In fitting parametric or nonparametric regression models, one or a few observations may have undue effects on estimators. These influential observations are precisely detected by the well-known influence measure, Cook's distance. In this paper, we introduce a type of Cook's distance for one or a...

While most research concerning thermoelectrics has focused on the enhancement of the thermoelectric figure of merit, zT, the $/W is a direct indication of its practical use. It is suggested that in the conventional device architecture, it is better to reduce thermoelectric material consumption...

We present a version of Cook's distance that is applicable to groups of observations in spline smoothing and can be used for outlier detection when masking is present. We express them as functions of the basic diagnostic building blocks: residuals and leverage values. An example based on a real...