A Mann-Whitney U-Test compares the means between two unrelated groups, such as comparing the difference in heights between Cats and Yorkshire Terriers.
It is considered a non-parametric test and therefore is suitable for non-parametric data. To check if your data is parametric, please check our dedicated guide: Parametric or Not Guide (PDF)
If your data is parametric you should consider using an Independent-Samples t-Test
The process of carrying out a Mann-Whitney U test on Jamovi is very similar to that of an Independent t-test. This is because it can be considered as the non-parametric alternative.
1. Identify the two columns of data you are to use. One for the independent (or grouping) variable, and another for the dependent (or test) variable.
2. Select the "T-Tests" option, drop down the menu and select "Independent Samples T-Test":
3. The Independent Samples T-Tests options will open. Using the arrow button, move the dependent variable across to the "Dependent Variables" box and the independent variable into the "Grouping Variable" box. You will want to unselect "Student's" and select "Mann-Whitney U" instead.
Look though the options on this view for additional information you may want, here we have selected the addition of "Descriptives" to get the median information for the write up. Your results will appear to the right of the options box, and will update as you tick or untick options.
Jamovi produces the results as you add variables and tick options. If you have results that you don't need or find you have not selected all that you want, you can come back to the menu at any point to change your selection. For this Mann-Whitney U test, the results are given in two tables; an "Independent Samples T-Test" table and a "Group Descriptives" table, these are produced in APA style formatting.
These results may not give you all the results you would like for your write up. It is common for Mann-Whitney U results to be reported alongside the Interquartile Range (IQR) or quartiles. These can be produced in Jamovi under the "Exploration" tab, in the "Descriptives" menu.
This table shows a selection of descriptive statistics: the sample size of each group (N), the mean of each group (Mean), the median of each group (Median), the standard deviation of each group (SD) and the standard error (SE). Typically the N and Medians are reported from this table.
This table shows the specific test results including the Mann-Whitney U statistic (Statistic) and the p-value (p).
(Here we recommend caution to ensure this is reported as a Mann-Whitney U and not as a t-Test).
Here is an example of how this could be reported, with the statistics in APA format:
Heights of Cats and Yorkshire Terriers were compared. On average the Yorkshire Terriers (Mdn = 30.00) were taller than the Cats (Mdn = 28.00) however a Mann-Whitney U test indicated that this difference was not statistically significant, U (NCats=11, NTerriers=11) = 35.5, p = .101.