The Minkowski content L0(G) of a body G ⊂ Rd represents the boundary length (for d = 2) or the surface area (for d = 3) of G. A method for estimating L0(G) is proposed. It relies on a nonparametric estimator based on the information provided by a random sample (taken on a rectangle containing G) in which we are able to identify whether every point is inside or outside G. Some theoretical properties concerning strong consistency, L1-error and convergence rates are obtained. A practical application to a problem of image analysis in cardiology is discussed in some detail. A brief simulation study is providedSupported in part by Spanish Grant MTM2004-00098, MTM2005-00820 and PGIDIT06PXIB207009P

We consider the problem of estimating the boundary of a compact set S ⊂ ℝ d from a random sample of points taken from S. We use the Devroye-Wise estimator which is a union of balls centred at the sample points with a common radius (the smoothing parameter in this problem). A universal consistency result, with respect to the Hausdorff metric, is proved and convergence rates are also obtained under broad intuitive conditions of a geometrical character. In particular, a shape condition on S, which we call expandability, plays an important role in our results. The simple structure of the considered estimator presents some practical advantages (for example, the computational identification of the boundary is very easy) and makes this problem quite close to some basic issues in stochastic geometry.

This paper presents the R package alphahull which implements the α-convex hull and the α-shape of a finite set of points in the plane. These geometric structures provide an informative overview of the shape and properties of the point set. Unlike the convex hull, the α-convex hull and the α-shape are able to reconstruct non-convex sets. This flexibility make them specially useful in set estimation. Since the implementation is based on the intimate relation of theses constructs with Delaunay triangulations, the R package alphahull also includes functions to compute Voronoi and Delaunay tesselations. The usefulness of the package is illustrated with two small simulation studies on boundary length estimation.

Given an unknown function (e.g. a probability density, a regression function, . . .) f and a constant c, the problem of estimating the level set L(c) = {f ≥ c} is considered. This problem is tackled in a very general framework, which allows f to be defined on a metric space different from R d . Such a degree of generality is motivated by practical considerations and, in fact, an example with astronomical data is analyzed where the domain of f is the unit sphere. A plug-in approach is followed; that is, L(c) is estimated by L n (c) = {f n ≥ c}, where f n is an estimator of f . Two results are obtained concerning consistency and convergence rates, with respect to the Hausdorff metric, of the boundaries ∂L n (c) towards ∂L(c). Also, the consistency of L n (c) to L(c) is shown, under mild conditions, with respect to the L 1 distance. Special attention is paid to the particular case of spherical data.

The identification of peaks or maxima in probability densities, by mode testing or bump hunting, has become an important problem in applied fields. This task has been approached in the statistical literature from different perspectives, with the proposal of testing procedures which are based on kernel density estimators or on the quantification of excess mass. However, none of the existing proposals provides a satisfactory performance in practice. In this work, a new procedure which combines the previous approaches (smoothing and excess mass) is presented and compared with the existing methods, showing a superior behaviour. A real data example on philatelic data is also included for illustration purposes.