Research on neighborhood effects faces enormous methodological challenges, with selection bias being near the top of the list. In this issue of the Journal (Am J Epidemiol. 2014;180(8):776-784), Professor Jokela addresses this issue with novel repeated measures data and models that decompose putative effects into those within and between persons. His contribution shows that within-person neighborhood effects are quite modest and that there is evidence of selection bias between persons. Like all research, the work rests on assumptions. Unfortunately, such assumptions are difficult to substantiate or validate in this context. A consequentialist epidemiologic perspective compels further innovation and a larger social epidemiologic imagination.

The article by professors Galea and Link in this issue of the Journal (Am J Epidemiol. 2013;178(6):843-849) is an important contribution to the field of social epidemiology. Their 6 paths provide ample fodder for reflection, debate, and advancement. Although I agree with the thrust and spirit of their recommendations, I argue that if social epidemiology is to advance and become not just more popular but also more useful, we social epidemiologists need to first address our disciplinary pathologies. Among other things, we must embrace macro-to-micro transitions, understand and act on the principles of effect identification, conduct many more experiments, and train students to be not researchers but scientists.

This research examines trends in the relationship between obesity based on self-report height and weight and self-perceived health over a 30-year period. Importantly, this period included the articulation of comprehensive public health campaigns on excess weight and thus provides opportunities for assessment of the efficacy of the campaign, as well as the broader psycho-social impact of excess weight. Using novel data from the Integrated Health Interview Series, odds ratios for the association between obesity and self-perceived health were estimated for repeated cross-sectional samples that are nationally representative of noninstitutionalized American adults aged 18-85 and older spanning 1976-2006. Our findings show that (i) there are weak associations between obesity and self-perceived poor health; (ii) these associations are particularly small among men, often to the point of being nonexistent; and (iii) weak relationships for both men and women have remained virtually unchanged over the past 30 years. Several reasons why the public health campaign around excess weight has had limited traction are discussed including the collective problem of excess weight in America and how this undermines current approaches in public health efforts addressing excess weight.

Health is central to research on both immigration and assimilation, and differences in health among immigrants are a focal part of health disparities research. In both fields, immigrant health has been deemed paradoxical because a) immigrants tend to have better health than is predicted by their socioeconomic position and b) acculturation into American society is associated with declines in immigrant health status despite increasesin socioeconomic position and related utilization of health care. Using data from the 2000-2006 Integrated Health Interview Series, we assess the immigrant health paradox infour ways. First, we conduct a systematic assessment of the health of 10 immigrant groups defined in terms of global region of birth. Second, we examine similarity and difference in health by education gradients and assimilation trajectories across immigrant groups. Third, we assess the ability of widely recognized explanatory factors to account for health differences across immigrant groups, educational gradients, and assimilation effects. Finally, we assess the overall implications of immigrant health dynamics for health disparities in the United States. Across four health outcomes, there is remarkablesimilarity in health advantages, consistency in both educational gradients and detrimental acculturation trajectories, limited ability of the explanatory factors to account for the immigrant health advantage, and enduring differences in health statuses even among those with long tenures in the United States. As these findings highlight the significance of healthy immigrant selection, we discuss implications for existing theory and researchon assimilation processes and health disparities research.Issues of immigrant health have been a central feature of immigration research and a focal concern of health disparities research for more than a century (Jasso, Massey, Rosenzweig, and Smith 2004; Kandula, Kersey, and Lurie 2004; Rumbaut 1997). During this time, an impressive body of work has emerged that highlights the apparent paradox of immigrant health. In one respect, immigrants typically have better health statuses than would be expectedgiven their socioeconomic standing in U.S. society(Padilla, Boardman, Hummer, and Espitia 2002; Palloni and Arias 2004) and the average health status in their sending country (Jasso et al.2004). In another respect, equally compelling evidence suggests that immigrant health declinesover time. Here, acculturation, be it behavioral, linguistic, or simply exposure to U.S. society,seems to foster poorer health (Angel, Buckley, and Sakamoto 2001; Antecol and Bedard 2006; Aravena, and Hummer 2005; Cho, Frisbie, Hummer, and Rogers 2004; Lara et al. 2005; LeClere, Jensen, and Biddlecom 1994; Lopez-Gonzales). This is also paradoxical given that immigrants typically gain ground through acculturation on many of the factorsincome and access to health care, for examplethat improve health in the native population (Rumbaut 1997). Ultimately, the apparent paradox of immigrant health provides a fascinating lens into the dynamics of health over the life course, the nature of immigration and assimilation, and the complexities of health disparities and their life course context. As such, issues of immigrant health are key avenues for theoretical and empirical advancement.This paper makes four unique and necessary contributions to the question of the immigrant health paradox. First, evidence on immigrant health advantages and subsequent declines with increased exposure to U.S. society is primarily based on Hispanic immigrants. While Hispanics are clearly an important facet of the immigrant health issue, the late 20th and early 21st centuries have seen dramatic growth in both the Hispanic and non-Hispanic immigrantpopulation, with the latter including increasing numbers of Asian, Southeast Asian, Indian and Pakistani, and African immigrants (see Figure 1). The increasing prevalence of such groups necessitates further systematic analysis to fully understand both immigrant health as a demographic phenomenon and the scope and extent of the immigrant health paradox. Second, assessment of immigrant health requires simultaneous and comparative assessment of immigrant health dynamics. This includes both socioeconomic gradients in health and assimilation trajectories. Such dynamics have yet to be investigated, particularly in a systematic manner with high quality data that allow for comparisons across multiple immigrant groups. Third, research on health disparities highlights the endogenous factors, such as riskbehaviors and access to health care, that translate socioeconomic, racial, ethnic, and sex differences in differential health outcomes (see Chang and Lauderdale 2009; Link and Phelan 1995, 1996; Ross and Wu 1995). In contrast, immigrant health research has not broadly andsystematically examined such factors and what they mean for health differentials between the various immigrant groups and those born in the United States. Finally, we include multiple comparison populations based on the major racial and ethnic groupings of those born in the United States and thereby avoid the WASP comparator bias in traditional assimilation research(Alba an Nee 2005)

