As discussed in Chapter 7, data-driven variable selection and multiple testing to arrive at the final model alter the true significance levels; probability levels and confidence intervals should be used with caution The variable Na has the smallest partial sum of squares in the five-variable model, This means the variability in BIMASS after the contributions of the other four variables have been taken into account. As a result, Na is the logical variable to eliminate first. And, since the partial sum of squares for Na R( ) = 47, 011 is not significant, there is no reason = Na should not be eliminated.