Suppose I have this model
$$Y=B_0+B_1X_1+B_2X_2$$
and these observations
Y <- c(64, 73, 61, 76, 72, 80, 71, 83, 83, 89, 86, 93, 88, 95, 94, 100)
X1 <- c(4, 4, 4, 4, 6, 6, 6, 6, 8, 8, 8, 8, 10, 10, 10, 10)
X2 <- c(2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4, 2, 4)
I know how to calculate SSLF (1) and SSPE (2) in R, but I want to know how to do it at hand
$$SSLF=SSE-SSPE$$
where
$$SSE=\sum(Y_i-\hat{Y_i})^2$$
setting up the table this way is easy to calculate the sum of squares of pure error, but there is an easier way to do this?
(1) SSLF: sum of squares of lack of fit
(2) SSPE: sum of squares of pure error
Best Answer
Let me give you a hint. The SSPE is made up of squared deviations from the means at each $X$ level. Let's denote the number of $X$ levels by $c$, then
$$SSPE=\sum_j^c \sum_{i}^{n_j} \left(Y_{ij} - \bar{Y_j} \right)^2$$.
Simply put, for a replicate, i.e. an identical $X$ value, you compute the mean of the the corresponding $Y$s and sum the squared deviations from it. It is easy to see that any $X$ level with no replications makes no contribution to SSPE because the mean is just that one observation!
Hope this clears it up a bit.