In Exercise 17.12, suppose the researcher wishes to use one of the models in this section, but is uncertain as to whether y might be nonlinearly related to x1 and/or x2. Also, the researcher doesn’t have any idea as to whether interaction might exist between x1 and x2. Of the models in this section, which one would result in the highest R2 value while at the same time reducing the possibility that the researcher might “miss” an important aspect of the relationship between the dependent and predictor variables?
In exercise
A researcher suspects that the dependent variable y is linearly related to both x1 and x2, but believes there is little or no interaction between the two predictor variables.