EXACT FINITE-SAMPLE PROPERTIES OF A PRE-TEST ESTIMATOR IN RIDGE REGRESSION

This paper discusses a pre-test regression estimator which uses the least squares estimate when it is “large” and a ridge regression estimate for “small” regression coefficients, where the preliminary test is applied separately to each regression coefficient in turn to determine whether it is “large” or “small.” For orthogonal regressors, the exact finite-sample bias and mean squared error of the pre-test estimator are derived. The latter is less biased than a ridge estimator, and over much of the parameter space the pre-test estimator has smaller mean squared error than least squares. A ridge estimator is found to be inferior to the pre-test estimator in terms of mean squared error in many situations, and at worst the latter estimator is only slightly less efficient than the former at commonly used significance levels.     

Ageism Across the Lifespan: Towards a Self-Categorization Model of Ageing

This article uses this collection of articles on ageism as a springboard to discuss empirical lacunae in the literature as well as propose a self-categorization model of ageing phenomena. In particular, we argue that research would benefit from a more lifespan communication perspective. This includes the social origins of ageism that can be laid down early in development and perpetuated through collusive processes as individuals themselves age. Further, problems of interactively managing ageism, its intragenerational parameters, and the variable consequences of making death salient, are identified. Finally, we elaborate and illustrate a self-categorization model of ageing processes before critically examining panaceas proposed by others to ameliorate ageism.     

Playing the scales: Regional transformations and the differentiation of rural space in the Chilean wine industry

Globalization and industrial restructuring transform rural places in complex and often contradictory ways. These involve both quantitative changes, increasing the size and scope of operation to achieve economies of scale, and qualitative shifts, sometimes leading to a shift up the quality/price scale, towards finer spatial resolution and identification with place of origin. This paper examines the transformation of the Chilean wine industry noting its expansion and orientation towards export production. As the industry has changed, it has become apparent that firms have adopted different scalar strategies, sometimes downscaling by seeking low-cost production, homogenisation of product and a weak identification with place, and sometimes upscaling by improving quality, claiming exclusiveness and fixing products to ever finer definitions of place. Places have been defined, reconstructed, promoted and significantly differentiated as a result.     

Personality characteristics and environmental attitudes

The relationship between attitudes toward environmental issues and certain personality characteristics were investigated. The personality characteristics related to locus of control, openness of belief system, and perceptions about self. The subjects in the study were 74 female college students in a teacher preparation program.Results of the study indicate that 1. self-controlled, well-organized and goal oriented persons will be more likely to display favorable environmental behaviors and 2. persons who view themselves as having more control over events in their environment are less likely to favor laws or restrictive measures designed to preserve or improve environmental quality.     

Bias-corrected maximum likelihood estimation of the parameters of the generalized Pareto distribution

ABSTRACT

We derive analytic expressions for the biases, to O(n^?1), of the maximum likelihood estimators of the parameters of the generalized Pareto distribution. Using these expressions to bias-correct the estimators in a selective manner is found to be extremely effective in terms of bias reduction, and can also result in a small reduction in relative mean squared error (MSE). In terms of remaining relative bias, the analytic bias-corrected estimators are somewhat less effective than their counterparts obtained by using a parametric bootstrap bias correction. However, the analytic correction out-performs the bootstrap correction in terms of remaining %MSE. It also performs credibly relative to other recently proposed estimators for this distribution. Taking into account the relative computational costs, this leads us to recommend the selective use of the analytic bias adjustment for most practical situations.     

Implementation fidelity in a teacher-led alcohol use prevention curriculum

There is now ample evidence that teachers tend to make substantial modifications to both the prescribed content and methods of the curricula they administer, and that such modifications are likely to attenuate curricula effects. We examine the fidelity with which teachers implement "Protecting You, Protecting Me," an underage alcohol use prevention curriculum. Findings suggest that while teachers attempted to implement most sections of a lesson, the lessons taught were consistently--and often extensively--adapted. We conclude that since teachers are likely to continue to modify lessons, curriculum developers and trainers should enhance their understanding of how prevention curricula are taught under real world conditions, help teachers to reinforce key curriculum concepts, and consider modifying those curricular sections that teachers are adapting with greatest frequency.     

The importance of context specificity in work stress research: A test of the Demand-Control-Support model in academics

Abstract

The Demand-Control (D-C) (Karasek, 1979) and the Demand-Control-Support (D-C-S) (Johnson & Hall, 1988; Johnson, Hall, & Theorell, 1989; Karasek & Theorell, 1990) models of work stress suggest that jobs with high demands and low control (and low support) are stressful. In line with the support in the literature for context-specificity in occupational stress research (Sparks & Cooper, 1999) and the limited and even contradictory support for interaction effects, the main aim of the present study was to examine how the D-C-S model applied in a well-defined occupational group. Using hierarchical regression analyses, and controlling for negative affect, the D-C-S model accounted for 26%, 6%, and 8% of the variance in job satisfaction, psychological distress and burnout, respectively, among 166 academics in a UK university. No two-way or three-way interactive effects were evident, but additive effects of job demands and control on psychological well-being and of job demands and support on both burnout and job satisfaction were shown, corroborating research showing that high job strain is linked to ill health and job dissatisfaction in this homogenous occupational sample. It is recommended that, in future, research includes more variables that are specific to a particular occupation.     

Prediction-based regularization using data augmented regression

The role of regularization is to control fitted model complexity and variance by penalizing (or constraining) models to be in an area of model space that is deemed reasonable, thus facilitating good predictive performance. This is typically achieved by penalizing a parametric or non-parametric representation of the model. In this paper we advocate instead the use of prior knowledge or expectations about the predictions of models for regularization. This has the twofold advantage of allowing a more intuitive interpretation of penalties and priors and explicitly controlling model extrapolation into relevant regions of the feature space. This second point is especially critical in high-dimensional modeling situations, where the curse of dimensionality implies that new prediction points usually require extrapolation. We demonstrate that prediction-based regularization can, in many cases, be stochastically implemented by simply augmenting the dataset with Monte Carlo pseudo-data. We investigate the range of applicability of this implementation. An asymptotic analysis of the performance of Data Augmented Regression (DAR) in parametric and non-parametric linear regression, and in nearest neighbor regression, clarifies the regularizing behavior of DAR. We apply DAR to simulated and real data, and show that it is able to control the variance of extrapolation, while maintaining, and often improving, predictive accuracy.