From the course: Six Sigma: Black Belt

Unlock the full course today

Join today to access over 23,500 courses taught by industry experts.

Nonparametric tests

Nonparametric tests - Minitab Tutorial

From the course: Six Sigma: Black Belt

Start my 1-month free trial Buy for my team

Nonparametric tests

“

- What happens if you want to test theories on differences in means using t-tests and ANOVA, but the data is non-normal? Well, those tests cannot be used. So, what can you do? Fortunately, there's an alternative. You can compare medians instead of means using nonparametric methods. They can also be used if you want to compare medians because you're dealing with duration data like processing times. Let's go over some of the options for nonparametric methods. First, there's the one-sample Wilcoxon test, which can be used to compare the population median to a target. There's also the Mann-Whitney test, which can be used to compare two population medians of two groups. And there's the Kruskal-Wallis test that can be used to compare population medians of multiple groups. Let's apply these nonparametric methods using Minitab. To get started download from the exercise files MediansData.MTW and open the file. Here we have…

Contents