Kuehl -- Example 7.1 -- Machine Performance The GLM Procedure Class Level Information Class Levels Values day 4 1 2 3 4 machine 4 1 2 3 4 Number of Observations Read 32 Number of Observations Used 32 Kuehl -- Example 7.1 -- Machine Performance The GLM Procedure Dependent Variable: serum Sum of Source DF Squares Mean Square F Value Pr > F Model 15 3767.777187 251.185146 14.04 <.0001 Error 16 286.325000 17.895313 Corrected Total 31 4054.102188 R-Square Coeff Var Root MSE serum Mean 0.929374 2.996284 4.230285 141.1844 Source DF Type I SS Mean Square F Value Pr > F day 3 1334.463437 444.821146 24.86 <.0001 machine 3 1647.278438 549.092813 30.68 <.0001 day*machine 9 786.035312 87.337257 4.88 0.0029 Source DF Type III SS Mean Square F Value Pr > F day 3 1334.463437 444.821146 24.86 <.0001 machine 3 1647.278438 549.092813 30.68 <.0001 day*machine 9 786.035312 87.337257 4.88 0.0029 Tests of Hypotheses Using the Type III MS for day*machine as an Error Term Source DF Type III SS Mean Square F Value Pr > F day 3 1334.463437 444.821146 5.09 0.0248 machine 3 1647.278438 549.092813 6.29 0.0137 Kuehl -- Example 7.1 -- Machine Performance The GLM Procedure Source Type III Expected Mean Square day Var(Error) + 2 Var(day*machine) + 8 Var(day) machine Var(Error) + 2 Var(day*machine) + 8 Var(machine) day*machine Var(Error) + 2 Var(day*machine) Kuehl -- Example 7.1 -- Machine Performance Variance Components Estimation Procedure Class Level Information Class Levels Values day 4 1 2 3 4 machine 4 1 2 3 4 Number of Observations Read 32 Number of Observations Used 32 Dependent Variable: serum Type 1 Analysis of Variance Sum of Source DF Squares Mean Square day 3 1334.463437 444.821146 machine 3 1647.278438 549.092813 day*machine 9 786.035312 87.337257 Error 16 286.325000 17.895313 Corrected Total 31 4054.102188 Type 1 Analysis of Variance Source Expected Mean Square day Var(Error) + 2 Var(day*machine) + 8 Var(day) machine Var(Error) + 2 Var(day*machine) + 8 Var(machine) day*machine Var(Error) + 2 Var(day*machine) Error Var(Error) Corrected Total Type 1 Estimates Variance Component Estimate Var(day) 44.68549 Var(machine) 57.71944 Var(day*machine) 34.72097 Var(Error) 17.89531 Kuehl -- Example 7.1 -- Machine Performance The Mixed Procedure Model Information Data Set WORK.ONE Dependent Variable serum Covariance Structure Variance Components Estimation Method REML Residual Variance Method Profile Fixed Effects SE Method Model-Based Degrees of Freedom Method Containment Class Level Information Class Levels Values day 4 1 2 3 4 machine 4 1 2 3 4 Dimensions Covariance Parameters 4 Columns in X 1 Columns in Z 24 Subjects 1 Max Obs Per Subject 32 Number of Observations Number of Observations Read 32 Number of Observations Used 32 Number of Observations Not Used 0 Iteration History Iteration Evaluations -2 Res Log Like Criterion 0 1 242.51834215 1 1 215.03835944 0.00000000 Convergence criteria met. Kuehl -- Example 7.1 -- Machine Performance The Mixed Procedure Covariance Parameter Estimates Standard Z Cov Parm Estimate Error Value Pr > Z Alpha Lower day 44.6855 45.6901 0.98 0.1640 0.05 11.8836 machine 57.7194 56.2774 1.03 0.1525 0.05 15.9896 day*machine 34.7210 20.8272 1.67 0.0477 0.05 14.0432 Residual 17.8953 6.3269 2.83 0.0023 0.05 9.9262 Covariance Parameter Estimates Cov Parm Upper day 2037.90 machine 1951.29 day*machine 183.52 Residual 41.4503 Fit Statistics -2 Res Log Likelihood 215.0 AIC (smaller is better) 223.0 AICC (smaller is better) 224.6 BIC (smaller is better) 220.6