2 Assume that you decide to use a different method to estimate the impact of HISP on health expenditure. You are convinced that it would be more appropriate to estimate the counterfactual in the post-intervention period (2 years after the program started). You argue that the outcomes of the group that did not enroll in the program after the intervention could be used to estimate the counterfactual outcomes of the group that enrolled in HISP You therefore decide to calculate average health expenditures in the post-intervention period for both the households that enrolled in the program, and the households that did not. Using the average health expenditures of the nonenrolled households as the estimate of the counterfactual you conduct two regression analysis: Linear regression (only one independent variable) and multivariate linear regression (more than one Independent variables). The main independent variable is a dummy variable (0-1) Indicator that takes the value 1 If the household enrolled the program and if the household did not enroll in the program. The multivariate linear regression adds independent variables to control for other characteristics that are observed for the households in your sample, including indicators for wealth (assets) household composition, and so on. Table 2 shows your regression results Table 2: Effect of HISP on health expenditures (GHC) Health Expenditure Linear regression Multivariate linear regression Coel PU Coel P> HISP -44.46 0.000 39.98 0 .000 (0.33) (0.29) Note: Figures in parentheses are standard errors (a) What method did you perform to estimate the counterfactual? (5 marks) (b) What is the main shortcoming of this method you performed? (5 marks) (c) Interpret the coefficients of both the linear regression and the multivariate linear regression Are they statistically significant? (5 marks). (d) Based on the results in Table 2 should the government scale up the HISP program? (5 marks) 2 Assume that you decide to use a different method to estimate the impact of HISP on health expenditure. You are convinced that it would be more appropriate to estimate the counterfactual in the post-intervention period (2 years after the program started). You argue that the outcomes of the group that did not enroll in the program after the intervention could be used to estimate the counterfactual outcomes of the group that enrolled in HISP You therefore decide to calculate average health expenditures in the post-intervention period for both the households that enrolled in the program, and the households that did not. Using the average health expenditures of the nonenrolled households as the estimate of the counterfactual you conduct two regression analysis: Linear regression (only one independent variable) and multivariate linear regression (more than one Independent variables). The main independent variable is a dummy variable (0-1) Indicator that takes the value 1 If the household enrolled the program and if the household did not enroll in the program. The multivariate linear regression adds independent variables to control for other characteristics that are observed for the households in your sample, including indicators for wealth (assets) household composition, and so on. Table 2 shows your regression results Table 2: Effect of HISP on health expenditures (GHC) Health Expenditure Linear regression Multivariate linear regression Coel PU Coel P> HISP -44.46 0.000 39.98 0 .000 (0.33) (0.29) Note: Figures in parentheses are standard errors (a) What method did you perform to estimate the counterfactual? (5 marks) (b) What is the main shortcoming of this method you performed? (5 marks) (c) Interpret the coefficients of both the linear regression and the multivariate linear regression Are they statistically significant? (5 marks). (d) Based on the results in Table 2 should the government scale up the HISP program