Answers are grounded in this paper and cite their sources.
We use geometric methods to investigate the relative magnitudes of SSR(x 2), the sum of squares for regression on x 2 alone, and SSR(x 2|x 1), the increase in the regression sum of squares resulting from the addition of x 2 to a model that already contains x 1. We examine a variety of cases, emphasizing those in which SSR(x 2|x 1) > SSR(x 2). We also point out that SSR(x 2) and SSR(x 2|x 1) can be equal even when x 1 and x 2 are correlated. We present contrived data sets illustrating these points, and examine the relative magnitudes of SSR(x 2) and SSR(x 2|x 1) for two real data sets.
No takes yet. Share an insight, caveat, or question.
Harry M. Schey (1993) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: