KENDALL Subcommand (NPAR TESTS command)

NPAR TESTS KENDALL=varlist

KENDALL tests whether k related samples are from the same population. W is a measure of agreement among judges or raters, where each case is one judge’s rating of several items (variables). The output includes the mean rank for each variable in the Ranks table and the valid number of cases, Kendall’s W, chi-square, degrees of freedom, and probability in the Test Statistics table.

Syntax

The minimum specification is a list of two variables.

Operations

• The values of the k variables are ranked from 1 to k for each case, and the mean rank is calculated for each variable over all cases. Kendall’s W and a corresponding chi-square statistic are calculated, correcting for ties. In addition, a single test statistic is calculated for all variables.
• W ranges between 0 (no agreement) and 1 (complete agreement).

Example

DATA LIST /V1 TO V5 1-10.
BEGIN DATA
2 5 4 5 1
3 3 4 5 3
3 4 4 6 2
2 4 3 6 2
END DATA.
NPAR TESTS KENDALL=ALL.

• This example tests four judges (cases) on five items (variables V1 through V5).