The Gamma-count distribution in the analysis of experimental underdispersed data

Event counts are response variables with non-negative integer values representing the number of times that an event occurs within a fixed domain such as a time interval, a geographical area or a cell of a contingency table. Analysis of counts by Gaussian regression models ignores the discreteness, asymmetry and heteroscedasticity and is inefficient, providing unrealistic standard errors or possibly negative predictions of the expected number of events. The Poisson regression is the standard model for count data with underlying assumptions on the generating process which may be implausible in many applications. Statisticians have long recognized the limitation of imposing equidispersion under the Poisson regression model. A typical situation is when the conditional variance exceeds the conditional mean, in which case models allowing for overdispersion are routinely used. Less reported is the case of underdispersion with fewer modeling alternatives and assessments available in the literature. One of such alternatives, the Gamma-count model, is adopted here in the analysis of an agronomic experiment designed to investigate the effect of levels of defoliation on different phenological states upon the number of cotton bolls. Data set and code for analysis are available as online supplements. Results show improvements over the Poisson model and the semi-parametric quasi-Poisson model in capturing the observed variability in the data. Estimating rather than assuming the underlying variance process leads to important insights into the process.     

Technology transfer concerns of college graduates with disabilities: Profiles in transition from higher education to competitive careers

The article describes the technology transfer concerns reported by a small sample (N=14) of recent college graduates with disabilities. In structured, in-depth interviews, researchers asked respondents to reflect on the extent to which they had utilized technology resources during their college years in preparation for the world of work. Results suggest that colleges and universities need to play a more active role in introducing students with disabilities to both generalized and assistive technology services.     

Walking a tightrope: Dilemmas of participant observation of groups in conflict

This article addresses issues that develop in the conduct of comparative participant observation research. The two groups in which the authors became involved as participant observers were the Unification Church of the Korean evangelist Reverend Sun Myung Moon and the emerging network of organizations involved in the practice of deprogramming. Each group was dedicated to the destruction of the other. Five major methodological problems, common to conducting investigation on single groups, are discussed in the context of researching these two antagonistic groups: 1) role definition and justification; 2) pressures to go native; 3) public pressure to take a stand; 4) evolving commitments; and 5) gaining comparable information and insights. The authors describe their efforts to resolve these problems and maintain a good rapport with both groups. This paper is the product of a joint effort. The order of authorship is random and does not imply any difference in the importance of contributions.