JFET_V7_N3_RP3 Elimination of Non-monotonicity of Variance Estimate in Weighted Overlap Segment Averaging Moram venkatanarayana Mahaboob Pasha Jayachandra Prasad Talari Journal on Future Engineering and Technology 2230 – 7184 7 3 35 42 Circular Overlap, Non-Monotonic, Periodogoram Weighted Averaging, Spectral Leakage, Spectral Density Estimation The most popular method of nonparametric spectral density is the Weighted Segment Overlap Averaging (WOSA). Because of the unequal weighting of observed samples, its variance estimate is non monotonic function of fraction of overlap. Simple theoretical analysis of the mean and the variance of the WOSA have been presented nicely. Selecting the optimal fraction of overlap, which minimizes the variance, is in general difficult since it depends on the window used. The main objective in this paper is to avoid the nonmonotonic behavior of the variance for the Welch power spectrum estimator (PSE) by introducing circular overlap to the Welch method. With slight modification, the mean and the variance of Welch Circular Overlap Segment Averaging (WCOSA) have been presented. With the help of simulation, the performance evaluations of WOSA and WCOSA have been presented and finally, it is observed that the variance estimate based on WCOSA is a monotonically decreasing function of the fraction of overlap. February - April 2012 Copyright © 2012 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1799