ST 590G -- Computation for Data Analysis

  Third Assignment -- due Thursday, 27 October 2011

  We'll soon look at the permutation test for the two sample t-test.
  Permutation tests or p-values are based on permuting the association
  between variables.  In the two-sample problem or ANOVA, we're permuting
  the group labels.  We seek the distribution of the statistic when there
  is no effect -- the group labels are meaningless -- all groups are the
  same.  

  Your assignment is to write a macro to compute permutation p-values
  for correlations.  Here you will need to permute the order of one of
  the two variables in the dataset.  You can either use PROC CORR to 
  compute the correlations, or notice that the distribution of the 
  sample correlation is linearly related to the distribution of 
  SUM(i) xi*yi so that you could do that calculation with PROC MEANS.

  The arguments to your macro should be 
    a) the name of the dataset
    b) the names of the two variables
    c) the number of replications.
  
  Test your macro on the casino data in the file 'oct20.ex2.dat' in the
  oct11 directory.
  
  ***Also, email your macro code to be as flat file attachment.***