Use the table of individual statistics to assess the following properties of your data:

·    N. The number of observations included for each level of the factor.

·    Mean. The mean of the observations for each level. These sample means provide an estimate of the population means for each level.

·    StDev. The sample standard deviation for each level. The traditional analysis of variance procedure assumes that the population standard deviations for all levels are equal. You can test the data for equality of variances with the Test for Equal Variances.

      If the standard deviations are not equal, uncheck  Assume equal variances in the One-Way ANOVA Options dialog. For unequal variances, Minitab performs Welch's ANOVA.

·    CI. These confidence intervals (CI) provide a range of values that is likely to contain the true mean of each population. The confidence intervals are calculated using the pooled standard deviation if you assume equal variances. If you do not assume equal variances, each interval is calculated using the group's standard deviation.

·    Pooled StDev. The pooled standard deviation is an estimate of the common standard deviation for all levels. Minitab displays this statistic only if you assume equal variances.

The results of the paint hardness analysis indicate that:

·    Blend 2 has the lowest mean hardness (8.57) and Blend 4 has the highest (18.07).

·    The interval tells you that based on the sample data, you can be 95% confident that the mean hardness for Blend 2 is greater than or equal to 5.20 and less than or equal to 11.93.

·    The standard deviations for the different blends appear to be equal. If you perform the Test for Equal Variances on these data, it produces high p-values, which suggests that the standard deviations are not different.

The pooled standard deviation is 3.95012.