Abstract

Watson (1962) introduced a distribution-free test of the null hypothesis that two samples come from the same population. The computed statistic, U , depends on the relative ranks of the observations in the two samples, and not on the starting point of the measurement scale. Thus, while it may also be used for data measured on a linear scale, the test is especially useful for data on a circle, for which conventional hypothesis testing is inappropriate. Common data from a circular scale of measurement are compass directions or clock times; parametric testing for such data is possible (see Batschelet, 1965, 1972; Mardia, 1972; Zar, 1974, 1976). Watson's nonparametric test is described in Batschelet (1965, pp. 35·36), Mardia (1972, pp. 201-203), and Zar (1974, pp. 324.326). A computer program has been developed that performs Watson's (1962) calculation of U , appro, priate for either nontied data or data tied within and/or between samples. The most extensive tables of critical values of U are in Zar (1974, pp.575-576). Stephens (1965) gives Pearson curve approximations for some large sample sizes. For large samples, a normal deviate may be calculated as:

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.