The information in Figures 10.18 and 10.19 are based on the ICU data set. Figure 10.18 results from fitting the logistic regression interaction model with

Question

53 users unlocked this solution today!

The information in Figures 10.18 and 10.19 are based on the ICU data set. Figure 10.18 results from fitting the logistic regression interaction model with vital status

(STA) as the response variable with age (AGE) and CPR prior to admission

(CPR) as the explanatory variables, and Figure 10.19 results from fitting the logistic regression no-interaction model with STA as the response variable with AGE and CPR as the explanatory variables. Use the information in Figures 10.18 and 10.19 and ???? = 200 to answer the following questions.

(a) Test the goodness-of-fit of the interaction model summarized in Figure 10.18.

(b) Compare the fit of the interaction model with the no-interaction model using a drop-in-deviance test and ???? = 0.05.

(c) Which model appears to be a better model for explaining the response variable?
Explain.

(d) For the better model chosen in part (c), estimate ????(STA = 1) when AGE=30 and CPR=1.

(e) Compute the values of BIC for both models.

(f) Which model appears to be a better model for explaining the response variable according to BIC? Explain.

Coefficients Term Coef SE Coef Constant -3.352 0.745 AGE 0.0296 0.0111 CPR 1 1.784 0.607 Goodness-of-Fit Tests Test DF Chi-Square P-Value Deviance 197 183.95 0.738