Sociological Methods & Research

The need to determine the correct dimensionality of theoretical constructs and generate valid measurement instruments when underlying items are categorical has generated a significant volume of research in the social sciences. This article presents two studies contrasting different categorical exploratory techniques. The first study compares Mokken scale analysis (MSA) and two-factor-based exploratory techniques for noncontinuous variables: item factor analysis and Normal Ogive Harmonic Analysis Robust Method (NOHARM). Comparisons are conducted across techniques and in reference to the common principal component analysis model using simulated data under conditions of two-dimensionality with different degrees of correlation (r = .0 to .6). The second study shows the theoretical and practical results of using MSA and NOHARM (the factorial technique which functioned best in the first study) on two nonsimulated data sets. The nonsimulated data are particularly interesting because MSA was used to solve a theoretical debate. Based on the results from both studies, we show that the ability of NOHARM to detect dimensionality and scalability is similar to MSA when the data comprise two uncorrelated latent dimensions; however, NOHARM is preferable when data are drawn from instruments containing latent dimensions weakly or moderately correlated. This article discusses the theoretical and practical implications of these findings.

This article pushes forward a critical dialogue about the value of visualization as a method of sociological theorizing. Building on a nascent literature, I argue theory diagrams may operate not only conjunctively but also disjunctively, independent from empirics; that their theoretical value lies not only in capturing sociological problems but also in the inferential procedures they embody; that their creative use spans not only deduction and abduction but also induction; that abduction may be pursued with diagrams not only in conjunction with deduction or in the production of visual sketches but also in visual exercises in theoretical play geared primarily toward getting new ideas; and that theory visuals often feature metaphorical aspects that, like their linguistic cousins, transfer thought patterns from one domain to another, thereby providing a major avenue for visual theoretical creativity. Taken together, pursuing these lines of thought helps to build a better understanding of how visualization contributes to the creative intellectual practice of sociological theorizing.

Social scientists are often interested in estimating the marginal effects of a time-varying treatment on an end-of-study continuous outcome. With observational data, estimating these effects is complicated by the presence of time-varying confounders affected by prior treatments, which may lead to bias in conventional regression and matching estimators. In this situation, inverse-probability-of-treatment-weighted (IPTW) estimation of a marginal structural model remains unbiased if treatment assignment is sequentially ignorable and the conditional probability of treatment is correctly modeled, but this method is not without limitations. In particular, it is difficult to use with continuous treatments, and it is relatively inefficient. This article explores using an alternative regression-based method—regression-with-residuals (RWR) estimation of a constrained structural nested mean model—that may overcome some of these limitations in practice. It is unbiased for the marginal effects of a time-varying treatment if treatment assignment is sequentially ignorable, the treatment effects of interest are invariant across levels of the confounders, and a model for the conditional mean of the outcome is correctly specified. The performance of RWR estimation relative to IPTW estimation is evaluated with a series of simulation experiments and with an empirical example based on longitudinal data from the Panel Study of Income Dynamics. Results indicate that it may outperform IPTW estimation in certain situations.

Newly precise evidence of the trajectory of top incomes in the United States and around the world relies on shares and ratios, prompting new inquiry into their properties as inequality measures. Current evidence suggests a mathematical link between top shares and the Gini coefficient and empirical links extending as well to the Atkinson measure. The work reported in this article strengthens that evidence, making several contributions: First, it formalizes the shares and ratios, showing that as monotonic transformations of each other, they are different manifestations of a single inequality measure, here called TopBot. Second, it presents two standard forms of TopBot, which satisfy the principle of normalization. Third, it presents a new link between top shares and the Gini coefficient, showing that properties and results associated with the Lorenz curve pertain as well to top shares. Fourth, it investigates TopBot in mathematically specified probability distributions, showing that TopBot is monotonically related to classical measures such as the Gini, Atkinson, and Theil measures and the coefficient of variation. Thus, TopBot appears to be a genuine inequality measure. Moreover, TopBot is further distinguished by its ease of calculation and ease of interpretation, making it an appealing People’s measure of inequality. This work also provides new insights, for example, that, given nonlinearities in the (monotonic) relations among inequality measures, Spearman correlations are more appropriate than Pearson correlations and that weakening of correlations signals differences and shifts in distributional form, themselves signals of income dynamics.

