3. The data (bloodpressure) gives the systolic blood pressure (SBP), body size (QUET) and smoking history (SMK=0 if nonsmoker, SMK=1 if smoker) for a hypothetical sample of 32 white males over 40 years old from the town of Angina. In the problem, we will choose SBP as the response. The two variables QUET and SMK will be considered. Answer the following questions about the separate straight-line regression of SBP on QUET for smokers (SMK=1) and nonsmoker (SMK=0). (You will choose significance level at .05). a. Define a single multiple regression model (Hint: you need put these two variables and also don’t forget the interaction). b. Using SAS to estimate this model; Write out the regression lines for smokers and nonsmokers. Are there any differences with the previous two lines from question 2? c. (Test for the qualitative variable) For every QUET, does the mean effect of the response depend on the smoking history? (Hint: Should the variable smoking status be included in the model?) You need to write the hypotheses, report SAS output and show your conclusion. d. Assume that the result in the above test is significant. Does the effect of QUET on the SBP depend on the status of smoking? You need to write the hypotheses, report SAS output and show your conclusion. (Hint: Should the interaction be included in the model?)