Moving-weighted-average smoothing extended to the extremities of the data. II. Methods

Abstract

The use of a moving weighted average to smooth equally spaced observational data does not produce smoothed values for arguments too near the extremities of the data. This is a serious disadvantage of the method and may have discouraged its use to some extent. In the first paper of this series it was argued that there is a single preferred method of extending the graduation to the ends of the data set, and the theory of that method was developed. This paper focuses on the computational aspects: abbreviated procedures are described and tables are provided to facilitate the calculations. The preferred method is compared, numerically and otherwise, with other plausible methods of extending the graduation.

Sponsored by the United States Army under Contract No. DAAG29-75-0024.

Sponsored by the United States Army under Contract No. DAAG29-75-0024.

Notes

Sponsored by the United States Army under Contract No. DAAG29-75-0024.