Q7 Comparing Mean LDL Levels by BMI by Statin Usage (4 Points + 6 Extra Credit Points) How do mean LDL cholesterol levels vary by BMI and statins useage while controlling for age and glucose levels? Running separate regression models for statins users (statins==1) and and non-users(statins= =0) one finds different relationships between LDL and BMI. ## ## Call: ## 1m(formula = LDL - BMI + glucose + age, data = hers, subset = statins => ## 1) ## ## Residuals: Min 10 Median 3Q Max ## -80.067 -23.563 -3.535 18. 185 176.563 ## Coefficients: # # Estimate Std. Error t value Pr(>It/) ## (Intercept) 147.20614 23.34593 6. 305 8.470-10 *#* ## BMI 0. 02981 0. 35977 0. 083 0.934 ## glucose -0. 08936 0. 05757 -1. 652 0. 122 ## age -0. 07099 0. 29084 -0.244 0.807 ## ## Signif. codes: 0 '**' 0.001 '*>' 0.01 '*' 0.05 ".' 0.1 > > 1 # # ## Residual standard error: 34.21 on 358 degrees of freedom (3 observations deleted due to missingness) ## Multiple R-squared: 0.006987, Adjusted R-squared: -0.001334 ## F-statistic: 0.8397 on 3 and 358 DF, p-value: 0.4728 # # ## Call: ## 1m (formula = LDL - BMI + glucose + age, data = hers, subset = statins == ## 0) ## Residuals: # # Min 1Q Median 3Q Max ## -105.478 -23.959 -2. 021 22.169 239.807 # # ## Coefficients: # # Estimate Std. Error t value Pr(>It/) ## (Intercept) 166.37538 17 . 16624 9.692 > 1 ## Residual standard error: 36.46 on 630 degrees of freedom ## (1 observation deleted due to missingness) ## Multiple R-squared: 0.024, Adjusted R-squared: 0.01935 ## F-statistic: 5.163 on 3 and 630 DF, p-value: 0.001567 In this question, we will test this hypothesis at a significance level of 5%. We will follow the steps below: 12 (a) [2 points] Interpret the slope parameters related to the coefficient of BMI for statins users in the context of this problem. Is this coefficient significantly different from zero? Answer: (b) [2 points] Interpret the slope parameters related to the coefficient of BMI for statins non-users in the context of this problem. Is this coefficient significantly different from zero