One-Way ANOVA

Graphs - Fisher CIs for Differences of Means

  

Fisher's LSD method compares the means for each pair of factor levels using the individual error rate you select. Note that the family error rate, which is the probability of making one or more type I errors for the entire set of comparisons, will be higher than the error rate for each individual comparison.

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.

Example Output

Interpretation

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 Blend 1 and Blend 2 extends from -10.9239 to -1.40942. This range does not include zero, which indicates that the difference between these means is significant.

·    Similarly, the intervals for the differences between Blend 2 and Blend 4 (4.743 to 14.257) and Blend 3 and Blend 4 (0.326 to 9.841) do not include zero, which indicates that these differences are significant as well.

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