In a stepwise regression procedure, if two independent variables are highly correlated, then one variable usually eliminates the second variable.

Question

Quizplus · Accepted Answer

When two independent variables are highly correlated, it indicates that they are measuring similar aspects of the phenomenon being studied. In such cases, including both variables in a regression model may lead to multicollinearity, which can affect the stability and interpretability of the coefficients. In a stepwise regression procedure, the algorithm typically evaluates the contribution of each variable to the model based on the improvement in the model fit (e.g., R-squared) and the significance of the coefficients. If two variables are highly correlated, they may have similar improvements and significance levels, making it difficult for the algorithm to choose between them. However, as the algorithm proceeds through the stepwise procedure, it may eliminate one of the variables based on some additional criteria (e.g., p-value, adjusted R-squared). Therefore, it is possible that one variable eliminates a highly correlated second variable in a stepwise regression procedure.

In a Stepwise Regression Procedure, If Two Independent Variables Are