Fit statistics are reported along with factor loadings and error variances.

Other variances related to the test are treated as error variances.

Summing in this fashion has the effect of further randomizing the error variance.

Also, error variance must be a monotonic function of the specified explanatory variable.

Unless informative prior information about expression levels or error variance is used, the following (minimal) requirements must be met.

They contribute to estimation of the error variance of genes.

One author wrote, "unequal error variance is worth correcting only when the problem is severe."

Linear regression assumes homoscedasticity, that the error variance is the same for all values of the criterion.

Let denote the unbiased form of approximating the error variance.

The error variances should be equal for different treatment classes.