BayesProject: Fast computation of a projection direction for multivariate changepoint detection

Statistics and Computing - This article focuses on the challenging problem of efficiently detecting changes in mean within multivariate data sequences. Multivariate changepoints can be detected by...     

Implementing Monte Carlo tests with p-value buckets

Software packages usually report the results of statistical tests using p-values. Users often interpret these values by comparing them with standard thresholds, for example, 0.1, 1, and 5%, which is sometimes reinforced by a star rating (***, **, and *, respectively). We consider an arbitrary statistical test whose p-value p is not available explicitly, but can be approximated by Monte Carlo samples, for example, by bootstrap or permutation tests. The standard implementation of such tests usually draws a fixed number of samples to approximate p. However, the probability that the exact and the approximated p-value lie on different sides of a threshold (the resampling risk) can be high, particularly for p-values close to a threshold. We present a method to overcome this. We consider a finite set of user-specified intervals that cover [0, 1] and that can be overlapping. We call these p-value buckets. We present algorithms that, with arbitrarily high probability, return a p-value bucket containing p. We prove that for both a bounded resampling risk and a finite runtime, overlapping buckets need to be employed, and that our methods both bound the resampling risk and guarantee a finite runtime for such overlapping buckets. To interpret decisions with overlapping buckets, we propose an extension of the star rating system. We demonstrate that our methods are suitable for use in standard software, including for low p-value thresholds occurring in multiple testing settings, and that they can be computationally more efficient than standard implementations.     

Public Support for Rehabilitation Programs: The Analysis of U.S. Disability Policy

Although political scientists have displayed relatively little interest in research on disability thus far, a brief review of major issues in rehabilitation in the United States indicates the contribution that policy analysts can make to the study of this subject. This opportunity is enhanced by a recent shift in the definition of disability from a medical orientation, which emphasizes functional impairments, and from an economic approach, which stresses vocational limitations, to a socio-political perspective, which regards disability as the product of interactions between individuals and the environment. The latter definition has become the foundation for a new 'minority-group' model of disability that is challenging the traditional 'functional-limitations' paradigm and that might profitably be utilized in future research.     

The Politics of Physical Differences: Disability and Discrimination

Although a "minority-group" model has emerged to challenge the traditional dominance of the "functional-limitations" paradigm for the study of disability, research on attitudes toward disabled people has not produced a theoretical orientation that reflects these developments. This paper proposes a new conceptual framework, based on the fundamental values of personal appearance and individual autonomy, for assessing the "aesthetic" and "existential" anxiety aroused by persons with disabilities. Investigations using this perspective might contribute to determining the attitudinal foundations of the competing models that are dividing research on disability.     

Standard Errors for Elasticities: A Comparison of Bootstrap and Asymptotic Standard Errors

This article compares two methods of deriving standard errors for elasticities in a linear expenditure demand system with first-order autoregressive errors. The first is the ordinary Taylor series method and the second is Efron's bootstrap. In an example problem, these two methods yielded similar values for the standard errors, with the exception of the income elasticity standard errors, for which the asymptotic standard errors were apparently too large by a factor of two.     

Existence of Maximum Likelihood Estimates for Multi-dimensional Exponential Families

This paper deals with the existence of maximum likelihood estimators for multi-dimensional exponential families, including curved exponential families. It first gives an algorithm for determining the MLE from the data. Then it establishes that when the parameter set is either open or relatively closed in the natural parameter set, the MLE of the parameter exists in the sense of Hoffmann-Jorgensen.     

The control function in major German companies

Control as a specific managerial function is receiving increasing recognition. This article presents different concepts of control which have developed in the U.S.A. over many years and quite recently in the Federal Republic of Germany. Examples are given of control concepts as put into practice by leading German industrial enterprises.     

New Developments in Statistical Computing: New Bias Evaluation Features of EXPLOR—A Program for Assessing Experimental Design Properties

Longitudinal investigations play an increasingly prominent role in biomedical research. Much of the literature on specifying and fitting linear models for serial measurements uses methods based on the standard multivariate linear model. This article proposes a more flexible approach that permits specification of the expected response as an arbitrary linear function of fixed and time-varying covariates so that mean-value functions can be derived from subject matter considerations rather than methodological constraints. Three families of models for the covariance function are discussed: multivariate, autoregressive, and random effects. Illustrations demonstrate the flexibility and utility of the proposed approach to longitudinal analysis.