CONFIDENCE-INTERVALS FOR KENDALL TAU

A simulation study was conducted to examine the performance of several confidence intervals (CIs) for Kendall's tau (t(xy)) under a variety of population conditions. Two normal population variables (N = 10,000) were transformed to have tau correlations, tau = 0,.19,.41, or .71. S amples (n = 10, 50, 200) were drawn from the transformed populations 2 000 times under each level of correlation, and accompanying CIs were c omputed on each sample. The results show that the CI for tau based on a consistent estimate of the variance of t(xy) has the best coverage a nd power among a number of alternatives. Kendall's t(xy) is unaffected by non-normality induced by monotonic transformations and with its co nsistent variance estimated from the sample, performs well under a wid e range of conditions.