Identify factor settings that produce the least variability in a 2-level factorial design

Analyze Variability identifies factor settings that produce less variable results in 2-level factorial designs with repeat or replicate measurements. Minitab calculates and stores the standard deviations of your responses and analyzes them to detect differences, or dispersion effects, across factor settings.

For example, a publishing company wants to determine the printing press (1 or 2) and line speed (A or B) that results in the highest print quality. Using Analyze Variability, they determine that one setting combination (press 1 and line speed B) results in excessive variation to the point that a large number of pages are unreadable. When analyzing the means using Analyze Factorial Design, they can determine the settings that produce both the best average and most consistent response.

You can use the results of Analyze Variability as weights when you analyze the mean responses in Analyze Factorial Design. If the variances are not constant, observations with large variances are given relatively small weight and observations with small variances are given relatively large weight.