These data are taken from Chapter 9 of "Experimental Design: Procedures for the Behavioral Sciences" 
by Roger E. Kirk, Third Edition, Brooks/Cole Publishing, 1995.  

The data are from an experiment to examine police officer attitudes toward minority groups after taking 
a human relations course.

Factor A is the type of patrol that an officer has: 1 is an 'upper class beat', 2 is a 'middle class beat',
 and 3 is an 'inner city beat'.

Factor B is the number of hours of human relations training: 1 is 5 hours, 2 is 10 hours, and 3 is 15 hours.

The response y is the attitude of the police officer toward minority groups following the human relations course.

Analyze the data to confirm the results below, and examine plots of the data to understand the results and 
to assess the appropriateness of the analysis.


Dependent Variable: y

                                               Sum of
       Source                      DF         Squares     Mean Square    F Value    Pr > F

       Model                        8     2970.000000      371.250000       5.94    <.0001

       Error                       36     2250.000000       62.500000

       Corrected Total             44     5220.000000


                        R-Square     Coeff Var      Root MSE        y Mean

                        0.568966      22.58770      7.905694      35.00000


       Source                      DF       SS            Mean Square    F Value    Pr > F

       a                            2      190.000000       95.000000       1.52    0.2324
       b                            2     1543.333333      771.666667      12.35    <.0001
       a*b                          4     1236.666667      309.166667       4.95    0.0028