In this paper, we investigate the relationship of male and female economic opportunity to marriage formation in 2000, examining how relationships vary with race and ethnicity. To address these issues, we carry out multi-level analysis of the effects of local economic conditions on the marriage decisions of young men and women. We will compare results obtained using the 5% sample of Census 2000 from the Integrated Public Use Microdata Series (IPUMS) with those from an analysis of restricted access census files available only through Census Bureau Research Data Centers (RDCs). The internal files allow the identification of small geographic regions to measure local economic conditions. This analysis will help gauge the value of the restricted access data by presenting a benchmark using public data.

Virtually all quantitative microdata used by social scientists derive from samples that incorporate clustering, stratification, and weighting adjustments (Kish 1965, 1992). Such data can yield standard error estimates that differ dramatically from those derived from a simple random sample of the same size. Researchers using historical U.S. census microdata, however, usually apply methods designed for simple random samples. The resulting p values and confidence intervals could be inaccurate and could lead to erroneous research conclusions. Because U.S. census microdata samples are among the most widely used sources for social science and policy research, the need for reliable standard error estimation is critical. We evaluate the historical microdata samples of the Integrated Public Use Microdata Series (IPUMS) project from 1850 to 1950 in order to determine (1) the impact of sample design on standard error estimates, and (2) how to apply modern standard error estimation software to historical census samples. We exploit a unique new data source from the 1880 census to validate our methods for standard error estimation, and then we apply this approach to the 18501870 and 19001950 decennial censuses. We conclude that Taylor series estimation can be used effectively with the historical decennial census microdata samples and should be applied in research analyses that have the potential for substantial clustering effects

Virtually all quantitative microdata used by social scientists derive from samples that incorporate clustering, stratification, and weighting adjustments (Kish 1992, 1965). Such data can yield standard error estimates that differ dramatically from a simple random sample of the same size. Researchers using historical U.S. census microdata, however, usually apply methods designed for simple random samples. The resulting p-values and confidence intervals could be inaccurate and could lead to erroneous research conclusions. Because U.S. census microdata samples are among the most widely-used sources for social science and policy research, the need for reliable standard error estimation is critical. We evaluate the historical microdata samples of the IPUMS project from 1850-1930 in order to determine (1) the impact of sample design on standard error estimates and (2) how to apply modern standard error estimation software to historical census samples. We exploit a unique new data source from the 1880 census to validate our methods for standard error estimation and then we apply this approach to the 1850-1870 and 1900-1930 decennial censuses. We conclude that Taylor series estimation can be used effectively with the historical decennial census microdata samples, and should be applied in research analyses that have the potential for substantial clustering effects.