The identification of influential subsets in regression using a fuzzy clustering strategy

A fuzzy clustering strategy is used to identify subsets of influential obse rvations in regression, As part of the fuzzy clustering strategy, the analy st can explore the uniqueness of selected subsets and the degree of belongi ng of observations to selected subsets. This is accomplished by either vary ing a fuzzy parameter or the number of clusters. Once the observations or s ubsets have been identified, the analyst can then compute regression diagno stics to confirm their degree of influence in regression. Bootstrapping and high-breakdown procedures were used to confirm the influence of the previo usly identified subsets. This fuzzy clustering strategy is applied to the m odified data on wood-specific gravity and an augmented production dataset. Both datasets have been previously presented in the literature.