Enter your search terms Submit search form
	Web pdp-10.trailing-edge.com

SUBROUTINE WTEST

PURPOSE
   TEST DEGREE OF ASSOCIATION AMONG A NUMBER OF VARIABLES BY
   THE KENDALL COEFFICIENT OF CONCORDANCE

USAGE
   CALL WTEST(A,R,N,M,WA,W,CS,NDF,NR)

DESCRIPTION OF PARAMETERS
   A   - INPUT MATRIX, N BY M, OF ORIGINAL DATA
   R   - OUTPUT MATRIX, N BY M, OF RANKED DATA.SMALLEST VALUE
	 IS RANKED 1, LARGEST IS RANKED N. TIES ARE ASSIGNED
	 AVERAGE OF TIED RANKS
   N   - NUMBER OF VARIABLES
   M   - NUMBER OF CASES
   WA  - WORK AREA VECTOR OF LENGTH 2*M
   W   - KENDALL COEFFICIENT OF CONCORDANCE(OUTPUT)
   CS  - CHI-SQUARE (OUTPUT)
   NDF - NUMBER OF DEGREES OF FREEDOM (OUTPUT)
   NR  - CODE, 0 FOR UNRANKED DATA IN A, 1 FOR RANKED DATA
	 IN A (INPUT)

REMARKS
   CHI-SQUARE IS SET TO ZERO IF M IS 7 OR SMALLER

SUBROUTINES AND FUNCTION SUBPROGRAMS REQUIRED
   RANK
   TIE

METHOD
   DESCRIBED IN S. SIEGEL, 'NONPARAMETRIC STATISTICS FOR THE
   BEHAVIORAL SCIENCES', MCGRAW-HILL, NEW YORK, 1956,
   CHAPTER 9