Model 1:  Let’s consider the logistic regression model, which we would refer to as Model 1, given by
        log(pi / [1-pi]) = 0.25 + 0.32*X1 + 0.70*X2 + 0.50*X3         (M1),
Where X3 is an indicator variable with X3=0 if the observation is from Group A and X3=1 if the observation is from Group B. The likelihood value for this fitted model on 100 observations is 850.

(1) For X1=2 and X2=1 find out the log-odds ratio for each group, i.e. X3=0 and X3=1.

(2) For X1=2 and X2=1 find out the odds ratio for each group, i.e. X3=0 and X3=1.

(3) For X1=2 and X2=1 find out the probability of the event for each group, i.e. X3=0 and X3=1.

(4) Using the equation for M1, find out the relative odds related with X3, i.e. the relative odds ratio of Group B compared to Group A.

(5) Use the odds ratios for each group to find out the relative odds of Group B to Group A. How does this number compare to the result in problem 4.  Does this make sense?

Model 2:  Now let us consider the alternate logistic regression model, which we would refer to as Model 2, given by
        log(pi / [1-pi]) = 0.25 + 0.32*X1 + 0.70*X2 + 0.50*X3 + 0.1*X4    (M2),
Where X3 is an indicator variable with X3=0 if the observation is from Group A and X3=1 if the observation is from Group B.  The likelihood value from fitting this model to the similar 100 observations as M1 is 910.

(6) Make use of the G statistic to carry out a likelihood ratio test of nested models for M1 and M2.  State the hypothesis that is being tested, compute the test statistic, and test the statistical importance using a critical value for alpha=0.05. From these results should we prefer M1 or M2?