An actuary wanted to develop a model to predict individual life duration. After consulting a number of physicians, actuary decided to investigate few factors, which in opinion of doctors may affect life duration. The actuary proposed the multiple regression model y = Be + B,X, + B2x2 + B3x3 +, where y = the age at the death (in years), x = the average number of hours of exercise per week, x2 = the cholesterol level (in milligrams per deciliter blood (mg/dL)), Xz = the number of points that the individual's blood pressure exceeded the recommended value. To estimate multiple regression model, a random sample of 40 individual records was selected by actuary from the records of insurance company. He used MINITAB multiple regression program and obtained the following computer output: Predictor Constant X1 Coef 55.80 1.79 SE Coet 11.800 0.440 T 4.729 4.068 x2 -0.021 0.011 -1.909 X3 -0.016 0.014 -1.143 S = 9.47 R-Sq = 22.5% Analysis of variance Source Regression Residual Error Total DF 3 SS 936 3230 4166 MS 312 89.722 F 3.477 36 39 a. b. In the context of given problem interpret the regression coefficient 2. Do these data provide sufficient evidence to conclude at the 5% significance level that the model is useful in predicting length of life? Approximate the value fo.05, 3, 36 with available in the table. Do these data provide sufficient evidence to conclude at the 5% significance level that the age at death and cholesterol level are negatively linearly related? $0.05, 3, 40 C