Bayesian variable selection with strong heredity constraints

In this paper, we propose a Bayesian variable selection method for linear regression models with high-order interactions. Our method automatically enforces the heredity constraint, that is, a higher order interaction term can exist in the model only if both of its parent terms are in the model. Based on the stochastic search variable selection George and McCulloch (1993), we propose a novel hierarchical prior that fully considers the heredity constraint and controls the degree of sparsity simultaneously. We develop a Markov chain Monte Carlo (MCMC) algorithm to explore the model space efficiently while accounting for the heredity constraint by modifying the shotgun stochastic search algorithm Hans et al. (2007). The performance of the new model is demonstrated through comparisons with other methods. Numerical studies on both real data analysis and simulations show that our new method tends to find relevant variable more effectively when higher order interaction terms are considered.     

Using ranked set sampling with binary outcomes in cluster randomized designs

We study the use of ranked set sampling (RSS) with binary outcomes in cluster-randomized designs (CRDs), where a generalized linear mixed model (GLMM) is used to model the hierarchical data structure involved. Under the GLMM-based framework, we propose three different approaches to estimate the treatment effect, including the nonparametric (NP), maximum likelihood (ML) and pseudo likelihood (PL) estimators. We investigate their asymptotic properties and examine their finite-sample performance via simulation. Based on these three RSS estimators, we further develop procedures for testing the existence of the treatment effect. We examine the power and size of our proposed RSS tests and compare them with existing tests based on simple random sampling (SRS). All the proposed RSS estimation and test methods are illustrated with two data examples, one for rare events and the other for non-extreme events. Throughout our investigations, we also consider the possible effect of imperfect ranking. Among the proposed methods, we provide recommendations on whether to use RSS rather than SRS with binary outcomes in CRDs and, if yes, when to use which RSS method. The Canadian Journal of Statistics 48: 342–365; 2020 © 2019 Statistical Society of Canada     

Design and Assessment Methodology for System Resilience Metrics

By providing objective measures, resilience metrics (RMs) help planners, designers, and decisionmakers to have a grasp of the resilience status of a system. Conceptual frameworks establish a sound basis for RM development. However, a significant challenge that has yet to be addressed is the assessment of the validity of RMs, whether they reflect all abilities of a resilient system, and whether or not they overrate/underrate these abilities. This article covers this gap by introducing a methodology that can show the validity of an RM against its conceptual framework. This methodology combines experimental design methods and statistical analysis techniques that provide an insight into the RM's quality. We also propose a new metric that can be used for general systems. The analysis of the proposed metric using the presented methodology shows that this metric is a better indicator of the system's abilities compared to the existing metrics.     

Determinants of state long-term debt: The political market framework

Because it focuses on the moderating role of political institutions – which emphasize equilibrium policy outcomes under different institutional arrangements derived from the interaction of policy supply and demand – the political market framework provides useful insights for analyzing the determinants of state long-term debt. Thus, different types of state political institutions should affect the degree of long-term debt in terms of specific demands and supply. Despite the numerous studies that have either applied the political market approach to local governments in policy areas or have analyzed the determinants of long-term debt from only a financial management perspective, few studies have applied the political market framework to state governments. Thus, adopting a state financial management perspective and conducting a panel data analysis using state data from 1980 to 2014, this study identifies the reasons why state governments act on long-term obligations in terms of the political market framework. This study also aims to expand the application of the political market framework to state governments and to integrate determinants of state long-term indebtedness.     

Negotiation of identity and internal contradictions: the Terengganu and Kelantan Peranakan Chinese foodways compared

This study explores the Terengganu and Kelantan Peranakan Chinese foodways with special reference to two types of foods: daily and ancestral prayer foods. The principal focus is to illustrate the negotiation of identity through foodways as well as internal contradictions arising from this process of identity negotiation. These two groups of Peranakan Chinese are largely the product of acculturation by the local Malays through socio-cultural interactions, though the Kelantan Peranakan Chinese are also acculturated by the local Thai community. Their daily and ancestral prayer foods display contrasting identities that stem from the negotiating of their acculturated and primordial identities. The former displays a strong local cultural influence, while the latter displays a strong Chinese cultural influence. However, despite the pervasive influence of localisation in their daily foods, elements of hybridisation are visible in some occasionally prepared food items. Meanwhile, localised and hybrid food items are included in their ancestral prayer foods, which are supposed to express their primordial Chinese identity. These internal contractions illustrate the complexity of the negotiation of identity through foodways within a cross-cultural context.     

