Flexible models for non-equidispersed count data: comparative performance of parametric models to deal with underdispersion

AStA Advances in Statistical Analysis - Count data as response variables are commonly modeled using Poisson regression models, which require equidispersion, i.e., equal mean and variance. However,...     

Evaluating employee assistance policy in an HMO-based alcoholism project.

One aspect of successful employee assistance program (EAP) implementation is the adoption of a formal, written policy, reflecting company commitment to EAP guidelines and goals. This study of criteria predictive of such policy adoption was conducted at the occupational alcoholism project of a New England health maintenance organization (HMO). Data on nearly 400 organizations contacted by occupational program consultants (OPCs) over a 20-month period were collected by questionnaire and interview. One third of these organizations adopted employee assistance policies and set about establishing formal programs. Stepwise multiple regression is the principal method used to pinpoint the correlates of policy adoption. Two of the most important of these are the attitudes of contact persons within the organization toward alcoholism and employee assistance programs, particularly their admission of alcohol problems within their social networks; and the consultants' persistence and marketing skills. The adopting organizations also had reputations for being progressive, and actively concerned about employee welfare; they tended to be large, their executives autonomous, and their union membership rates high. Inhibiting policy acceptance were fears that a written policy would jeopardize the reputation and image of the organization, and that an employee assistance program would remove internal control of personal procedures. The adequacy of the evaluative data and methods are discussed, and recommendations are offered in the interests of streamlining the efforts of OPCs and of achieving greater penetration of targeted organizations.     

Newborns' Perceptual Categorization for Closed and Open Geometric Forms

This study explored newborns' ability to perceive perceptual similarities between different exemplars of 2 broad classes of simple shapes: closed and open geometric forms. Three experiments were carried out using a visual paired‐comparison task. Evidence showed that, after familiarization either to closed‐shaped or to open‐shaped forms, newborns manifested a novelty preference for a novel‐category rather than for a familiar‐category exemplar (Experiment 1). This result could not be explained either as a consequence of the newborns' inability to discriminate between instances of the same category of simple geometric forms (Experiment 2), or as a consequence of a spontaneous preference for the novel‐category exemplars (Experiment 3). Overall, findings revealed that newborns are able to form broad categories of distinguishable geometric shapes by relying on the shapes' perceptual similarity.     

Parametric estimation for ARFIMA models via spectral methods

Given a fractional integrated, autoregressive, moving average,ARFIMA (p, d, q) process, the simultaneous estimation of the short and long memory parameters can be achieved by maximum likelihood estimators. In this paper, following a two-step algorithm, the coefficients are estimated combining the maximum likelihood estimators with the general orthogonal decomposition of stochastic processes. In particular, the principal component analysis of stochastic processes is exploited to estimate the short memory parameters, which are plugged into the maximum likelihood function to obtain the fractional differencingd.     

Yearning, learning, and conceding: reasons men and women change their childbearing intentions

People's childbearing intentions change over the course of their reproductive lives. These changes have been conceptualized as occurring in response to the realization that an individual is unlikely to achieve his or her intended fertility, because of constraints such as the "biological clock" or lack of a partner. In this article, we find that changes to child-bearing plans are influenced by a much wider range of factors than this. People change their plans in response to the wishes of their partners, in response to social norms, as the result of repartnering, and as the result of learning about the costs and benefits of parenthood; there are also differences between the factors that influence men's and women's decision-making. In a departure from existing studies in this area, we use a flexible analytical framework that enables us to analyze increases in planned fertility separately from decreases. This allows us to uncover several complexities of the decision-making process that would otherwise be hidden, and leads us to conclude that the determinants of increases in planned fertility are not simply equal and opposite to the determinants of decreases.     

Competence effects for choices involving gains and losses

We investigate how choices for uncertain gain and loss prospects are affected by the decision maker’s perceived level of knowledge about the underlying domain of uncertainty. Specifically, we test whether Heath and Tversky’s (J Risk Uncertain 4:5–28, 1991) competence hypothesis extends from gains to losses. We predict that the commonly-observed preference for high knowledge over low knowledge prospects for gains reverses for losses. We employ an empirical setup in which participants make hypothetical choices between gain or loss prospects in which the outcome depends on whether a high or low knowledge event occurs. We infer decision weighting functions for high and low knowledge events from choices using a representative agent preference model. For gains, we replicate the results of Kilka and Weber (Manage Sci 47:1712–1726, 2001), finding that decision makers are more attracted to choices that they feel more knowledgeable about. However, for losses, we find limited support for our extension of the competence effect.     

Performance of coefficient of variation estimators in ranked set sampling

In this paper, we propose and evaluate the performance of different parametric and nonparametric estimators for the population coefficient of variation considering Ranked Set Sampling (RSS) under normal distribution. The performance of the proposed estimators was assessed based on the bias and relative efficiency provided by a Monte Carlo simulation study. An application in anthropometric measurements data from a human population is also presented. The results showed that the proposed estimators via RSS present an expressively lower mean squared error when compared to the usual estimator, obtained via Simple Random Sampling. Also, it was verified the superiority of the maximum likelihood estimator, given the necessary assumptions of normality and perfect ranking are met.