McNemar test
                         The FREQ Procedure
                         Table of r1 by r2
                r1        r2
                Frequency|F       |NF      |  Total
                ---------+--------+--------+
                F        |      2 |      9 |     11
                ---------+--------+--------+
                NF       |      5 |      6 |     11
                ---------+--------+--------+
                Total           7       15       22

                  Statistics for Table of r1 by r2
                          McNemar's Test
                      -----------------------
                      Statistic (S)    1.1429
                      DF                    1
                      Pr > S           0.2850

                      Simple Kappa Coefficient
                  --------------------------------
                  Kappa                    -0.2727
                  ASE                       0.1911
                  95% Lower Conf Limit     -0.6472
                  95% Upper Conf Limit      0.1018

                           McNemar test
                         The FREQ Procedure
               Summary Statistics for proce by result
                       Controlling for batch
    Cochran-Mantel-Haenszel Statistics (Based on Table Scores)
  Statistic    Alternative Hypothesis DF    Value      Prob
  ---------------------------------------------------------
      1        Nonzero Correlation     1   1.1429    0.2850
      2        Row Mean Scores Differ  1   1.1429    0.2850
      3        General Association     1   1.1429    0.2850

          Case-Control      Mantel-Haenszel        1.8000
            (Odds Ratio)    Logit **               1.8734

   Type of Study     Method          95% Confidence Limits
   -------------------------------------------------------
   Case-Control      Mantel-Haenszel   0.6032       5.3709
     (Odds Ratio)    Logit **          0.5588       6.2808

 ** Logit estimators use a correction of 0.5 in every cell
   of those tables that contain a zero. Tables with a zero
   row or a zero column are not included in computing the
    logit estimators.

                        Breslow-Day Test for
                   Homogeneity of the Odds Ratios
                   ------------------------------
                   Chi-Square             26.8328
                   DF                          13
                   Pr > ChiSq              0.0131


                       Total Sample Size = 44
              Fake comparisons of McNemar and Pearson
------------------------- ex=1 -------------------------------
                          Table of a by b
                a         b
                Frequency|
                Expected |       0|       1|  Total
                ---------+--------+--------+
                       0 |    100 |     50 |    150
                         |    100 |     50 |
                ---------+--------+--------+
                       1 |     50 |     25 |     75
                         |     50 |     25 |
                ---------+--------+--------+
                Total         150       75      225

                   Statistics for Table of a by b
       Statistic                     DF       Value      Prob
       ------------------------------------------------------
       Chi-Square                     1      0.0000    1.0000
                          McNemar's Test
                      -----------------------
                      Statistic (S)    0.0000
                      DF                    1
                      Pr > S           1.0000
------------------------- ex=2 -------------------------------
                          Table of a by b
                a         b
                Frequency|
                Expected |       0|       1|  Total
                ---------+--------+--------+
                       0 |    100 |     50 |    150
                         |  112.5 |   37.5 |
                ---------+--------+--------+
                       1 |     50 |      0 |     50
                         |   37.5 |   12.5 |
                ---------+--------+--------+
                Total         150       50      200
                   Statistics for Table of a by b
       Statistic                     DF       Value      Prob
       ------------------------------------------------------
       Chi-Square                     1     22.2222    <.0001
                          McNemar's Test
                      -----------------------
                      Statistic (S)    0.0000
                      DF                    1
                      Pr > S           1.0000
------------------------- ex=3 -------------------------------
                          Table of a by b
                a         b
                Frequency|
                Expected |       0|       1|  Total
                ---------+--------+--------+
                       0 |    200 |     50 |    250
                         |    200 |     50 |
                ---------+--------+--------+
                       1 |    100 |     25 |    125
                         |    100 |     25 |
                ---------+--------+--------+
                Total         300       75      375
                   Statistics for Table of a by b
       Statistic                     DF       Value      Prob
       ------------------------------------------------------
       Chi-Square                     1      0.0000    1.0000
                           McNemar's Test
                      ------------------------
                      Statistic (S)    16.6667
                      DF                     1
                      Pr > S            <.0001

                      Poisson regression model

                        The GENMOD Procedure

                         Model Information

                  Data Set              WORK.FALLS
                  Distribution             Poisson
                  Link Function                Log
                  Dependent Variable         falls

              Number of Observations Read          12
              Number of Observations Used          12

                      Class Level Information
Class Levels   Values
month     12   Apr Aug Dec Feb Jan Jul Jun Mar May Nov Oct Sep

               Criteria For Assessing Goodness Of Fit
  Criterion                     DF           Value    Value/DF
  Deviance                       0          0.0000       .
  Scaled Deviance                0          0.0000       .
  Pearson Chi-Square             .          0.0000       .
  Scaled Pearson X2              .          0.0000       .
  Log Likelihood                        79364.9865
  Full Log Likelihood                     -53.0481
  AIC (smaller is better)                 130.0962
  AICC (smaller is better)                   .
  BIC (smaller is better)                 135.9151

