When we talk about error variance in the analysis of variance, we are talking about

In the Analysis of Variance (ANOVA), error variance refers to the variation in the data that cannot be accounted for by the model. It is the variability that is left unexplained after accounting for the variance explained by the predictors in the model.

Here are the steps to understand it:

1. In ANOVA, we are trying to understand if the means of different groups are significantly different from each other. For example, we might want to know if students from different schools perform differently in a national exam.

2. To do this, we compare the variance (or variability) within each group (the error variance) to the variance between the groups (the treatment variance).

3. The error variance is the variability within each group. It's the variation that we can't explain by our model. For example, even if students are from the same school, they will not all get the same score in the exam. This variation within the group is the error variance.

4. If the error variance is high, it means there's a lot of variability within the groups that we can't explain by our model. This makes it harder to detect a significant difference between the groups.

5. On the other hand, if the error variance is low, it means that most of the variability in the data can be explained by the differences between the groups. This makes it easier to detect a significant difference between the groups.

6. In summary, when we talk about error variance in ANOVA, we are talking about the unexplained variability within each group.