For high-dimensional data, most feature-selection methods, such as SIS and the lasso, involve ranking and selecting features individually. These methods do not require many computational resources, but they ignore feature interactions. A simple recursive approach, which, without requiring many...

In standard parametric classifiers, or classifiers based on nonparametric methods but where there is an opportunity for estimating population densities, the prior probabilities of the respective populations play a key role. However, those probabilities are largely ignored in the construction of...

In this paper we propose simple, general tiered classifiers for relatively complex data. Empirical studies on real and simulated data show that three two-tier classifiers, which are respective extensions of linear discriminant analysis, linear logistic regression and support vector machines, can...

It is shown that the zeros of the derivatives of the Cauchy density occur at quantiles that are regularly spaced in terms of probability. A few non-statistical consequences are obtained and the derivatives of the Student-t densities are give closed form expressions.

We describe a unified approach to the construction of confidence bands in nonparametric density estimation and regression. Our techniques are based on interpolation formulae in numerical differentiation, and our arguments generate a variety of bands depending on the assumptions one is prepared...

The interpretation of generative, discriminative and hybrid approaches to classification is discussed, in particular for the generative-discriminative tradeoff (GDT), a hybrid approach. The asymptotic efficiency of the GDT, relative to that of its generative or discriminative counterpart, is...

The aims of this short note are two-fold. First, it shows that, for a random variable X, the area under the curve of its folded cumulative distribution function equals the mean absolute deviation (MAD) from the median. Such an equivalence implies that the MAD is the area between the cumulative...

Network models are widely used to represent relations between interacting units or actors. Network data often exhibit transitivity, meaning that two actors that have ties to a third actor are more likely to be tied than actors that do not, homophily by attributes of the actors or dyads, and...