How to obtain one-sided (1-sided) p-value from Mann-Whitney U test and t-test in Statistica?
Article ID: KB0074231
Updated On:
| Products | Versions |
|---|---|
| Spotfire Statistica | 13.0 and higher |
Description
Statistica produces 2-sided p-value for both Mann-Whitney U test and t-test. How to obtain one-sided (1-sided) p-value from them?
Issue/Introduction
How to obtain one-sided (1-sided) p-value from Mann-Whitney U test and t-test in Statistica?
Environment
Windows
Resolution
1. For t-test, Statistica produces 2-tailed p-values. Since t-distribution (normal distribution) is symmetric, for example, symmetric about zero if comparing the means of two independent groups, thus the two-tailed p-value is twice the one-tailed p-value for alternative hypothesis (e.g. Means difference <0 or Means difference >0). So one can simply take the 2-sided p-value from t-test result table and divide it by 2 to obtain the one-sided p-value.
Below is example of 2-independent sample t-test result table in Statistica.
2. For Mann-Whitney u test result table, it shows the 2-sided p-value and there is also a column named "2*1sided exact p". One can take that "2*1sided exact p" and divide it by 2 to get the 1-sided p-value for the test.
Feedback
Yes
No
Powered by
