Kuehl -- Example 7.5 -- Spectrophotometer Data The GLM Procedure Class Level Information Class Levels Values conc 3 1 2 3 day 3 1 2 3 run 6 1 2 3 4 5 6 Number of Observations Read 36 Number of Observations Used 36 Kuehl -- Example 7.5 -- Spectrophotometer Data The GLM Procedure Dependent Variable: glucose Sum of Source DF Squares Mean Square F Value Pr > F Model 17 108908.2156 6406.3656 4460.91 <.0001 Error 18 25.8500 1.4361 Corrected Total 35 108934.0656 R-Square Coeff Var Root MSE glucose Mean 0.999763 1.024790 1.198379 116.9389 Source DF Type I SS Mean Square F Value Pr > F conc 2 108263.6172 54131.8086 37693.3 <.0001 day 2 24.8772 12.4386 8.66 0.0023 conc*day 4 176.3961 44.0990 30.71 <.0001 run(day) 3 263.1050 87.7017 61.07 <.0001 conc*run(day) 6 180.2200 30.0367 20.92 <.0001 Source DF Type III SS Mean Square F Value Pr > F conc 2 108263.6172 54131.8086 37693.3 <.0001 day 2 24.8772 12.4386 8.66 0.0023 conc*day 4 176.3961 44.0990 30.71 <.0001 run(day) 3 263.1050 87.7017 61.07 <.0001 conc*run(day) 6 180.2200 30.0367 20.92 <.0001 Tests of Hypotheses Using the Type III MS for conc*day as an Error Term Source DF Type III SS Mean Square F Value Pr > F conc 2 108263.6172 54131.8086 1227.51 <.0001 Tests of Hypotheses Using the Type III MS for conc*run(day) as an Error Term Source DF Type III SS Mean Square F Value Pr > F conc*day 4 176.3961111 44.0990278 1.47 0.3206 run(day) 3 263.1050000 87.7016667 2.92 0.1223 Kuehl -- Example 7.5 -- Spectrophotometer Data The GLM Procedure Source Type III Expected Mean Square conc Var(Error) + 2 Var(conc*run(day)) + 4 Var(conc*day) + Q(conc) day Var(Error) + 2 Var(conc*run(day)) + 6 Var(run(day)) + 4 Var(conc*day) + 12 Var(day) conc*day Var(Error) + 2 Var(conc*run(day)) + 4 Var(conc*day) run(day) Var(Error) + 2 Var(conc*run(day)) + 6 Var(run(day)) conc*run(day) Var(Error) + 2 Var(conc*run(day)) Kuehl -- Example 7.5 -- Spectrophotometer Data The Mixed Procedure Model Information Data Set WORK.ONE Dependent Variable glucose 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 conc 3 1 2 3 day 3 1 2 3 run 6 1 2 3 4 5 6 Dimensions Covariance Parameters 5 Columns in X 4 Columns in Z 36 Subjects 1 Max Obs Per Subject 36 Number of Observations Number of Observations Read 36 Number of Observations Used 36 Number of Observations Not Used 0 Iteration History Iteration Evaluations -2 Res Log Like Criterion 0 1 200.48215283 1 3 163.68144329 0.00091036 2 3 163.62990573 . 3 1 163.62761860 0.00000008 4 1 163.62761441 0.00000000 Convergence criteria met. Kuehl -- Example 7.5 -- Spectrophotometer Data The Mixed Procedure Covariance Parameter Estimates Cov Parm Estimate day 0 conc*day 0 run(day) 3.6558 conc*run(day) 17.1127 Residual 1.4361 Fit Statistics -2 Res Log Likelihood 163.6 AIC (smaller is better) 169.6 AICC (smaller is better) 170.5 BIC (smaller is better) 166.9 Solution for Fixed Effects Standard Effect conc Estimate Error DF t Value Pr > |t| Intercept 172.11 1.8924 2 90.95 0.0001 conc 1 -129.96 2.4379 4 -53.31 <.0001 conc 2 -35.5500 2.4379 4 -14.58 0.0001 conc 3 0 . . . . Type 3 Tests of Fixed Effects Num Den Effect DF DF F Value Pr > F conc 2 4 1517.93 <.0001