Output from manova4.sas

Source
0 Graphs

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 1 Analysis using REPEATED statement

                       General Linear Models Procedure
                   Number of observations in data set = 19


Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 2 Analysis using REPEATED statement

                       General Linear Models Procedure
                    Repeated Measures Analysis of Variance
                     Repeated Measures Level Information

           Dependent Variable   HIGH_NOH  LOW_NOH   HIGH_H    LOW_H

                 Level of HAL          1        1        2        2
                 Level of CO2          1        2        1        2



               Manova Test Criteria and Exact F Statistics for
                       the Hypothesis of no HAL Effect
          H = Type III SS&CP Matrix for HAL   E = Error SS&CP Matrix

                             S=1    M=-0.5    N=8

 Statistic                     Value          F      Num DF    Den DF  Pr > F
 Wilks' Lambda              0.16940251    88.2558         1        18  0.0001
 Pillai's Trace             0.83059749    88.2558         1        18  0.0001
 Hotelling-Lawley Trace     4.90310036    88.2558         1        18  0.0001
 Roy's Greatest Root        4.90310036    88.2558         1        18  0.0001
               Manova Test Criteria and Exact F Statistics for
                       the Hypothesis of no CO2 Effect
          H = Type III SS&CP Matrix for CO2   E = Error SS&CP Matrix

                             S=1    M=-0.5    N=8

 Statistic                     Value          F      Num DF    Den DF  Pr > F
 Wilks' Lambda              0.57715417    13.1875         1        18  0.0019
 Pillai's Trace             0.42284583    13.1875         1        18  0.0019
 Hotelling-Lawley Trace     0.73263931    13.1875         1        18  0.0019
 Roy's Greatest Root        0.73263931    13.1875         1        18  0.0019
               Manova Test Criteria and Exact F Statistics for
                     the Hypothesis of no HAL*CO2 Effect
        H = Type III SS&CP Matrix for HAL*CO2   E = Error SS&CP Matrix

                             S=1    M=-0.5    N=8

 Statistic                     Value          F      Num DF    Den DF  Pr > F
 Wilks' Lambda              0.97766408     0.4112         1        18  0.5294
 Pillai's Trace             0.02233592     0.4112         1        18  0.5294
 Hotelling-Lawley Trace     0.02284621     0.4112         1        18  0.5294
 Roy's Greatest Root        0.02284621     0.4112         1        18  0.5294

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 3 Analysis using REPEATED statement

                       General Linear Models Procedure
                    Repeated Measures Analysis of Variance
          Univariate Tests of Hypotheses for Within Subject Effects

Source: HAL
                                                                 Adj  Pr > F
     DF      Type III SS      Mean Square   F Value   Pr > F    G - G    H - F
      1   208112.2236842   208112.2236842     88.26   0.0001    .        .
Source: Error(HAL)

     DF      Type III SS      Mean Square
     18    42445.0263158     2358.0570175
Source: CO2
                                                                 Adj  Pr > F
     DF      Type III SS      Mean Square   F Value   Pr > F    G - G    H - F
      1   17130.01315789   17130.01315789     13.19   0.0019    .        .
Source: Error(CO2)

     DF      Type III SS      Mean Square
     18   23381.23684211    1298.95760234
Source: HAL*CO2
                                                                 Adj  Pr > F
     DF      Type III SS      Mean Square   F Value   Pr > F    G - G    H - F
      1     776.96052632     776.96052632      0.41   0.5294    .        .
Source: Error(HAL*CO2)

     DF      Type III SS      Mean Square
     18   34008.28947368    1889.34941520

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 4 Analysis using MANOVA statement

                       General Linear Models Procedure
                   Number of observations in data set = 19

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 5 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

                  M Matrix Describing Transformed Variables
                  HIGH_NOH          LOW_NOH           HIGH_H            LOW_H

 Halothan                1                1               -1               -1

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 6 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

          Characteristic Roots and Vectors of: E Inverse * H, where
       H = Type III SS&CP Matrix for INTERCEPT   E = Error SS&CP Matrix

               Variables have been transformed by the M Matrix

        Characteristic   Percent        Characteristic Vector  V'EV=1
             Root
                                              Halothan
            4.90310036    100.00            0.00242693


               Manova Test Criteria and Exact F Statistics for
                the Hypothesis of no Overall INTERCEPT Effect
           on the variables defined by the M Matrix Transformation
       H = Type III SS&CP Matrix for INTERCEPT   E = Error SS&CP Matrix

                             S=1    M=-0.5    N=8

 Statistic                     Value          F      Num DF    Den DF  Pr > F
 Wilks' Lambda              0.16940251    88.2558         1        18  0.0001
 Pillai's Trace             0.83059749    88.2558         1        18  0.0001
 Hotelling-Lawley Trace     4.90310036    88.2558         1        18  0.0001
 Roy's Greatest Root        4.90310036    88.2558         1        18  0.0001

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 7 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

                  M Matrix Describing Transformed Variables
                  HIGH_NOH          LOW_NOH           HIGH_H            LOW_H

 Halothan                1                1               -1               -1
 Co2                     1               -1                1               -1
 HxCO2                   1               -1               -1                1


                            E = Error SS&CP Matrix
                          Halothan               Co2             HxCO2

