Summary
A simple method of testing whether a particular period is of use in forecasting is explained. The method was first tested on artificial sets of data in two of which random variations were superposed upon a periodic variation, and in the remaining three there were no periodicities at all. In the former case the periodicity tested was found to be significant, while in the latter the periodicity was not significant. When the same method was applied to see whether the 23-year period, suggested by C. G. Abbot, would be of use in forecasting annual rainfall at Madras and Nagpur, it was found that the period is not of use.
Similar content being viewed by others
References.
C. G. Abbot, “Sun-Spots and Weather,”Simithsonian Misc. Collections,87, No. 18.
S. R. Savur and S. Gopal Rao,Ind. Met. Dept. Sci. Notes, 5, No. 49.
C. W. B. Normand,Q.J.R. Met. Soc., 1932,58, 3–10.
S. R. Savur, “On the ‘Performance Test’ in Statistics,”Ind. Jour. Phys., 7, 27–34.
R. A. Fisher,Statistical Methods for Research Workers.
Sankhya, 1, Parts 2 and 3, pp. 303–328.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Savur, S.R. A simple test of value of a particular period inforecasting. Proc. Indian Acad. Sci. (Math. Sci.) 2, 336–341 (1935). https://doi.org/10.1007/BF03035831
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF03035831