An algorithm for autocorrelation analysis of time series data was presented and compared with two alternative computational methods. The algorithm was based on continuous variance adjustment following withdrawal of an element from the lagged series. The algorithm not only reduces the number of computations during the repeated passes through the data vector but also avoids a dampening effect toward the end of the series.
Get full access to this article
View all access options for this article.
References
1.
Denton, F. H. and Phillips, W.Some patterns in the history of violence. Journal of Conflict Resolution, 1968, 12, 182-195.
2.
Guilford, J. P.Fundamental statistics in psychology and education. (4th ed.). New York: McGraw-Hill, 1965.
3.
Krus, D. J. and Blackman, H. S.Time-scale factor as related to theories of societal change. Psychological Reports, 1980, 46, 95-102.
4.
Krus, D. J. and Ceurvorst, R. W.Computed assisted construction of variable norms. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1978, 38, 815-818.
5.
Makridakis, S. and Wheelwright, S. C.Interactive forecasting: Univariate and multivariate methods. (2nd ed.). San Francisco: Holden-Day, 1978.
6.
McCleary, R. and Hay, R. A.Applied time series analysis for the social sciences. Beverly Hills, Ca: Sage, 1980.
7.
Moyal, J. E.The distribution of wars in time . Journal of the Royal Statistical Society, 1949, 112, 446-458.
8.
Southworth, R. W.Autocorrelation and spectral analysis. In A. Ralston and H. S. Wilf (Eds.) Mathematical methods for digital computers. New York: Wiley, 1960.
9.
Veldman, D. J.Fortran programming for the behavioral sciences. New York: Holt, Rinehart and Winston, 1967.
10.
Wright, Q.A study of war. Chicago: University of Chicago Press, 1942.
