Problem 12-098 Transient points of an electronic inverter are influenced by many factors. Table below gives data on the transient point (y, in volts) of PMOS-NMOS inverters and five candidate regressors: x = width of the NMOS device, x = length of the NMOS device, x; width of the PMOS device, x, length of the PMOS device, and x temperature (C). Observation Number 31 N 3 8 30 239 X4 y 3 3 0 0.787 8 8 0 0.293 3 3 4 4 5 8 6 10 8 6 24 4 10 10 16 3 10 8 13 3 6+ 796702036 6 6 6 0 1.710 4 4 12 6 5 S 5 3 3 4 + 12 12 200 4 + + 00 m m 8 00 8 3 3 3 3 14 3 15 4 16 5 0000 2 8 8 2 * 42 8 8 2 17 2 18 10 15 19 15 256 23 3 ww 3 3 6 2 3 20 15 21 10 64 6. 2 3 4 3 3 22 23 24 3623 00 8 2 2 2 6 m 6 3 8 6 ••• 2 2 2 2 2 2 F F F F 46 0 0.203 0 0.806 0 4.713 25 0.607 25 9.107 25 9.210 25 1.365 25 4.5541 25 0.293 50 2.252 3 50 9.167 50 0.694 50 0.379 50 0.485 50 3.345 50 0.208 75 0.201 75 0.329 75 4.966 75 1.362 75 1.515 3 8 8 75 0.751 (a) Fit a multiple linear regression model that uses all regressors to these data. Test for significance of regression using a 0.01. (b) Test the contribution of each variable to the model using the t-test with a = 0.05. What are your conclusions? (c) Delete xs from the model. Test the new model for significance of regression at a = 0.05. Also test the relative contribution of each regressor to the new model with the t-test. Using a 0.05, what are your conclusions? Round all intermediate calculations to four decimal places (e.g. 12.3456) and round the final answer to two decimal places (e.g. 98.76). (a) The regression model + significant at a 0.01. is or is not Xs (b) Bl significant, B significant, B significant, B significant, and B significant at a 0.05. (c) The regression model B significant, B significant at a 0.05. significant at a 0.05. significant, B significant, and Ba