On the Heart and Estrogen Replacement Study, a research question of interest was to quantify the effect of physical activity (1 to 5 increasing scale) and drinking status (1=any drinking, 0 = no drinking) on serum glucose levels at year one of the study. These data were analyzed using two different models. Results from the analysis are provided below labeled SAS Output 1 and SAS Output 2. To answer some of the questions that follow, you need to fill in some critical pieces of information that have been deleted.

45. What type of analysis should you perform to test the given hypothesis? . ANCOVA b. Two-way ANOVA c. Linear regression d. Logistic Regression e. One-way ANOVA 46. In SAS Output 2, what number should you insert for the Error degrees of freedom? a. 5 b. 2605 c. 2604 d. 2601 e. 2610 47. Which model is more appropriate for these data: the model in SAS Output 1 or the model in SAS Output 2? Which test statistic and p-value should you use to make this decision? a. Output 1 because the interaction is significant (F = 10.08, p-value It Source DF Sum of Squares Mean Square F Value Pr > F Intercept 133.5214559 8 3.32553319 40.15 F PHYSACT GLUCOSE1 LSMEAN LSMEAN Number Pr > [t for HO: LSMean(i)=LSMean(] PHYSACT 4 99414 06422 24853.51605 13.17 F 114. 184838 3 2 0.7301 0.1223 0 0014 <.0001 n w a physact drinkany sas output dependent variable: glucose1 year fasting glucose standard parameter estimate error t value pr> It Source DF Sum of Squares Mean Square F Value |Pr > F Intercept 136.1311475 8 3.93349578 34.61 <.0001 model physact error corrected total b r-square coeff var root mse glucose1 mean drinkany source df type i ss square f value pr> F DRINKANY 0 0.0000000 B PHYSACT 4 99414.06422 24853.51605 13.17 <.0001 physact drinkany b source df typo ill ss moan square f value pr> F PHYSACT*DRINKANY 3 1 11.0550220 8 7.76171494 1.42 0.1545 PHYSACT 4 72177.32993 18044.33248 9.56 <.0001 physact b drinkany>