Comments on a simple test for new better than used in expectation1 by borges,proschan and rodrigues

Procedures and tables are givenfor construction and selection of continuous sampling plans of the type CSP-2 for a given pair of conditions.     

Multivariate outbreak detection

Online monitoring is needed to detect outbreaks of diseases such as influenza. Surveillance is also needed for other kinds of outbreaks, in the sense of an increasing expected value after a constant period. Information on spatial location or other variables might be available and may be utilized. We adapted a robust method for outbreak detection to a multivariate case. The relation between the times of the onsets of the outbreaks at different locations (or some other variable) was used to determine the sufficient statistic for surveillance. The derived maximum-likelihood estimator of the outbreak regression was semi-parametric in the sense that the baseline and the slope were non-parametric while the distribution belonged to the one-parameter exponential family. The estimator was used in a generalized-likelihood ratio surveillance method. The method was evaluated with respect to robustness and efficiency in a simulation study and applied to spatial data for detection of influenza outbreaks in Sweden.     

Covariance structure approximation via gLasso in high-dimensional supervised classification

Recent work has shown that the Lasso-based regularization is very useful for estimating the high-dimensional inverse covariance matrix. A particularly useful scheme is based on penalizing the ?₁ norm of the off-diagonal elements to encourage sparsity. We embed this type of regularization into high-dimensional classification. A two-stage estimation procedure is proposed which first recovers structural zeros of the inverse covariance matrix and then enforces block sparsity by moving non-zeros closer to the main diagonal. We show that the block-diagonal approximation of the inverse covariance matrix leads to an additive classifier, and demonstrate that accounting for the structure can yield better performance accuracy. Effect of the block size on classification is explored, and a class of asymptotically equivalent structure approximations in a high-dimensional setting is specified. We suggest a variable selection at the block level and investigate properties of this procedure in growing dimension asymptotics. We present a consistency result on the feature selection procedure, establish asymptotic lower an upper bounds for the fraction of separative blocks and specify constraints under which the reliable classification with block-wise feature selection can be performed. The relevance and benefits of the proposed approach are illustrated on both simulated and real data.     

A test statistic to choose between Liu-type and least-squares estimator based on mean square error criteria

In this study, the necessary and sufficient conditions for the Liu-type (LT) biased estimator are determined. A test for choosing between the LT estimator and least-squares estimator is obtained by using these necessary and sufficient conditions. Also, a simulation study is carried out to compare this estimator against the ridge estimator. Furthermore, a numerical example is given for defined test statistic.     

Statistical games against a prophet-proof of a minimax conjecture

“Prophet theory” quantifies the price a statistician has to pay for his lack of information in stochastic sequences. In a recent paper, Schmitz (1991) gave a game-theoretical interpretation of this situation and he formulated in particular a minimax conjecture for the difference case. In this note we prove that conjecture and, moreover, present minimax ran domized stopping times (minimax procedures for the statistician).     

Desertification and the political agenda

Why, more than ten years after the United Nations Conference on Desertification, can so little progress on implementing the Plan of Action be reported? The answer lies, in part, in the characteristics of the issue. As an issue, desertification lacks definitional clarity, and geographic and resource specificity; it is intractable, long-term and latent; and it has a technical bias and no clearly defined villain. These characteristics make it difficult to muster the requisite political support needed to generate sustained policy attention from the public and decisionmakers. If the real problems encompassed by desertification are to be solved, the issue needs to be reframed and recast into a set of manageable and feasible objectives.     

People,fire, and wildland environments

The mixing of people, wildlands, and fire hazards—the urban/wildland interface—is creating a management problem that offers both challenges and opportunities to resource managers. This paper provides an overview of the many facets of the urban/wildland fire interface. The nature of the problem is defined, and the steps that managers have taken since the mid-1980s to define the problem and increase awareness are described. Building awareness of policy problems, however, is only a first step in any policy development process. Concern and interest must be translated into sustained policy action. To do so will require capturing the attention of a broader audience, transferring technological improvements to all impacted interests, and systematically evaluating a broad range of innovative policy alternatives. The activities taking place in Palm Coast, Florida illustrate the involvement and resources of local citizens, researchers, and government entities that will need to be marshalled to work toward a solution of the problem.     

Wie ehrlich berichten männliche Jugendliche über ihr delinquentes Verhalten?

Survey-based studies on the prevalence and causes of deviant behaviour very much depend on the honesty of respondents. However, the validity of self-reports is rarely investigated. We report on a external validation of self-reported delinquency of male juveniles based on two survey samples — face-to-face interviews in households (N=309), and paper and pencil interviews in school (N=337) — which have been done in 1999 and 2000 in Freiburg and are used for record checks of self-reported police contacts both on the individual and aggregate level. Individual-level record checks reveal that a majority of respondents has honestly reported contacts with the police, while there are a considerable number of both ‘false negative’ and ‘false positive’ answers which come predominately from respondents with low educational and social status and of migration background. As these groups show high non-response rates as well, the correlation between delinquency and socio-economic status is likely to be underestimated. The school survey, on the other hand, yields higher and more realistic prevalence rates. However, comparisons between the two survey modes hint at differential effects of social desirability which question the validity of self-reports by respondents with high educational status. Survey results on self-reported delinquency should generally be interpreted with great caution, and more research on the mode effects of class room interviews are deemed necessary.