Exam 24: Selecting a Procedure for Analyzing Data

Type II error involves failure to detect a difference that actually exists.

Type I error involves detecting a difference between phases that doesn't actually exist.

Because all statistics for single-system designs are focused on small numbers, we don't have to worry about size of the sample (number of observations) for accurate use of these statistics.

When you have difficulty determining the characteristics of the data, it is safest to select one statistic and stick with it.