Influence measure for the L1 regression

Because outliers and leverage observations unduly affect the least squares regression, the identification of influential observations is considered an important and integrai part of the analysis. However, very few techniques have been developed for the residual analysis and diagnostics for the minimum sum of absolute errors, L₁ regression. Although the L₁ regression is more resistant to the outliers than the least squares regression, it appears that outliers (leverage) in the predictor variables may affect it. In this paper, our objective is to develop an influence measure for the L₁ regression based on the likelihood displacement function. We illustrate the proposed influence measure with examples.     

The Next Generation of Collective Action Research

The articles presented in this volume describe part of a new generation of interest and vigor in the social psychological study of collective action. This new wave builds nicely on the foundation set by social identity, self-categorization, and relative deprivation theories but also introduces a number of important innovative perspectives and variables. In this commentary, I review some of these expansions and additions, raise a number of conceptual concerns that arise out of these new directions, and discuss more generally some novel and important directions that emerge from the work presented in the volume and in other recent work on collective action.     

Do “Clicker” Educational Sessions Enhance the Effectiveness of a Social Norms Marketing Campaign?

Abstract

Objective: Social norms campaigns are a cost-effective way to reduce high-risk drinking on college campuses. This study compares effectiveness of a “standard” social norms media (SNM) campaign for those with and without exposure to additional educational sessions using audience response technology (“clickers”). Methods: American College Health Association's National College Health Assessment questions are used to evaluate actual and perceived use. Additional survey questions assess individual exposure to the interventions. Results: The authors find “clicker” technology to be more effective than social norms poster media alone in reducing misperceptions of normative alcohol use for those students who attended clicker sessions. Conclusion: Poster SNM campaigns may be most effective when supported by group “clicker” heath-related sessions.     

Lag Length Selection for Unit Root Tests in the Presence of Nonstationary Volatility

A number of recent papers have focused on the problem of testing for a unit root in the case where the driving shocks may be unconditionally heteroskedastic. These papers have, however, taken the lag length in the unit root test regression to be a deterministic function of the sample size, rather than data-determined, the latter being standard empirical practice. We investigate the finite sample impact of unconditional heteroskedasticity on conventional data-dependent lag selection methods in augmented Dickey–Fuller type regressions and propose new lag selection criteria which allow for unconditional heteroskedasticity. Standard lag selection methods are shown to have a tendency to over-fit the lag order under heteroskedasticity, resulting in significant power losses in the (wild bootstrap implementation of the) augmented Dickey–Fuller tests under the alternative. The proposed new lag selection criteria are shown to avoid this problem yet deliver unit root tests with almost identical finite sample properties as the corresponding tests based on conventional lag selection when the shocks are homoskedastic.     

Geeta distribution and its properties

A new discrete distribution defined over all the positive integers and with the name of Geeta distribution is described. It is L-shaped like the logarithmic series distribution, Yule distribution and the discrete Pareto distribution but is far more versatile than them as it has two parameters. It belongs to the classes of location parameter distributions, modified power series distributions, Lagrange series distributions and exponential distributions. Its mean fi, variance a2 and two recurrence formulae for higher central moments are obtained. Convolution theorem and variations in the model with changes in the parameters have been considered. ML estimators, MVU estimators and estimators based of mean and variance and on mean and first frequency have been derived.     

A powerful test for uniformity to detect highly peaked alternativedensities

A new class of statistical tests for uniformity based on sample ranges is proposed to detect a uniform density contaminated by a density with one or more high peaks. These kinds of alternatives occur quite frequently, especially in physics. It is shown that the proposed tests arc consistent and have high Pitman asymptotic relative efficiencies. Results of a Monte Carlo power study indicate that they, compared with other tests of uniformity, possess good power properties.A comparative study of various tests is also conducted using real data. An effcient algorithm for computing out test statistic and a table of percentage points are given, providing a practical guide for using the new test.     

市场经济条件下传媒企业的发展战略研究

在分析传媒企业特点的基础上，重点探讨了传媒企业在发展过程中采用的三种战略：差异化战略、多元化经营战略及合作竞争战略。同时，为保证发展战略的成功实施，传媒企业应该从建立学习型动态网络组织、构建合理的人才素质结构、塑造优秀企业文化及领导者角色的扮演等方面做出努力。