From the course: Six Sigma: Black Belt
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Test for normality - Minitab Tutorial
From the course: Six Sigma: Black Belt
Test for normality
- Let's say you want to conduct hypothesis testing to prove differences in the population means or variances between groups or against a target value. That output could be dimensions, processing times or any characteristic that's continuous data. Many statistical tests require that continuous data follow a normal distribution, commonly known as the bell-shaped curve. But not all continuous data are normally distributed. Testing for normality is essential, because some tests require normal data. Otherwise they will fail to work, and give you the wrong conclusions. In another video, we look at a hypothesis testing road map to show the correct test to use. Let's look at the top left quadrant of that matrix. For example, when comparing means, the one sample t-test, the two sample t-test, and ANOVA or analysis of variance all assume the use of normal data. When comparing variances, Bartlett's test for equal variances also assumes normal data. If data is non-normal, then nonparametric tests…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.