A simple method for combining estimates to improve the overall error rates in classification

We present a new and easy-to-implement procedure for combining J≥2$$J\ge 2$$ different classifiers in order to develop more effective classification rules. The method works by finding nonparametric estimates of the class conditional expectation of a new observation (that has to be classified), conditional on the vector of J$$J$$ predicted values corresponding to the J$$J$$ individual classifiers. Here, we propose a data-splitting method to …