#### Notes on the ANOVA formulas

1. In computing the *SSE,* if we summed only the squares for
a fixed *g* and divided by
*n*_{g}, we would have the variance, i.e., the square of the
*SD,* of the sample from group *g*. So we can begin to see where
the term "analysis of variance" comes from. Also, it follows from what
we have just said that, if we have already computed the variances, or
the *SD*s, of the samples, then we could use them to compute the
*SSE*: If *Var*_{g} and *SD*_{g} denote
the variance and standard deviation of the sample from group *g*,
then the *SSE* is the sum of the products
*n*_{g}(Var_{g})
= *n*_{g}(SD_{g}^{2})

2. Provided that we interpret
*n*_{g}(AV_{g}-AV)^{2}
as the sum of *n*_{g} copies of
*(AV*_{g}-AV)^{2}, there are the same total
number of terms in finding *SSE* and *SSG*, namely the
total number of data points *N*.