        Halothan      169780.10526      -19780.31579      -16696.73684
        Co2           -19780.31579      93524.947368      16462.210526
        HxCO2         -16696.73684      16462.210526      136033.15789

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 8 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

         Partial Correlation Coefficients from the Error SS&CP Matrix
    of the Variables Defined by the Specified Transformation / Prob > |r|
                   DF = 18     Halothan       Co2     HxCO2

                   Halothan    1.000000 -0.156973 -0.109867
                                 0.0001    0.5210    0.6543
                   Co2        -0.156973  1.000000  0.145949
                                 0.5210    0.0001    0.5510
                   HxCO2      -0.109867  0.145949  1.000000
                                 0.6543    0.5510    0.0001



Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 9 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

                   H = Type III SS&CP Matrix for INTERCEPT
                          Halothan               Co2             HxCO2

        Halothan      832448.89474      238829.31579      50863.736842
        Co2           238829.31579      68520.052632      14592.789474
        HxCO2         50863.736842      14592.789474      3107.8421053

          Characteristic Roots and Vectors of: E Inverse * H, where
       H = Type III SS&CP Matrix for INTERCEPT   E = Error SS&CP Matrix

               Variables have been transformed by the M Matrix

Characteristic   Percent                Characteristic Vector  V'EV=1
     Root
                                      Halothan            Co2          HxCO2
    6.44535118    100.00            0.00232259     0.00154805     0.00025916
    0.00000000      0.00            0.00000083    -0.00058630     0.00273933
    0.00000000      0.00           -0.00083221     0.00290069     0.00000000


               Manova Test Criteria and Exact F Statistics for
                the Hypothesis of no Overall INTERCEPT Effect
           on the variables defined by the M Matrix Transformation
       H = Type III SS&CP Matrix for INTERCEPT   E = Error SS&CP Matrix

                             S=1    M=0.5    N=7

 Statistic                     Value          F      Num DF    Den DF  Pr > F
 Wilks' Lambda              0.13431200    34.3752         3        16  0.0001
 Pillai's Trace             0.86568800    34.3752         3        16  0.0001
 Hotelling-Lawley Trace     6.44535118    34.3752         3        16  0.0001
 Roy's Greatest Root        6.44535118    34.3752         3        16  0.0001

Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 10 Analysis using MANOVA statement

                       General Linear Models Procedure
                      Multivariate Analysis of Variance

Dependent Variable: Halothan

Source                  DF     Type III SS    Mean Square   F Value     Pr > F
INTERCEPT                1    832448.89474   832448.89474     88.26     0.0001

Error                   18    169780.10526     9432.22807

Dependent Variable: Co2

Source                  DF     Type III SS    Mean Square   F Value     Pr > F
INTERCEPT                1    68520.052632   68520.052632     13.19     0.0019

Error                   18    93524.947368    5195.830409

Dependent Variable: HxCO2

Source                  DF     Type III SS    Mean Square   F Value     Pr > F
INTERCEPT                1    3107.8421053   3107.8421053      0.41     0.5294

Error                   18   136033.157895   7557.3976608


Sleeping Dog Data: Johnson and Wichern (1992, p. 228) 11 Analysis using MANOVA statement

                       OBS    DOG    _NAME_      BEATRATE
                         1      1    HIGH_NOH       426
                         2      1    LOW_NOH        609
                         3      1    HIGH_H         556
                         4      1    LOW_H          600
                         5      2    HIGH_NOH       253
                         6      2    LOW_NOH        236
                         7      2    HIGH_H         392
                         8      2    LOW_H          395
                         9      3    HIGH_NOH       359
                        10      3    LOW_NOH        433
                        11      3    HIGH_H         349
                        12      3    LOW_H          357
                        13      4    HIGH_NOH       432
                        14      4    LOW_NOH        431
                        15      4    HIGH_H         522
                        16      4    LOW_H          600
                        17      5    HIGH_NOH       405
                        18      5    LOW_NOH        426
                        19      5    HIGH_H         513
                        20      5    LOW_H          513
                        21      6    HIGH_NOH       324
                        22      6    LOW_NOH        438
                        23      6    HIGH_H         507
                        24      6    LOW_H          539
                        25      7    HIGH_NOH       310
                        26      7    LOW_NOH        312
                        27      7    HIGH_H         410
                        28      7    LOW_H          456
                        29      8    HIGH_NOH       326
                        30      8    LOW_NOH        326
                        31      8    HIGH_H         350
                        32      8    LOW_H          504
                        33      9    HIGH_NOH       375
                        34      9    LOW_NOH        447
                        35      9    HIGH_H         547
                        36      9    LOW_H          548
                        37     10    HIGH_NOH       286
                        38     10    LOW_NOH        286
                        39     10    HIGH_H         403
                        40     10    LOW_H          422
                        41     11    HIGH_NOH       349
                        42     11    LOW_NOH        382
                        43     11    HIGH_H         473
                        44     11    LOW_H          497
                        45     12    HIGH_NOH       429
                        46     12    LOW_NOH        410
                        47     12    HIGH_H         488
                        48     12    LOW_H          547
                        49     13    HIGH_NOH       348
                        50     13    LOW_NOH        377