When we assess X1 as a predictor of Y, there are several ways we can add a third variable (X2), and several "stories" that may describe the relations among variables. Explain what information can be obtained from these two different analyses:
I. Assess the X1, Y relation separately for each group on X2 variable.
II. Partial correlation (partial r of Y with X1 controlling for X2)
a. Which of these analyses (I or II) makes it possible to detect an interaction between X1 and X2? Which analysis assumes that there is no interaction)?
b. If there is an interaction between X1 and X2 as predictors of Y, what pattern would you see in the scatter plots in part I?