Estimation in linear models using gradient descent with early stopping

A new shrinkage estimator of the coefficients of a linear model is derived. The estimator is motivated by the gradient-descent algorithm used to minimize the sum of squared errors and results from early stopping of the algorithm. The statistical properties of the estimator are examined and compared with other well-established methods such as least squares and ridge regression, both analytically and through a simulation study. An important result is that the new estimator is shown to be comparable to other shrinkage estimators in terms of mean squared error of parameters and of predictions, and superior under certain circumstances.Supported by the Greek State Scholarships Foundation     

Methods for Whole System Change in Public Organizations and Communities: An Overview of the Issues

In a world that is made up of interconnected systems, public leaders are learning that they must build commitment, alignment, and ownership among a broad group of individuals and groups in order to implement change. An increasing variety of processes and methods are being utilized for engaging an organization or community in whole system change. Large group methodologies, originally developed by organization development practitioners and theorists, are now gaining currency in public organizations and communities. At the same time, community organizers who successfully utilized confrontation and conflict-oriented methods in the civil rights, labor and other movements, are employing broadly participative, collaborative approaches by creating small group settings where citizens can share their views and using large group meetings to engage multiple stakeholders in community change. This special symposium explores and reflects on the rich mix of methods in use for whole system change in public organizations and communities.     

Nursing Home Ownership Trends and Their Impacts on Quality of Care: A Study Using Detailed Ownership Data From Texas

The role of ownership in the provision of nursing home care has long been a challenging issue for policy makers and researchers. Although much of the focus historically has been on differences between for-profit and not-for-profit facilities, this simple distinction has become less useful in recent years as companies have employed more complicated ownership and management structures. Using detailed ownership data from the state of Texas, we describe the evolution of nursing home corporate structures from 2000 to 2007, analyze the effect of these structures on quality of care and staffing in nursing homes, and discuss the policy implications of these changes.     

An agent-based model of indirect minority influence on social change and diversity

The present paper describes an agent-based model of indirect minority influence. It examines whether indirect minority influence can lead to social change as a function of cognitive rebalancing, a process whereby related attitudes are affected when one attitude is changed. An attitude updating algorithm was modelled with minimal assumptions drawing on social psychology theories of indirect minority influence. Results revealed that facing direct majority influence, indirect minority influence along with cognitive rebalancing is a recipe for social change. Furthermore, indirect minority influence promotes and maintains attitudinal diversity in local ingroups and throughout the society. We discuss the findings in terms of social influence theories and suggest promising avenues for model extensions for theory building in minority influence and social change.