Bayesian assessment of assumptions of regression analysis

Many statistical procedures are based on the models which specify the conditions under which the data are generated. Many applications of linear regression, for example, assume that:(i) the observations are independent; (ii) the errors in the observations are identically distributed; (iii) each error has a normal distribution with mean zero and unknown variance σ²> 0. Previous works have examined individual departures from these assumptions. Here we examine composite departures. It is assumed that the error distribution in a linear model is power-exponential and that the observations are generated via a first order autoregressive model with the possibility of spurious observations. The consequences are illustrated via an example.     

Suburban Sprawl,Regional Diffusion,and the Fate of Small Retailers in a Large Retail Environment, 1977–1996

Abstract

Research on the decline of public life in the United States has largely overlooked the role of Main Street retailers that provide public spaces for the maintenance of informal social ties. A central factor shaping the viability of small retailers is the development of big box chain stores that offer one-stop shopping and price out smaller competitors. Although prior studies have considered the transition from small to large retailers as a national phenomenon, arguing for the importance of place effects, we document the spatial variation in this process for nonmetropolitan counties in the United States. We hypothesize that the economic downturns in agriculture and manufacturing during the 1980s, combined with suburban sprawl into nonmetropolitan counties, facilitated the decline of small retailing in specific locales. Employing data from the 1977–1996 U.S. County Business Patterns, we test our hypotheses concerning the spatial variability in the decline of small retailing. Our results point to a marked decline in the number of establishments and employment in selected retail industries for nonmetropolitan counties near metropolitan areas in the South, Midwest, and West. These findings highlight the importance of considering local business enterprises as an important dimension of public life and local leadership in community affairs. We conclude our study by outlining the social consequences of the decline of small retail activity and suggest directions for future research.     

“Your Picture Looks the Same as My Picture”: An Examination of Passing in Transgender Communities

Transgender people remain one of the groups most susceptible to discrimination in the U.S. Previous studies have examined the discrimination and stress transgender people face, but few studies have examined trans identities using existing sociological theories of marginalized groups and identity formation. Using the theories of Dubois and Cooley, this study explores identity formation in conjunction with the phenomenon of passing among transgender people residing in Nebraska. Results suggest that while trans people do pass as a mechanism for subverting discrimination, there are other factors that influence an individual’s choice and strategy to pass or not. The current investigation lends a sociological perspective on the social aspect of gender presentation and gender visibility for trans individuals in a largely conservative Midwestern state.     

Bayesian analysis of reliability in multicomponent stress-strength models

This paper provides a Bayesian treatment of the problem of inference about the reliability of a multicomponent stress-strength system which functions if s or more of k identical components simultaneously operate. All stresses and strengths are assumed to be independent, exponentially distributed random variables. Exact and approximate asymptotic posterior distributions for the reliability are derived, and the results are illustrated by a numerical example.     

The Role of the Statistician: Scientist or Shoe Clerk

A carnival game is described in which a player rolls eight dice or eight marbles into holes. To win, the player must obtain a favorable outcome on a number of plays. The probability distribution for the outcome of a single play is discussed. The distribution of a winning combination of outcomes is discussed and approximated. These probabilities show that the game is essentially unbeatable.     

Observing Women Caregivers’ Everyday Experiences: New Ways of Understanding and Intervening

This article discusses the practice implications of videographic research examining the everyday lived experiences of 5 women family caregivers of older adults with chronic illness. The women’s nonverbal expressions and gestures revealed how caregiving is accomplished and lived on a daily basis, in particular through emotion and body management, abnegation, and performance. The findings from this microethnographic study suggest that observing women caregivers’ everyday experiences can open new avenues for holistic intervention with this population. Observing nonverbal cues can offer a way for practitioners to better understand women caregivers’ realities, to question their practice, and to adapt their interventions accordingly.     

Creating Ethnicity: East European Jews and Lithuanian Immigrants in Chicago

Abstract

By focusing on East European Jewish and Lithuanian ethnic groups in the United States, this paper offers a three stage model for understanding the process by which assimilating groups create their ethnicity: Stage One, ethnic community and participatory organizations; Stage Two, individual perpetuation and representational organizations; Stage Three, informal behavior and residual symbols. The model considers the impact of both cultural and structural variables, instead of treating them as rival claimants to primacy. In applying the model to data gathered in the groups' Chicago communities, we found that despite particular divergencies, both groups presented a similar response to the United States, enabling their members to maintain a dual ethnic identity beyond the tightly-knit ghetto and urban village.     

Grief and Trauma Group Therapy for Children After Hurricane Katrina

Theoretical and evidence-based group therapy models that address the interplay of grief and trauma are needed for children postdisaster. This article describes a theoretically informed 10-week grief and trauma group model that was evaluated with children in schools after Hurricane Katrina. The foundation of the grief and trauma intervention includes utilizing developmentally specific methods, an ecological perspective, and culturally relevant approaches. The theoretical ordering of themes addressed occurs within three overlapping phases: (1) resilience and safety, (2) restorative retelling, (3) and reconnecting (Herman, 1997 Herman, J. L. 1997. Trauma and recovery, New York: Basic Books.  [Google Scholar]; Rynearson, 2001 Rynearson, R. 2001. Retelling violent death, Philadelphia: Brunner-Routledge.  [Google Scholar]). Techniques from cognitive behavioral therapy and narrative therapy are combined to address loss and trauma.