Jackknife-After-Bootstrap in Fuzzy Regression Modeling

Jackknife-After-Bootstrap in Fuzzy Regression Modeling

There are many endeavors to exhibit a fuzzy regression model which can, in a logical sense, improve goodness of fit (GOF) and power of prediction. Considering different well-known approaches of fuzzy regression modeling (FRM), including possibility, least squares and other combined methods, we propose a method to improve the GOF and prediction in FRM. Specifically, we introduce a resampling procedure to improve the estimation of the regression coefficients. Numerical studies demonstrate the superior performance of the proposed resampling procedure over usual ones..

There are many endeavors to exhibit a fuzzy regression model which can, in a logical sense, improve goodness of fit (GOF) and power of prediction. Considering different well-known approaches of fuzzy regression modeling (FRM), including possibility, least squares and other combined methods, we propose a method to improve the GOF and prediction in FRM. Specifically, we introduce a resampling procedure to improve the estimation of the regression coefficients. Numerical studies demonstrate the superior performance of the proposed resampling procedure over usual ones..