论文部分内容阅读
Detection of masking effects is a important issue in model diagnostics, This paper use stepwise local influence analysis to identify masking effects in dataset.Influential observations are detected step-by-step such that any highly influential observations identified in a previous step are removed from the perturbation in the next step.The process iterates until no further influential observations can be found.It is shown that this new method is very effective to identify the influential observations and have power to uncover the masking effects.The method is illustrated by several examples from regression models, linear mixed models and time series models.