82 BUSINESS APPLICATIONS OF MULTIPLE REGRESSION
Multiple Regression Equation
ˆ
Y = 185.3875 + 47.3511b
1
– 50.7684b
2
One of the assumptions of multiple regression is the nonmulticollinearity
assumption: There is no correlation between the independent variables.
In this example, there is slight (0.1406) correlation between the two
independent variables. It is this slight correlation that prevents the total
of the individual simple regression equations from totaling to the mul-
tiple regression equation. The higher the correlation, the greater the
difference there will be between the equations derived using these two
approaches. Because there is virtually always some degree of correlation
between independent variables, in practice ...