An Example
	q For a 2-predictor case: r1y = r2y = r12 = 0.50      If only include one predictor (x1) (r2y = r12 =0) è R2=025      By adding x2 in the regression (r2y = r12 =0.25) è R2=033      In this case, the 2nd predictor improve the regression. q For a 2-predictor case: r1y = r12 = 0.50 but r2y = 0.25      If with only x1 è R2=025      Adding x2        è R2=025 (still the same!!)      In this case, the 2nd predictor is not useful.  It is because      r2y £ r1y * r12 = 0.50*0.50 = 0.25