Question 1

You run a correlation matrix of the seven different skinfold sites and obtain an R value of .87 for the abdominal and subscapular sites and a variance inflation factor (VIF) of 0.1. What would you deduce from these findings?

Accepted Answer

A high R value indicates a strong positive correlation between the two skinfold sites, suggesting a high degree of collinearity.

Question 2

Which procedure could be used to determine whether the residuals from the proposed model are independent?

Accepted Answer

The Durbin-Watson statistic is used to test for autocorrelation, which is a violation of the assumption of independence among residuals. If the Durbin-Watson statistic falls between 0 and 4, and is close to 2, then the residuals are likely independent. If the statistic is closer to 0, then there is positive autocorrelation, and if it is closer to 4, then there is negative autocorrelation. Additionally, other diagnostic plots such as a plot of residuals vs. time can also be used to assess independence.

Question 3

Having developed a statistical model to predict percentage body fat, what is the purpose of conducting cross-validation?

Accepted Answer

Cross-validation is used to estimate the accuracy of the developed statistical model. By testing the model on a different subset of the data, it is possible to evaluate how well the model generalizes to new data that was not used during model development. This provides an estimate of the expected prediction error and allows for model optimization and selection. Therefore, the best choice is A.

Quiz 9: The Linear Model Regression

You run a correlation matrix of the seven different skinfold sites and obtain an R value of .87 for the abdominal and subscapular sites and a variance inflation factor (VIF) of 0.1. What would you deduce from these findings?

Which procedure could be used to determine whether the residuals from the proposed model are independent?

Having developed a statistical model to predict percentage body fat, what is the purpose of conducting cross-validation?