Regression diagnostics for response transformations in a partial linear model

摘要: In the transformation of response variable in partial linear models outliers can cause a bad effect on estimating parameter, just as models. To solve this problem processes parameter and detecting are needed, but have difficulties to be performed due arbitrariness nonparametric function included model. study, through estimation outlier detection methods such sequential test maximum trimmed likelihood estimation, for transforming robust suggested. The proposed verified compared their effectiveness by simulation study examples.