Journal of Data Science

Abstract: Constrained general linear models (CGLMs) have wide applications in practice. Similar to other data analysis, the identification of influential obser vations that may be potential outliers is an important step beyond in CGLMs. We develop local influence approach for detecting influential observations in CGLMs. The procedure makes use of the normal curvature and the direction achieving the maximum curvature to assess the local influences of minor perturbation of CGLMs. An illustrative example with a real data set is also reported.

In semiparametric regression it is of interest to detect anomalous observations that exert an unduly large influence on the parameter’s esti-mate and fitted values. Usually the existence of influential observations is complicated by the presence of collinearity. However no method of influ-ence diagnostics available for the possible effects that collinearity can have on the influence of an observation on the estimates of parametric and non-parametric component of semiparametric regression models. In this paper we show when Liu estimators are used to mitigate the effects of collinearity the influence of some observations can be drastically modified. We propose a case deletion formula to detect influential points in Liu estimators of semi-parametric regression models . As an illustrative example a real data set are analysed.