Mann-Whitney U Test

Research Question: Is there be statistically significant differences on by ?

Ho: There will be no statistically significant differences on by .

Ha: There will be statistically significant differences on by .

To examine this research question, a Mann-Whitney U test will be conducted on by .

The Mann-Whitney U test is the nonparametric equivalent to the independent t-test and the appropriate analysis to compare differences that come from the same population when the dependent variable is ordinal (Leech, Barrett & Morgan, 2005).  The Mann-Whitney U test compares the number of times a score from one sample is ranked higher than a score from another sample.  The scores from both samples will be ranked together; rank 1 is used for the lowest score, rank 2 for the next lowest score, and so on. When scores have the same value, a tie is determined.  The scores are ranked and those ranks are added together and then divided by the number of scores. Each of the tied scores is then assigned the same ranking (Cramer, 1998).  Once the data is ranked, calculations will be carried out on the ranks.  Given the nonparametric nature of this statistical analysis, there are fewer assumptions to assess.  The data must come from random samples of the population,  the data are independent, meaning that scores from one participant are not dependent on scores of the others,  and the measure of the two samples have at least an ordinal scale of measurement (Brace, Kemp & Sneglar, 2006).

Additional Resources

Watch the video

Take the course