Chapter 13 : Pygmalion effect study
Data Listing

Obs treat COMPANY SCORE
1 PYGMALION C1 80.0000
2 CONTROL C1 63.2000
3 CONTROL C1 69.2000
4 PYGMALION C2 83.9000
5 CONTROL C2 63.1000
6 CONTROL C2 81.5000
7 PYGMALION C3 68.2000
8 CONTROL C3 76.2000
9 PYGMALION C4 76.5000
10 CONTROL C4 59.5000
11 CONTROL C4 73.5000
12 PYGMALION C5 87.8000
13 CONTROL C5 73.9000
14 CONTROL C5 78.5000
15 PYGMALION C6 89.8000
16 CONTROL C6 78.9000
17 CONTROL C6 84.7000
18 PYGMALION C7 76.1000
19 CONTROL C7 60.6000
20 CONTROL C7 69.6000
21 PYGMALION C8 71.5000
22 CONTROL C8 67.8000
23 CONTROL C8 73.2000
24 PYGMALION C9 69.5000
25 CONTROL C9 72.3000
26 CONTROL C9 73.9000
27 PYGMALION C10 83.7000
28 CONTROL C10 63.7000
29 CONTROL C10 77.7000


Chapter 13 : Pygmalion effect study
Randomized block design

The Mixed Procedure

Model Information
Data Set WORK.PYGMALION
Dependent Variable SCORE
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
COMPANY 10 C1 C10 C2 C3 C4 C5 C6 C7 C8 C9
treat 2 CONTROL PYGMALION

Dimensions
Covariance Parameters 3
Columns in X 3
Columns in Z 30
Subjects 1
Max Obs Per Subject 29

Number of Observations
Number of Observations Read 29
Number of Observations Used 29
Number of Observations Not Used 0

Iteration History
Iteration Evaluations -2 Res Log Like Criterion
0 1 189.62816349  
1 3 188.52486198 0.00001389
2 1 188.52387871 0.00000001
3 1 188.52387787 0.00000000

Convergence criteria met.

Covariance Parameter Estimates
Cov Parm Estimate Standard Error Z Value Pr Z Alpha Lower Upper
COMPANY 11.5096 13.1166 0.88 0.1901 0.05 2.7832 1177.86
COMPANY*treat 0 . . . . . .
Residual 42.9038 14.1942 3.02 0.0013 0.05 24.5843 93.1732

Fit Statistics
-2 Res Log Likelihood 188.5
AIC (smaller is better) 192.5
AICC (smaller is better) 193.0
BIC (smaller is better) 193.1

Type 3 Tests of Fixed Effects
Effect Num DF Den DF F Value Pr > F
treat 1 9 7.72 0.0214

Least Squares Means
Effect treat Estimate Standard Error DF t Value Pr > |t| Alpha Lower Upper
treat CONTROL 71.5776 1.8514 9 38.66 <.0001 0.05 67.3895 75.7657
treat PYGMALION 78.7000 2.3327 9 33.74 <.0001 0.05 73.4231 83.9769

Differences of Least Squares Means
Effect treat _treat Estimate Standard Error DF t Value Pr > |t| Adjustment Adj P Alpha Lower Upper Adj Lower Adj Upper
treat CONTROL PYGMALION -7.1224 2.5626 9 -2.78 0.0214 Tukey-Kramer 0.0214 0.05 -12.9195 -1.3254 -12.9193 -1.3256


Chapter 13 : Pygmalion effect study
Randomized block design

Estimate Mean                                                                                      
                                                                                                   
   80.000000 +                   *****                                                             
             |                   *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
   60.000000 +       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
   40.000000 +       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
   20.000000 +       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
             |       *****       *****                                                             
             --------------------------------                                                      
                    CONTROL    PYGMALION                                                           
                                                                                                   
                           treat                                                                   


Chapter 13 : Pygmalion effect study
Randomized block design

The UNIVARIATE Procedure
Variable: Resid

Moments
N 29 Sum Weights 29
Mean 0 Sum Observations 0
Std Deviation 5.94652573 Variance 35.3611683
Skewness -0.4620638 Kurtosis -1.0780922
Uncorrected SS 990.112712 Corrected SS 990.112712
Coeff Variation . Std Error Mean 1.10424211

