Nested-model F-test
= Nested-model F-test
For nested <normal linear model>[Gaussian linear models] with a common unknown positive error <variance>, full-model rank $p_1<n$, and rank difference $r>0$, the statistic
$$
\frac{(RSS_0-RSS_1)/r}{RSS_1/(n-p_1)}
$$
has an $F_{r,n-p_1}$ <probability distribution>[distribution] under the reduced model.