A Statistical Package for the Analysis of Directional Data
by
Ashis SenGupta
Applied Statistics Division, Indian Statistical Institute, Calcutta, India

Observations on angular displacements, orientations, directional popagations, periodic phenomena, etc. fall in the realm of directional data. Such data occur in practice in almost all spheres of applied sciences, e.g. agricultural, atmospheric, biological, defence, environmental, medical, social, physical, etc. sciences. Their analyses however require special attention since the methods advocated for usual linear data are not only often misleading but also not applicable to such directional data. Further, associated descriptive and inference procedures usually call for intensive computations which have posed a major problem for their implementations in practice. DDSTAP - A STatistical Package for the analysis of Directional Data is the first of its kind and aims to bridge this gap. A version of this was used successfully in 1998 in the National Winter School on Analysis of Directional Data at Osmania University. The present version incorporates many new procedures, the theory for several of which have been developed by either this author or that with his coauthors. A concise presentation of this package using simulated and real data will be given to demonstrate that it can now be readily accessed by both the theoreticians as well as the practitioners of circular data as a useful resource for their work.

Date received: November 20, 2000

Copyright © 2000 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # cafx-17.