ON SMOOTHING TIME SERIES DATA USING A CLASSICAL MOVING AVERAGE FORMULA

by Khogali A. Khogali, and John. W. Odhiambo.

Abstract: Considering the Least Squared Method or the weighted moving average filter for smoothing a polynomial trend of the decomposed classical model of time series realization, this article attempts to provides an alternative filters that link the degree of the poynomial to the number of terms operating in the moving average formula. Their Statistical properties were examined. Illusterations using regional meteorological data from three East African countries were reported.

Key Words: Trend, Linear time invariant moving average filter,Differencing and unbiased estimater

Authors:
Khogali A. Khogali, khogh@hotmail.com
John. W. Odhiambo, mathuon@iconnect.ke

Editor: Hatemi J. Abdulnasser, Abdulnasser.Hatemi-J@ish.his.se

READING THE ARTICLE: You can read the article in portable document (.pdf) format (135085 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2529 times since July 24, 2006.


Return to the InterStat Home Page.