Abstract
The presence of outliers in data influences not only in diagnostic model, but exceed to parameters estimation. So the goal of this paper is to make the autocorrelation coefficient robust against outliers to estimate parameters which will be robust depending on those coefficients. This goal is achieved by two suggestions depending on Fuzzy Logic which suggests estimation procedure to estimate autocorrelation coefficients called Semi-Fuzzy Pearson coefficient ,and suggests another one called Semi-Fuzzy Kendall , to use it to estimate the autocorrelation coefficients which will be used in parameter estimation.