Advice on case selection in small-N research emphasizes controlling for confounding variables to facilitate inferential tests of a cross-case pattern. Yet many researchers embrace the “mechanismic worldview” and aim to construct explanations. Explanations differ from inferences because one explains an outcome at the individual case level. Hence, explanatory case studies are not simultaneously inferential tests, rendering prevailing case selection guidance ill fitting. This article provides an alternative outlook on case studies and case selection. It conceives of case studies as things that engage an analytical ideal type. Researchers can construct case-specific explanations by coupling the general claims of an ideal type with contextual analysis. In terms of case selection, if a case has contextual features that make it relatable to an ideal type, one can viably study that case in relation to the ideal type, regardless of the case’s other characteristics. This criterion diverges sharply from the conventional wisdom on case selection and can embolden unconventional comparisons.

Agent-based modeling holds great potential as an analytical tool. Agent-based models (ABMs) are, however, also vulnerable to critique, as they often employ stylized social worlds, with little connection to the actual environment in question. Given these concerns, there has been a recent call to more fully incorporate empirical data into ABMs. This article falls in this tradition, exploring the benefits of using sampled ego network data in ABMs of cultural diffusion. Thus, instead of relying on full network data, which can be difficult and costly to collect, or no empirical network data, which is convenient but not empirically grounded, we offer a middle-ground, one combining ABMs with recent work on network sampling. The main question is whether this approach is effective. We provide a test of the approach using six complete networks; the test also includes a range of diffusion models (where actors follow different rules of adoption). For each network, we take a random ego network sample and use that sample to infer the full network structure. We then run a diffusion model through the known, complete networks, as well as the inferred networks, and compare the results. The results, on the whole, are quite strong: Across all analyses, the diffusion curves based on the sampled data are very similar to the curves based on the true, complete network. This suggests that ego network sampling can, in fact, offer a practical means of incorporating empirical data into an agent-based model.

New technologies transform research specialties and potentiate new fields. Sociometers—wearable electronic sensors collecting quantitative, dynamic data about embodied social interactions at hyperfine scales—represent such a possibility for small group research. This article introduces this new method and its distinctive qualities and affordances. Next, we relate its potential for advancing understanding of three types of small group phenomena: (1) rhythmic entrainment, emotional energy, and solidarity; (2) nonverbal dominance and deference; and (3) groups as complex systems. We then present findings from two pilot studies of small group creativity in science and art collaborations. To do so, we combine sociometric, survey, and ethnographic data to consider how speech participation, body movement, and volume shape group creativity and to illustrate how sociometric data complements traditional qualitative and quantitative methods. We close by relating practical lessons learned to aid future researchers working to harness this powerful new research technology.

Longitudinal social network studies can easily suffer from insufficient statistical power. Studies that simultaneously investigate change of network ties and change of nodal attributes (selection and influence studies) are particularly at risk because the number of nodal observations is typically much lower than the number of observed tie variables. This article presents a simulation-based procedure to evaluate statistical power of longitudinal social network studies in which stochastic actor-oriented models are to be applied. Two detailed case studies illustrate how statistical power is strongly affected by network size, number of data collection waves, effect sizes, missing data, and participant turnover. These issues should thus be explored in the design phase of longitudinal social network studies.

Postelection surveys regularly overestimate voter turnout by 10 points or more. This article provides the first comprehensive documentation of the turnout gap in three major ongoing surveys (the General Social Survey, Current Population Survey, and American National Election Studies), evaluates explanations for it, interprets its significance, and suggests means to continue evaluating and improving survey measurements of turnout. Accuracy was greater in face-to-face than telephone interviews, consistent with the notion that the former mode engages more respondent effort with less social desirability bias. Accuracy was greater when respondents were asked about the most recent election, consistent with the hypothesis that forgetting creates errors. Question wordings designed to minimize source confusion and social desirability bias improved accuracy. Rates of reported turnout were lower with proxy reports than with self-reports, which may suggest greater accuracy of proxy reports. People who do not vote are less likely to participate in surveys than voters are.

Ordinary kriging, a spatial interpolation technique, is commonly used in social sciences to estimate neighborhood attributes such as physical disorder. Universal kriging, developed and used in physical sciences, extends ordinary kriging by supplementing the spatial model with additional covariates. We measured physical disorder on 1,826 sampled block faces across four U.S. cities (New York, Philadelphia, Detroit, and San Jose) using Google Street View imagery. We then compared leave-one-out cross-validation accuracy between universal and ordinary kriging and used random subsamples of our observed data to explore whether universal kriging could provide equal measurement accuracy with less spatially dense samples. Universal kriging did not always improve accuracy. However, a measure of housing vacancy did improve estimation accuracy in Philadelphia and Detroit (7.9 percent and 6.8 percent lower root mean square error, respectively) and allowed for equivalent estimation accuracy with half the sampled points in Philadelphia. Universal kriging may improve neighborhood measurement.