The MIXED Procedure Class Level Information Class Levels Values PATIENT 5 1 2 3 4 5 TRT 2 D P WEEK 2 1 2 The MIXED Procedure REML Estimation Iteration History Iteration Evaluations Objective Criterion 0 1 9.57766620 1 2 8.75051836 0.03876999 2 1 8.53168239 0.01656601 3 1 8.44518286 0.00344031 4 1 8.42879045 0.00017751 5 1 8.42801613 0.00000053 6 1 8.42801387 0.00000000 Convergence criteria met. The MIXED Procedure Covariance Parameter Estimates (REML) Cov Parm Ratio Estimate Std Error Z Pr > |Z| PATIENT(TRT) 8.43590506 2.17104064 2.00065995 1.09 0.2778 Residual 1.00000000 0.25735717 0.37484252 0.69 0.4924 The MIXED Procedure Model Fitting Information for SCORE Description Value Observations 8.0000 Variance Estimate 0.2574 Standard Deviation Estimate 0.5073 REML Log Likelihood -7.8898 Akaike's Information Criterion -9.8898 Schwarz's Bayesian Criterion -9.2761 -2 REML Log Likelihood 15.7795 The MIXED Procedure Solution for Fixed Effects Parameter Estimate Std Error DDF T Pr > |T| INTERCEPT 17.10597818 1.20744315 1 14.17 0.0449 TRT D 5.14900364 1.53252240 1 3.36 0.1842 The MIXED Procedure Solution for Fixed Effects Parameter Estimate Std Error DDF T Pr > |T| TRT P 0.00000000 . . . . WEEK 1 5.89402182 0.70786808 1 8.33 0.0761 WEEK 2 0.00000000 . . . . TRT*WEEK D 1 -3.48233697 0.86826763 1 -4.01 0.1556 TRT*WEEK D 2 0.00000000 . . . . TRT*WEEK P 1 0.00000000 . . . . TRT*WEEK P 2 0.00000000 . . . . The MIXED Procedure Tests of Fixed Effects Source NDF DDF Type III F Pr > F TRT 1 3 5.81 0.0949 WEEK 1 1 91.51 0.0663 TRT*WEEK 1 1 16.09 0.1556 The MIXED Procedure Least Squares Means Level LSMEAN Std Error DDF T Pr > |T| TRT D 23.46082424 0.88706430 1 26.45 0.0241 TRT P 20.05298909 1.10035886 1 18.22 0.0349 WEEK 1 23.83333333 0.71127787 1 33.51 0.0190 WEEK 2 19.68047999 0.76626120 1 25.68 0.0248 TRT*WEEK D 1 24.66666667 0.89970325 1 27.42 0.0232 TRT*WEEK D 2 22.25498181 0.94377219 1 23.58 0.0270 TRT*WEEK P 1 23.00000000 1.10190694 1 20.87 0.0305 TRT*WEEK P 2 17.10597818 1.20744315 1 14.17 0.0449 General Linear Models Procedure Class Level Information Class Levels Values PATIENT 5 1 2 3 4 5 TRT 2 D P WEEK 2 1 2 Number of observations in data set = 8 General Linear Models Procedure Dependent Variable: SCORE Sum of Mean Source DF Squares Square F Value Pr > F Model 6 41.7500000 6.9583333 27.83 0.1441 Error 1 0.2500000 0.2500000 Corrected Total 7 42.0000000 R-Square C.V. Root MSE SCORE Mean 0.994048 2.173913 0.50000 23.0000 Source DF Type I SS Mean Square F Value Pr > F TRT 1 13.3333333 13.3333333 53.33 0.0866 PATIENT(TRT) 3 4.1666667 1.3888889 5.56 0.3000 WEEK 1 20.1666667 20.1666667 80.67 0.0706 TRT*WEEK 1 4.0833333 4.0833333 16.33 0.1544 Source DF Type III SS Mean Square F Value Pr > F TRT 1 15.5648148 15.5648148 62.26 0.0803 PATIENT(TRT) 3 8.4166667 2.8055556 11.22 0.2152 WEEK 1 24.0833333 24.0833333 96.33 0.0646 TRT*WEEK 1 4.0833333 4.0833333 16.33 0.1544 