Beyond the “Usual Suspects”? Reimagining Democracy With Participatory Budgeting in Chicago

This article examines whether democratic innovations in the United States attract citizens who are typically underrepresented within existing political institutions. We focus on participatory budgeting, an intervention where residents decide how to allocate a particular pot of public money. Taking “PB Chicago” as our case study, we use survey and interview data to examine whether organizers realized their stated goal of involving residents other than the “usual suspects.” We find that residents who voted in PB Chicago were more often white, college educated, and from higher‐income households relative to both the local population and politically active residents in Chicago. While these residents were not necessarily the most active across other stages of the PB Chicago process, we find little evidence that lower socioeconomic status and minority residents were accessing the civic learning and empowerment gains associated with participatory forms of democracy. Outreach made the process more inclusive but was insufficient to overcome several important structural constraints. Of particular note, the needs and interests of less privileged residents were not met by the narrow capital works focus of PB Chicago. We suggest that when implemented under such conditions, participatory budgeting risks deepening existing political and social inequalities.     

Aspirations of Migrants and Returns to Human Capital Investment

Although there is adequate literature on the topic of state-employer collusion, this literature is barely underpinned in any theoretical framework. This article attempts to fill this theoretical lacuna by revisiting Gouldner’s (Patterns of industrial bureaucracy: a case study of modern factory administration, The Free Press, New York, 1954a) pioneering theoretical framework on patterns of bureaucracy, and extends his concept of mock bureaucracy to develop a new concept called ‘mock state bureaucracy’ to illustrate state-employer collusion in controlling workers in plants in developing third world economies. The article revisits and extends Gouldner’s (1954a) unit of analysis from the ‘firm’ level to the ‘state’ level and argues that the new concept mock state bureaucracy provides a better illustration of the state-employer collusion. The article argues that both ‘state’ and ‘employer’ are important units of analysis and they should be brought back to the centre stage of any discourse on employment relations of developing countries.     

Hybrid happening: Organizational reputations in corporate crises

Public relations professionals strive to develop mutually beneficial relationships among key publics that will result in favorable organizational reputations, but crises typically threaten those reputations. Much of public relations crisis research focuses on how to respond after a crisis, but drawing on Expectation Violation Theory (EVT), this research focuses on the expectations of stakeholders before a crisis and how they process information during a crisis. Drawing from reputation management research in marketing, it conceptualizes corporate reputations as encompassing associations related to corporate ability (CA) and corporate social responsibility (CSR). Reputation management research generally has investigated reputations as strong on either CA or CSR, but this research examines the effects of a “hybrid” reputation, which is strong in terms of both CA and CSR associations. The results of an experiment reveal that stakeholders’ responses during a crisis vary based on their expectations, how they perceive a hybrid reputation, and the crisis type. The study has theoretical implications regarding stakeholders’ information processing during a crisis, and it provides public relations professionals insights regarding how to cultivate and protect an organizational reputation.     

The Pyramid of Nonprofit Responsibility: The Institutionalization of Organizational Responsibility Across Sectors

Observers have noted that organizations in all sectors, whether business, nonprofit, or government, have been moving toward rationalized structures that presuppose and express empowered organizational actorhood. We draw upon neo-institutional theory in this paper to extend the argument: The arrival of organizational actorhood has precipitated a concomitant, cross-sectoral movement toward organizational social responsibility. Whereas existing research has tended to theorize the social responsibilities of businesses, we develop a pyramid conceptual schema to array the social responsibilities of nonprofits. We then document the coevolution of organizational actorhood and responsibility across both sectors with a metastudy of nearly 200 extant surveys. We chart the institutionalization of a slate of formal structures that express organizational actorhood (i.e., mission statements, vision statements, and strategic plans) and that profess and define organizational social responsibilities (i.e., core values, ethics codes, and responsibility communications). We close with implications and future directions for organizational studies and research on corporate social responsibility.