Optimal adaptive generalized Pólya urn design for multi-arm clinical trials

A class of optimal adaptive multi-arm clinical trial designs is proposed based on an extended generalized Pólya urn (GPU) model. The design is applicable to both the qualitative and quantitative responses and achieves, asymptotically, some pre-specified optimality criterion. Such criterion is specified by a functional of the response distributions and is implemented through the relationship between the design matrix and its first eigenvector. The asymptotic properties of the design are studied using the existing methods on GPU. Some examples for commonly used clinical designs are given as illustration.     

Parameter-based Fisher's information of orthogonal polynomials

The Fisher information of the classical orthogonal polynomials with respect to a parameter is introduced, its interest justified and its explicit expression for the Jacobi, Laguerre, Gegenbauer and Grosjean polynomials found.     

The one- and multi-sample problem for functional data with application to projective shape analysis

In this paper tests are derived for testing neighborhood hypotheses for the one- and multi-sample problem for functional data. Our methodology is used to generalize testing in projective shape analysis, which has traditionally involving data consisting of finite number of points, to the functional case. The one-sample test is applied to the problem of scene identification, in the context of the projective shape of a planar curve.     

Estimation of a tail index based on minimum density power divergence

In this paper, we consider the minimum density power divergence estimator for the tail index of heavy tailed distributions in strong mixing processes. It is shown that the estimator is consistent and asymptotically normal under regularity conditions. The simulation results demonstrate that the estimator is robust in the presence of outliers.     

A note on Srivastava and Hui’s tests of multivariate normality

The aim of the paper is to point out some imprecision in Srivastava and Hui’s tests for multivariate normality. A correction for their tests is proposed.     

Bivariate distributions characterized by one family of conditionals and conditional percentile or mode functions

It is well known that full knowledge of all conditional distributions will typically serve to completely characterize a bivariate distribution. Partial knowledge will often suffice. For example, knowledge of the conditional distribution of X given Y and the conditional mean of Y given X is often adequate to determine the joint distribution of X and Y. In this paper, we investigate the extent to which a conditional percentile function or a conditional mode function (of Y given X), together with knowledge of the conditional distribution of X given Y will determine the joint distribution. Finally, using this methodology a new characterization of the classical bivariate normal distribution is given.     

Some notes on multivariate generalized Pareto distributions

The investigation of multivariate generalized Pareto distributions (GPDs) has begun only recently and there are slightly varying definitions of GPDs available. In this article we investigate the one from Section 5.1 of Falk et al. [Laws of Small Numbers: Extremes and Rare Events, second ed., Birkhäuser, Basel, 2004], which does not differ in the area of interest from those of other authors. We first give an interpretation of the case of independence in terms of the peaks-over-threshold approach. This case is also used in dimension d=3 by Falk et al. [Laws of Small Numbers: Extremes and Rare Events, second ed., Birkhäuser, Basel, 2004] as a counterexample to show that GP functions are not necessarily distribution functions on their entire support. We generalize this counterexample to an arbitrary dimension d≥3 and demonstrate also that other GP functions show this behavior. Finally we show that different GPDs can lead to the same conditional probability measure in the area of interest.     

On discrete time ergodic filters with wrong initial data

For a class of non-uniformly ergodic Markov chains (X _n ) satisfying exponential or polynomial beta-mixing, under observations (Y _n ) subject to an IID noise with a positive density, it is shown that wrong initial data is forgotten in the mean total variation topology, with a certain exponential or polynomial rate.     

Learning from dependent observations

In most papers establishing consistency for learning algorithms it is assumed that the observations used for training are realizations of an i.i.d. process. In this paper we go far beyond this classical framework by showing that support vector machines (SVMs) only require that the data-generating process satisfies a certain law of large numbers. We then consider the learnability of SVMs for α-mixing (not necessarily stationary) processes for both classification and regression, where for the latter we explicitly allow unbounded noise.     

Shrinkage structure in biased regression

Biased regression is an alternative to ordinary least squares (OLS) regression, especially when explanatory variables are highly correlated. In this paper, we examine the geometrical structure of the shrinkage factors of biased estimators. We show that, in most cases, shrinkage factors cannot belong to [0,1] in all directions. We also compare the shrinkage factors of ridge regression (RR), principal component regression (PCR) and partial least-squares regression (PLSR) in the orthogonal directions obtained by the signal-to-noise ratio (SNR) algorithm. In these directions, we find that PLSR and RR behave well, whereas shrinkage factors of PCR have an erratic behaviour.