The ALLELE Procedure

OUTSTAT= Data Set

The OUTSTAT= data set contains the following variables:

  • the BY variables, if any

  • Locus1 and Locus2, which contain the pair of markers for which the disequilibrium statistics are calculated

  • NIndiv, which contains the number of individuals that have been genotyped at both the markers listed in Locus1 and Locus2 (that is, the number of individuals that have no missing alleles for the two loci)

  • Test, which indicates which disequilibrium test is performed, HWE for individual markers (when Locus1 and Locus2 contain the same value) or LD for marker pairs

  • ChiSq, which contains the chi-square statistic for testing for disequilibrium. If Locus1 and Locus2 contain the same marker, the test is for HWE within that locus. Otherwise, the test is for linkage disequilibrium between the two loci.

  • DF, which contains the degrees of freedom for the chi-square test

  • ProbChi, which contains the $p$-value for the chi-square test

  • ProbEx, which contains an estimate of the exact $p$-value for testing the pair of markers in Locus1 and Locus2 for disequilibrium. This variable is included in the OUTSTAT= data set only when the PERMS= parameter in the PROC ALLELE statement is a positive integer and HAPLO=EST is not specified.