4. The researcher identifies variables useful in predicting maximum mouth openin

Question

4. The researcher identifies variables useful in predicting maximum mouth opening (MMo, millimeters) for 35 healthy volunteers. The variables examined were: years DOWN CON downward condylar translation, mm FOR W CON forward condylar translation, mm Gender Female, 1- Make MAN LENG mandibular length, mm MAN WIDT mandibular width, mm The following is the output of the stepwise regression. Describe the most suitable for estimatin the MMO. Also explain the reasons for the selection. Stepwise Regression: MMO versus AGE, DOWNCON, Forward selection Alpha-to-Enter 0.25

Explanation / Answer

Generally we dont include the variables in the final model having p value less than 0.10.

As here the p value of MANWIDT variable is close to 0.10, still we can include it if addition of this variable can result in significant increase in Adjusted R squared. We can use cross-validation to see if addition of this variable results in improved Adjusted R squared. RSS and R squared are not suitable for selecting the best model here, as the model containing all of the predictors will always have the smallest RSS and largest R squared.

Please let me know if you have any doubts.

Related Questions

Navigate

• Browse (All)
• Browse 4
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.