AVERAGE PREDICTIVE COMPARISONS FOR MODELS WITH NONLINEARITY, INTERACTIONS, AND VARIANCE COMPONENTS

In a predictive model, what is the expected difference in the outcome associated with a unit difference in one of the inputs? In a linear regression model without interactions, this average predictive comparison is simply a regression coefficient (with associated uncertainty). In a model with nonlinearity or interactions, however, the average predictive comparison in general depends on the values of the predictors. We consider various definitions based on averages over a population distribution of the predictors, and we compute standard errors based on uncertainty in model parameters. We illustrate with a study of criminal justice data for urban counties in the United States. The outcome of interest measures whether a convicted felon received a prison sentence rather than a jail or non-custodial sentence, with predictors available at both individual and county levels. We fit three models: (1) a hierarchical logistic regression with varying coefficients for the within-county intercepts as well as for each individual predictor; (2) a hierarchical model with varying intercepts only; and (3) a nonhierarchical model that ignores the multilevel nature of the data. The regression coefficients have different interpretations for the different models; in contrast, the models can be compared directly using predictive comparisons. Furthermore, predictive comparisons clarify the interplay between the individual and county predictors for the hierarchical models and also illustrate the relative size of varying county effects.     

Emerging themes in distance learning research and practice: some food for thought

With the rapid spread of distance learning as a medium for delivering instruction, the practice of distance learning has outpaced research. This paper describes major themes identified in a review of selected research papers published in the past five years. Themes include the following: definitions of distance learning and why it should be studied; identification of the major learning theories on which research is based; how collaboration can be achieved via distance learning; the role that learner characteristics play in the success of distance learning systems, and issues related to measuring the effectiveness of distance learning. The authors conclude that more research is needed to identify critical success factors for distance learning.     

Lawns of weeds: Status in opposition to life

The modern high status lawn is a recent cultural form that motivates human responses with emerging negative physical outcomes. From a dualistic theoretical perspective, this article analyzes the modern lawn in terms of cultural dichotomies and applies a theory of status construction to show how the lawn becomes both an indicator of status and a component of identity and motivation. Then, it reports selected indicators of negative physical outcomes. The dual outcomes illustrate the empirical challenge of “Simmel’s lemma” stating that culture is in opposition to life.     

Local government service systems improvement: exposing the social networks

Using a local government (LG) case study, this paper describes and qualitatively explores the value and use of social network analysis (SNA) in creating a rich environment for service network innovation and development. The case study analysed manages regional planning development applications and involves a complex social network. The study underpins the view that in LG service environments, mechanistic models for systems improvement are on their own inadequate. SNA constitutes an essential complementary development framework underpinning continuous innovation through human and social capital development. Findings presented are profound for local government and multiple service contexts and argue for a greater emphasis on understanding and developing the human and social aspects of service systems as opposed to a predominant technical systems bias.