Graphical methods for ranking data

Graphical methods are presented for the analysis of ranking data collected from g groups of rankers. The data provided by a single individual consist of the ranks of r objects. The sample space is the space of all permutations and has cardinality r! In order to reduce the dimensionality of the data and to study the interrelationships among rankers and items, a two-stage approach is proposed. First, transformations motivated by various metrics on permutations are defined. In particular, the Kendall metric gives rise to pairwise comparisons. Then, the transformed data are analyzed using results in connection with the generalized singular-value decomposition of a matrix. The methods are illustrated on two examples.     

Sociology as a discipline: Quasi-science and quasi-humanities

Sociologists, like other professionals and academic practitioners, have engaged in a collective project—“becoming a science.” This article traces the occupational and intellectual components of that project, focusing especially on the model of science employed, the limits of that model, and the limits of the science model in general. It is argued that sociology is a quasi-science and a quasi-humanities. Unfortunately, sociology has not systematically pursued its links to the humanities. The article argues for maintaining the empirical and explanatory thrust of the science model, while recognizing the extent to which concepts and theories are civilizationally embedded. The article ends with suggestions for systematically enriching sociology by closer links to the humanities. This article is a revision of a paper presented at the Plenary Session, The Future of Sociology, Annual Meeting of the American Sociological Association, August 24, 1988, Atlanta, Georgia. I have discussed the issues raised in this paper with, and received comments on previous drafts from, many colleagues: Andrew Abbott, Renee Anspach, Joseph Berger, Philip Converse, Claude Fischer, Herbert Gans, Michael Kennedy, Albert J. Rothenberg, AndrewScott, Anne Scott, Robert Scott, William Sewell, Jr., Margaret Somers, Sheldon Stryker, and Charles Tilly. They are not responsible for its sins.     

The Environmental Justice Debate: A Commentary on Methodological Issues and Practical Concerns

Over the last decade, environmental sociology has produced a tremendous stream of research pertaining to environmental justice issues. In general, we now know that low income groups and communities of color are disproportionately exposed to toxic wastes. In this paper, I argue that future research requires a shift in methodological approach. Learning how groups come to be exposed to toxic wastes requires an understanding of the organizational processes that shape decisions regarding production practices and regulatory enforcement strategies. I conclude by making three claims: (1) Documenting that disempowered groups are exposed to toxic wastes more than other groups is important. Disentangling whether race or class matters more is more dubious. (2) If we want to make claims about process, we should study process and not outcomes. (3) Insofar as we have to study outcomes, we should be more aware of which outcomes we want to study and what types of inferences we are able to draw from outcomes.     

Time to reconceptualize ‘green technology’ in the context of globalization and international relations

The focus on time is used to demonstrate that Newtonian conceptions of reality underpin the push for ‘green technology’ and its associated international relations. It brings to the surface the rationale of this technology and shows its limits and future potential by exploring underlying assumptions and principles: ‘green technology’, it is argued, is not achievable on those terms and such an approach to environmental problems is unlikely to lead to relevant action and suitable solutions. It is not simply a matter of finding the ‘right technical, economic and political solutions but, crucially, about reconceptualization and the restructuring of knowledge. Thus, conceptual revision is necessary if appropriate responses are to be found to the hazards of the industrial way of life; focus on the temporal dimension of technology and globalized political processes offers a first point of departure from the Newtonian tradition.     

The impact of unionization on the entry of firms: Evidence from U.S. industries

Traditional models of entry-deterrence typically emphasize sunk costs or predatory pricing, but unionization might also discourage potential entrants. This paper explores this possibility through an empirical model of entry that includes unionization as an explanatory variable. We find that unionization has a statistically significant entry-deterring effect.     

Marginality and its directions

The concept of marginality articulated by Robert Park in Migration and the Marginal Man is reconstructed in order to yield a more complex general theory of marginality. Park believed marginality results when individuals in migrant groups are barred by prejudice from complete acceptance into a dominant culture. Here it is argued that the marginal person, having taken on elements of the dominant culture, also is unable to return unchanged to his or her original group. Thus, the marginal person is caught in a structure of double ambivalence: unable either to leave or to return to the original group; unable either to merge with the new group or to slough it off. Marginal persons typically react to this field of cross-cutting pressures in four directions, here termed assimilation, return, poise, and transcendence. German Jewry of the Wilhelmine era serves as a test case of the general theory of marginality. Application of the theory resolves some of the salient difficulties attending efforts to understand postemancipation German Jewry.     

Asymptotically Uniform Tests After Consistent Model Selection in the Linear Regression Model

Abstract

This article specializes the critical value (CV) methods that are based upon (refinements of) Bonferroni bounds, introduced by McCloskey to a problem of inference after consistent model selection in a general linear regression model. The post-selection problem is formulated to mimic common empirical practice and is applicable to both cross-sectional and time series contexts. We provide algorithms for constructing the CVs in this setting and establish uniform asymptotic size results for the resulting tests. The practical implementation of the CVs is illustrated in an empirical application to the effect of classroom size on test scores.