann-Whitney U test and paired data

I've read that working with paired data requires other method than Mann-Whitney $U$ test. I am not sure about how formally accurate is this statement. Reasons: Suppose that there is a set of $n$ ...
1
vote
1answer
66 views

Testing for mean statistical difference in segments of different length in the same Time Series

I have a Time Series of 336 monthly observations, from January 1987 to December 2014. I'd like to test for differences in uneven (of different size) segments of this time series. In effect, it would ...
1
vote
1answer
59 views

3 values ordinal variable: Mann-Whitney or Chi-squared?

I have an ordinal variable which assumes only 3 values. I need to do a comparison between 2 treatments. I used Mann-Whitney test, since is an ordinal. My "p-value" is quite high (0.9388) which is ...
5
votes
2answers
89 views

Reporting Results of Mann-Whitney U Test - Means vs Medians

I had a question yesterday that I got a bunch of great responses on. I have, hopefully, a quicker question here. There is a debate in the literature regarding reporting means vs medians in a ...
8
votes
1answer
368 views

Displaying Ordinal Data - Means, Medians, and Mean Ranks

Thanks in advance for any help. I have some ordinal data that is not normally distributed, so I decided to do non-parametric testing using the Mann-Whitney U Test. I am looking at differences ...
2
votes
0answers
57 views

Hypothesis testing with non-iid observations

I have a dataset with observations which violate the independent and identically distributed (iid) assumption. The dataset is composed by a number of post-click conversion events (purchases on a ...
2
votes
1answer
43 views

Finding the P Value using the Mann Whitney Test

The problem is given below Along with the picture of the ranks ![enter image description here][2] I let the first sample be $X$ and the sum of the ranks which I let $W$ be is 44. Also $n_1=6$ ...
2
votes
1answer
106 views

Mann Whitney test, unequal sample sizes, different shaped distributions

I was hoping someone could help, I am comparing proportional data in to two different groups. One group has a sample size of 22 and the other 530. The data are not normally distributed and have ...
0
votes
0answers
38 views

Mann Whitney or t test?

I have 4 questions which ask different branches of the same topic (I suppose they are related to each other). Different numbers of people responded to each question. They responded to each question by ...
3
votes
2answers
192 views

Mann-Whitney U test with unequal group sizes and one group very small

I have a sample of 24 participants who gave their responses to 8 questions. I calculated their mean response. Can I use Mann Whitney to compare between 2 groups where one of them has only 2 ...
1
vote
0answers
26 views

Is it okay to convert binary data to percentage data?

I have a within-groups study with 4 groups (400+ users). Each user answered 10 questions for each group. The answers were scored as right/wrong (1/0). Can the percentage correct for each user/group be ...
0
votes
1answer
17 views

How to combine clinical variables?

I am dealing with several clinically used variables that are not linked to each others. Those variables are correlated to worsened prognosis (some are numeral and asymmetric, therefore correlations ...
2
votes
1answer
91 views

Mann-Whitney U test when only summary data (mean, sd, sample size) are available

When raw data is not available, which normally occurs when we obtain our data from different scientific papers, how is it possible to perform a Mann-Whitney analysis to test whether two samples are ...
0
votes
0answers
11 views

Dealing with gender bias in Clinical Field Study - non parametric data

I have 105 patients to compare to 191 non-patients, across numerous non-parametric variables. However, my key confound is gender: 60% male in the patient group and 35% male in the non-patient ...
3
votes
1answer
445 views

Kolmogorov-Smirnov vs Mann-Whitney U When There Are Ties

I have a dataset consisting of rank data, some 100 cases and 2 groups. (The 2 groups contain about 1/3 and 2/3 of the cases.) I would like to test whether the two groups differ with respect to median ...
1
vote
1answer
22 views

Mean comparison of two categorical variables

I'd like to compare people's perception of safety at a certain location [which is a categorical variable on a scale of 1-10, with 1=feel very unsafe & 10=feel very safe] before and after being ...
0
votes
1answer
79 views

multiple pair wise nonparametric comparisons

is it possible to perform multiple pair wise nonparametric comparisons (generally using a Mann–Whitney test) and adjust the significance level used for the decision criteria using a Bonferroni-type ...
2
votes
0answers
53 views

Am I using Paired Statistical Test Correctly?

I am comparing a feature between correct & incorrect trials. There are N=1194 paired samples $\{x_i,y_i| i=1,2,...N\}$, where x is for correct trials and y is incorrect trials. I am using a ...
2
votes
1answer
151 views

Does the Mann-Whitney U-test require the groups to have the same distribution?

If one of my data sets is normally distributed and the other is not, can I do a Mann-Whitney U-test on them, or would they both have to be non-normal?
2
votes
1answer
184 views

How do I interpret the p value returned in scipy's Mann Whitney U test?