Algorithm converged.
       Analysis Of Maximum Likelihood Parameter Estimates
                        Standard Wald 95% Conf-     Wald    Pr >
Parameter   DF Estimate  Error   idence Limits Chi-Square   ChiSq
Intercept    1   7.0157 0.0300   6.9570 7.0744 54831.3   <.0001
month   Apr  1   0.0107 0.0423  -0.0721 0.0935    0.06   0.7998
month   Aug  1  -0.0136 0.0425  -0.0969 0.0698    0.10   0.7498
month   Dec  1   0.0584 0.0418  -0.0235 0.1403    1.96   0.1620
month   Feb  1  -0.0745 0.0432  -0.1592 0.0101    2.98   0.0844
month   Jan  1   0.0318 0.0420  -0.0506 0.1142    0.57   0.4493
month   Jul  1  -0.0018 0.0424  -0.0849 0.0813    0.00   0.9662
month   Jun  1  -0.0126 0.0425  -0.0960 0.0707    0.09   0.7661
month   Mar  1  -0.0310 0.0427  -0.1147 0.0527    0.53   0.4679
month   May  1   0.0248 0.0421  -0.0577 0.1074    0.35   0.5555
month   Nov  1  -0.1090 0.0436  -0.1944 0.0236    6.25   0.0124
month   Oct  1  -0.0319 0.0427  -0.1156 0.0518    0.56   0.4548
month   Sep  0   0.0000 0.0000   0.0000 0.0000   .           .
Scale        0   1.0000 0.0000   1.0000 1.0000
NOTE: The scale parameter was held fixed.

              LR Statistics For Type 1 Analysis
  Source         Deviance        DF     Chi-Square Pr>ChiSq
  Intercept       24.9274
  month            0.0000        11      24.93     0.0093
                Poisson regression model with offset

                        The GENMOD Procedure
                         Model Information
                  Data Set              WORK.FALLS
                  Distribution             Poisson
                  Link Function                Log
                  Dependent Variable         falls
                  Offset Variable               lt

         Analysis Of Maximum Likelihood Parameter Estimates

                                Standard   Wald 95% Confidence
  Parameter     DF   Estimate      Error          Limits
  Intercept      1     3.6145     0.0300     3.5558     3.6732
  month   Apr    1     0.0107     0.0423    -0.0721     0.0935
  month   Aug    1    -0.0463     0.0425    -0.1297     0.0370
  month   Dec    1     0.0256     0.0418    -0.0562     0.1075
  month   Feb    1    -0.0055     0.0432    -0.0902     0.0791
  month   Jan    1    -0.0010     0.0420    -0.0834     0.0814
  month   Jul    1    -0.0346     0.0424    -0.1177     0.0485
  month   Jun    1    -0.0126     0.0425    -0.0960     0.0707
  month   Mar    1    -0.0638     0.0427    -0.1475     0.0199
  month   May    1    -0.0080     0.0421    -0.0905     0.0746
  month   Nov    1    -0.1090     0.0436    -0.1944    -0.0236
  month   Oct    1    -0.0647     0.0427    -0.1484     0.0190
  month   Sep    0     0.0000     0.0000     0.0000     0.0000
  Scale          0     1.0000     0.0000     1.0000     1.0000

             Poisson regression model to get goodness of fit

               Criteria For Assessing Goodness Of Fit
Criterion                  DF           Value        Value/DF
Deviance                   11         24.9274          2.2661
Scaled Deviance            11         24.9274          2.2661
Pearson Chi-Square         11         24.7143          2.2468
Scaled Pearson X2          11         24.7143          2.2468
  Log Likelihood                        79352.5228
  Full Log Likelihood                     -65.5118
  AIC (smaller is better)                 133.0236
  AICC (smaller is better)                133.4236
  BIC (smaller is better)                 133.5085

                        Chi-square approach

                         The FREQ Procedure

                                Test  Cumulative   Cumulative
 month   Frequency    Percent Percent  Frequency     Percent
 -----------------------------------------------------------
 Apr         1126       8.52    8.33      1126        8.52
 Aug         1099       8.32    8.33      2225       16.84
 Dec         1181       8.94    8.33      3406       25.77
 Feb         1034       7.82    8.33      4440       33.60
 Jan         1150       8.70    8.33      5590       42.30
 Jul         1112       8.41    8.33      6702       50.71
 Jun         1100       8.32    8.33      7802       59.03
 Mar         1080       8.17    8.33      8882       67.21
 May         1142       8.64    8.33     10024       75.85
 Nov          999       7.56    8.33     11023       83.41
 Oct         1079       8.16    8.33     12102       91.57
 Sep         1114       8.43    8.33     13216      100.00


                          Chi-Square Test
                     for Specified Proportions

                       Chi-Square    24.7143
                       DF                 11
                       Pr > ChiSq     0.0100

                        Sample Size = 13216