Which of the following iterative search procedures for model building in a multiple regression analysis starts with all independent variables in the model and then drops nonsignificant independent variables in a step-by-step manner?
A)backward elimination
B)stepwise regression
C)forward selection
D)all possible regressions
E)backward selection

Question

Quizplus · Accepted Answer

Backward elimination iteratively eliminates independent variables from the model that are not statistically significant until all remaining variables are significant. This approach starts with all independent variables in the model and drops nonsignificant independent variables in a step-by-step manner, which is the same as the description given in the question. Additionally, stepwise regression also starts with all independent variables in the model but adds and drops one independent variable at a time based on the significance level of the coefficients. Forward selection starts with a model with no independent variables and adds one independent variable at a time based on the significance level of the coefficients. All possible regressions enter all possible combinations of independent variables in the model and compare the models based on a criterion such as adjusted R-squared. Backward selection is not a commonly used term in regression analysis but may refer to a combination of backward elimination and forward selection.

Which of the Following Iterative Search Procedures for Model Building