Reconsider the electronic inverter data in Table B.14. In Problems 10.24 and 10.25 , you built regression models for the data using different variable selection algorithms. Suppose that you now learn that the second observation was incorrectly recorded and should be ignored.

a. Fit a model to the modified data using all possible regressions, using \(C_{p}\) as the criterion. Compare this model to the model you found in Problem 10.24.
b. Use stepwise regression to find an appropriate model for the modified data. Compare this model to the one you found in Problem 10.25.
c. Calculate the confidence intervals as the mean response for all points in the modified data set. Compare these results with the confidence intervals from Problem 10.26. Discuss your findings.

Problem 10.24

Table B. 14 presents data on the transient points of an electronic inverter. Use all possible regressions and the CpCp${\mathrm{????}}_{\mathrm{????}}$ criterion to find an appropriate regression model for these data. Investigate model adequacy using residual plots.

Problem 10.25

Reconsider the electronic inverter data in Table B.14. Use stepwise regression to find an appropriate regression model for these data. Investigate model adequacy using residual plots. Compare this model with the one found by the all-possible-regressions approach in Problem 10.24.

Problem 10.24

Table B. 14 presents data on the transient points of an electronic inverter. Use all possible regressions and the Cp${\mathrm{????}}_{\mathrm{????}}$ criterion to find an appropriate regression model for these data. Investigate model adequacy using residual plots.

Observation Number x1 X2 X3 Xs y 12345678 38 38 0 0.787 6 6 D 6 23 6633 342 83384223223268 00 8625534 0 0.293 0 1.710 0 0.203 0 0.806 0.806 0 4.713 4.713 0.607 0.607 9.107 9.107 9.210 1.365 4.554 33382333332468 0.293 2.252 9.167 0.694 0.094 0.379 0.485 0.403 3.345 3.545 0.208 0.201 0.329 4.966 1.362 1.515 0.751