I have a program in which I need to perform an action based on what results of a Mann Whitney U test are. I know the criteria that need to be met, but I would still like to understand what the results ...
2
votes
2answers
1k views

Mann-Whitney U-test: confidence interval for effect size

According to Fritz, Morris, and Richler (2011; see below), $r$ can be calculated as an effect size for the Mann-Whitney U-test using the formula $$ r = \frac{z}{\sqrt N} $$ This is convenient to me, ...
1
vote
1answer
56 views

Using nonparametric tests with small samples even when data are normaly distrubuted

Is it appropriate to use a nonparametric test with a small sample (e.g., less than 65 people) even when data are normally distributed? For example, using the Spearman correlation? Actually my data is ...
1
vote
0answers
51 views

Hypothesis testing on groups of time series data

I have some experimental data from two groups, where each group contains data from $n$ subjects. The data are in the form of a time series for each subject, but are not all the same length. To be ...
3
votes
1answer
84 views

Why are there two forms for the Mann-Whitney U test statistic?

I have encountered two forms for calculating the two-sample Mann-Whitney U test statistic, which are: $$U_1 = R_1 - \frac{n_1(n_1 + 1)}{2}$$ and $$U_1 = n_1n_2 + \frac{n_1(n_1+1)}{2} - R_1$$ where ...
1
vote
1answer
222 views

Significant p value for Mann-Whitney U test but low AUC

How is it possible that for two sample sets I'm getting a low p-value, but also a low AUC value (just below 0.5)? To compute the P-value I'm looking at the second outputted value of the function here ...
24
votes
6answers
2k views

How to choose between t-test or non-parametric test e.g. Wilcoxon in small samples

Certain hypotheses can be tested using Student's t-test (maybe using Welch's correction for unequal variances in the two-sample case), or by a non-parametric test like the Wilcoxon paired signed rank ...
2
votes
1answer
88 views

power to detect effect sizes for the usual t, Welch Adjusted t, and Mann-Whitney U test

For class, I am given a series of sample sizes and variances for two groups and am asked to calculate the power for detecting effect sizes for the usual t test, Welch adjusted T test, and the ...
1
vote
1answer
120 views

Best way to compare pre vs post levels in treatment vs control groups?

In a study, drug was given to tt (treatment) group and not to cc (control) group and blood levels of (say) cholesterol were tested before and after in each subject. I have following data: ...
0
votes
2answers
84 views

How to apply Mann-Whitney test Control vs Treatment Group

I have a treatment and a control group: both have pre- and post- values (I tested reading speed). I need to know if there are any significant differences between the groups (or if the treatment group ...
1
vote
1answer
42 views

If I am comparing actual data vs. forecasted data, is the Durbin-Watson statistic useful?

We are comparing our forecast vs actual data from the same time period and was using the mann-whitney test to help provide evidence our samples were not different. Someone challenged us saying the ...
0
votes
1answer
577 views

Problem with Mann-Whitney U test in scipy

I am trying to perform Mann-Whitney test on a real data set using scipy. I extracted an example where the problem occurs. It seems that the function tiecorrect returns negative value which is the ...
1
vote
2answers
132 views

Mann-Whitney/Wilcoxon rank sum test in R with a table of tallies

I have a 10 treatments, 5 samples per treatment, and the result of each treatment is ranked on a ordinal scale: Poor, Fair, Moderate, Good, Excellent. I have the data tallied up so I have the total ...
0
votes
0answers
209 views

Mann-Whitney U-test in R

I'm doing a Mann Whitney U test in R but it won't run the code: downstream<-subset(mydata,Direction=="D") Wilcox.test(Date, Species, data="downstream") ...
0
votes
1answer
39 views

How to show whether the average coefficients of determination from one regression technique are better than another across many objects?

I have 50,000 objects on which I have performed two different types of regression. Using cross validation, I obtained the average $R^2$ score from each model on each of the objects. So now I have a ...
2
votes
1answer
38 views

wilcox.test usage in R

I would like to know if there is a difference in the values taken from measurements of a given characteristic sampled at primary forest (Point=1) and secondary ...
3
votes
2answers
402 views

Mann Whitney test with unequal variances [duplicate]

I am confused on what I have read about the Mann whitney test. We are testing whether our actual data is the same as our projected data. We had been using the t-test until we realized the data might ...
3
votes
1answer
461 views

Non-parametric version of paired t-test (Mann–Whitney U test)

I have data from 100 individuals doing a 2AFC under a control and a manipulated setting. I want to compare the means. I initially used a paired t-test. My supervisor noticed the distributions were not ...