From the course: Learning Minitab (version Minitab 17)

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Compare medians with nonparametric tests

Compare medians with nonparametric tests - Minitab Tutorial

From the course: Learning Minitab (version Minitab 17)

Start my 1-month free trial

Compare medians with nonparametric tests

“

- [Voiceover] In this movie I will show you how to compare medians using nonparametric tests. Open exercise file 04-05. Here we have three data sets. These could be processing times of three offices, A, B, and C. Let's say I want to compare the median of A to a target value, 70. To do that I can run a one sample Wilcoxon test. Go up to Stat, Nonparametrics, One Sample Wilcoxon, select A, and my testing is a median target of 70 in our example, whether it's equal to or not equal to, that's our hypothesis. Okay, and here we have the prinout from the Wilcoxon test with a P value of 0.654, which is great that it's 0.05, therefore we failed to reject the null hypothesis. So we can see that a test median and a median of A are equal. What if I want to compare two offices, A versus C. Are they equal or not? To compare these two medians, I can run a Mann-Whitney test. Go up to Stat, Nonparametrics, Mann-Whitney. The first sample is A, second sample is C, and all for 0.05 or 95% confidence…

Contents