Consider a study of n = 40 patients. They all suffered a heart attack and have anger management issues. The dataframe has 3 variables: I ha2 Whether or not a patient had a second heart attack. If ha2 = 1, then the patient had a second heart attack; otherwise, haZ = O. This is the response variable. I treatment Whether or not the patient completed an anger control treatment program. 1 means the program was completed, else is is 0. o anxiety A continuous variable that scores the patient's anxiety level. A higher score denotes higher anxiety. We fit a logistic regression model with R. Here is a summary of the fit. > summary(mod) Call: glm(formula = ha2 ~ treatment + anxiety, binomial(link=logit), data = heartattack) Coefficients: Estimate Std. Error 2 value Pr(>|zl) (Intercept) -6.38342 2.50468 -2.549 0.01082 " treatment -2.73309 1.00548 -2.718 0.00656 \" anxiety 0.13970 0.04819 2.899 0.00374 ** --- Signif. codes: 0 *\" 0.001 '* 0.01 * 0.05.0.1 1 (Dispersion parameterfor binomial family taken to be 1) Null deviance: 55.452 on 39 degrees of freedom Residual deviance: 29.753 on 37 degrees of freedom AIC: 35.753 Use a likelihood ratio test to test for the significance of the regression. Compute the observed value of the test statistic and give the pvalue symbolically. 0 Dev : 29.753; pvalue : P(X2(2) 2 29.753) 0 s . , 2 Dev i 25.699, pvalue i P(X (1) 2 25.699) 0 Dev : 29.753; p-value : P(X2(37) 2 29.753) 0 i . i 2 Dev 55.452, pvalue P(X (39) 2 55.452) 0 Dev : 55.452; pvalue : 1308(2) 2 55.452) 0 Dev : 25.699; pvalue : P(x2(2) 2 25.699)