Basic Statistical Measures
Location Variability
Mean 0.000000 Std Deviation 5.94653
Median 1.637335 Variance 35.36117
Mode . Range 19.17583
    Interquartile Range 10.02176

Tests for Location: Mu0=0
Test Statistic p Value
Student's t t 0 Pr > |t| 1.0000
Sign M 1.5 Pr >= |M| 0.7111
Signed Rank S 4.5 Pr >= |S| 0.9245

Tests for Normality
Test Statistic p Value
Shapiro-Wilk W 0.912103 Pr < W 0.0193
Kolmogorov-Smirnov D 0.153832 Pr > D 0.0788
Cramer-von Mises W-Sq 0.151147 Pr > W-Sq 0.0221
Anderson-Darling A-Sq 0.949008 Pr > A-Sq 0.0155

Quantiles (Definition 5)
Quantile Estimate
100% Max 8.93474
99% 8.93474
95% 8.43359
90% 6.41116
75% Q3 4.21231
50% Median 1.63734
25% Q1 -5.80945
10% -9.46527
5% -9.47383
1% -10.24110
0% Min -10.24110

Extreme Observations
Lowest Highest
Value Obs Value Obs
-10.24110 10 5.64860 8
-9.47383 7 6.37322 12
-9.46527 5 6.41116 15
-8.66545 19 8.43359 17
-8.35989 28 8.93474 6

   Stem Leaf                     #  Boxplot                        Normal Probability Plot                     
      8 49                       2     |           9+                                       ++*   *            
      6 44                       2     |            |                                    +**                   
      4 22566                    5  +-----+         |                              **+***                      
      2 67028                    5  |     |         |                          ****++                          
      0 36                       2  *--+--*         |                        **+++                             
     -0 0443                     4  |     |       -1+                     ***+                                 
     -2 4                        1  |     |         |                   +*+                                    
     -4 8                        1  +-----+         |               ++++*                                      
     -6 0                        1     |            |            +++  *                                        
     -8 55743                    5     |            |         *++** **                                         
    -10 2                        1     |         -11+     *+++                                                 
        ----+----+----+----+                         +----+----+----+----+----+----+----+----+----+----+       
                                                         -2        -1         0        +1        +2            
                                                                                                               
                                                                                                               


Chapter 13 : Pygmalion effect study
Randomized block design

The GLM Procedure

Class Level Information
Class Levels Values
COMPANY 10 C1 C10 C2 C3 C4 C5 C6 C7 C8 C9
treat 2 CONTROL PYGMALION

Number of Observations Read 29
Number of Observations Used 29


Chapter 13 : Pygmalion effect study
Randomized block design

The GLM Procedure
 
Dependent Variable: SCORE

Source DF Sum of Squares Mean Square F Value Pr > F
Model 19 1321.322322 69.543280 1.34 0.3358
Error 9 467.039883 51.893320    
Corrected Total 28 1788.362205      

R-Square Coeff Var Root MSE SCORE Mean
0.738845 9.725668 7.203702 74.06897

Source DF Type I SS Mean Square F Value Pr > F
treat 1 327.3410535 327.3410535 6.31 0.0332
COMPANY 9 682.5172780 75.8352531 1.46 0.2905
COMPANY*treat 9 311.4639907 34.6071101 0.67 0.7221

Source DF Type III SS Mean Square F Value Pr > F
treat 1 301.8426278 301.8426278 5.82 0.0391
COMPANY 9 665.6630817 73.9625646 1.43 0.3030
COMPANY*treat 9 311.4639907 34.6071101 0.67 0.7221

Tests of Hypotheses Using the Type III MS for COMPANY*treat as an Error Term
Source DF Type III SS Mean Square F Value Pr > F
treat 1 301.8426278 301.8426278 8.72 0.0161
COMPANY 9 665.6630817 73.9625646 2.14 0.1366


Chapter 13 : Pygmalion effect study
Randomized block design

The GLM Procedure

Source Type III Expected Mean Square
treat Var(Error) + 1.2903 Var(COMPANY*treat) + Q(treat)
COMPANY Var(Error) + 1.2991 Var(COMPANY*treat) + 2.5983 Var(COMPANY)
COMPANY*treat Var(Error) + 1.2991 Var(COMPANY*treat)