Dunnett's method compares the mean of each level with the mean of a control level. The control level is usually a standard against which you want to compare all other levels.

This method uses a family error rate (often called familywise error rate) to control the rate of type I error. The family error rate is the probability of making one or more type I errors for the entire set of comparisons. Dunnett's method adjusts the error rate for individual comparisons (individual error rate), based on the family error rate you choose.

Use the confidence intervals to determine likely ranges for the differences and to assess the practical significance of the differences.

·    If an interval does not contain zero, there is a statistically significant difference between the corresponding means.

·    If the interval does contain zero, the difference between the means is not statistically significant.

To display the values of the confidence limits in the Session window, check Tests in Stat > ANOVA > One-Way > Comparisons.

For the paint hardness data, the confidence intervals display the likely ranges for all the mean differences:

·    The confidence interval for the difference between the means of the control level (Blend 1) and Blend 2 extends from -11.9604 to -0.372888. This range does not include zero, which indicates that the difference between these means is significant.

·    The confidence intervals for the remaining pairs of means all include zero, which indicates that the differences are not significant.