Tests of Hypotheses using the Type III MS for PATIENT(TRT) as an error term Source DF Type III SS Mean Square F Value Pr > F TRT 1 15.5648148 15.5648148 5.55 0.0998 T for H0: Pr > |T| Std Error of Parameter Estimate Parameter=0 Estimate INTERCEPT 16.00000000 B 18.48 0.0344 0.86602540 TRT D 7.75000000 B 8.00 0.0791 0.96824584 P 0.00000000 B . . . PATIENT(TRT) 3 D -1.50000000 B -3.00 0.2048 0.50000000 4 D -3.25000000 B -4.91 0.1278 0.66143783 5 D 0.00000000 B . . . 1 P 2.00000000 B 2.83 0.2163 0.70710678 2 P 0.00000000 B . . . WEEK 1 6.00000000 B 8.49 0.0747 0.70710678 2 0.00000000 B . . . TRT*WEEK D 1 -3.50000000 B -4.04 0.1544 0.86602540 D 2 0.00000000 B . . . P 1 0.00000000 B . . . P 2 0.00000000 B . . . NOTE: The X'X matrix has been found to be singular and a generalized inverse was used to solve the normal equations. Estimates followed by the letter 'B' are biased, and are not unique estimators of the parameters. General Linear Models Procedure Source Type III Expected Mean Square TRT Var(Error) + 1.1111 Var(PATIENT(TRT)) + Q(TRT,TRT*WEEK) PATIENT(TRT) Var(Error) + 1.3333 Var(PATIENT(TRT)) WEEK Var(Error) + Q(WEEK,TRT*WEEK) TRT*WEEK Var(Error) + Q(TRT*WEEK) General Linear Models Procedure Tests of Hypotheses for Mixed Model Analysis of Variance Dependent Variable: SCORE Source: TRT * Error: 0.8333*MS(PATIENT(TRT)) + 0.1667*MS(Error) Denominator Denominator DF Type III MS DF MS F Value Pr > F 1 15.564814815 3.10 2.3796296296 6.5409 0.0806 * - This test assumes one or more other fixed effects are zero. Source: PATIENT(TRT) Error: MS(Error) Denominator Denominator DF Type III MS DF MS F Value Pr > F 3 2.8055555556 1 0.25 11.2222 0.2152 Source: WEEK * Error: MS(Error) Denominator Denominator DF Type III MS DF MS F Value Pr > F 1 24.083333333 1 0.25 96.3333 0.0646 * - This test assumes one or more other fixed effects are zero. Source: TRT*WEEK Error: MS(Error) Denominator Denominator DF Type III MS DF MS F Value Pr > F 1 4.0833333333 1 0.25 16.3333 0.1544 Least Squares Means Standard Errors and Probabilities calculated using the Type III MS for PATIENT(TRT) as an Error term TRT SCORE Std Err Pr > |T| Pr > |T| H0: LSMEAN LSMEAN H0:LSMEAN=0 LSMEAN1=LSMEAN2 D 23.4166667 0.8374896 0.0001 0.0998 P 20.0000000 1.1843892 0.0005 Least Squares Means WEEK SCORE Std Err Pr > |T| Pr > |T| H0: LSMEAN LSMEAN H0:LSMEAN=0 LSMEAN1=LSMEAN2 1 23.8333333 0.2282177 0.0061 0.0646 2 19.5833333 0.3679900 0.0120 TRT WEEK SCORE Std Err Pr > |T| LSMEAN LSMEAN LSMEAN H0:LSMEAN=0 Number D 1 24.6666667 0.2886751 0.0075 1 D 2 22.1666667 0.4082483 0.0117 2 P 1 23.0000000 0.3535534 0.0098 3 P 2 17.0000000 0.6123724 0.0229 4 Pr > |T| H0: LSMEAN(i)=LSMEAN(j) i/j 1 2 3 4 1 . 0.1257 0.1702 0.0561 2 0.1257 . 0.3661 0.0901 3 0.1702 0.3661 . 0.0747 4 0.0561 0.0901 0.0747 . NOTE: To ensure overall protection level, only probabilities associated with pre-planned comparisons should be used.