We propose a new nonlinear classification method based on a Bayesian "sum-of-trees" model, the Bayesian Additive Classification Tree (BACT), whichextends the Bayesian Additive Regression Tree (BART) method into the classification context. Like BART, the BACT is a Bayesian nonparametric...

This paper presents a new method for spatially adaptive local likelihood estimation which applies to a broad class of nonparametric models, including the Gaussian, Poisson and binary response models. The main idea of the method is given a sequence of local likelihood estimates ("weak"...

This paper investigates industry classification systems. During the last 50 yearsthere has been a considerable discussion of problems regarding the classification of economic data by industries. From my perspective, the central point of each classification is to determine a balance between...

We derive the decomposition of the ranked continuous semimartingales i.e. order-statistics processes. We apply it to portfolios generated by functions of the ranked market weights. Thus we generalize recent results of Fernholz.