Stephen L. Morgan’s research while affiliated with Johns Hopkins University and other places

The five decades of results produced by analysts of the General Social Survey (GSS) have enriched our understanding of social change, but some core modeling challenges remain. This article proposes that we more fully engage in the development of targeted models of period-based attitude and opinion change, using counterfactual reasoning, as we continue to model cohort replacement. This shift is also consistent with the recent literature on age, period, and cohort analysis, which argues for attention to age varying period effects. Two outcomes are modeled to provide material for the argument: support for government spending on drug addiction and rehabilitation and the valuation of obedience as a goal for child behavioral development.

The General Social Survey (GSS) shows that many self-identified white adults continue to hold racial attitudes that can be regarded, collectively, as a persistent social problem. Similar to findings from the analysis of electoral surveys, the GSS also shows that these racial attitudes have more strongly predicted political behavior since 2012. However, and in contrast to group-identity interpretations of these patterns, the increase in predictive power since 2012 is attributable to a positive development: above and beyond the effects of cohort replacement, support for compensatory interventions to address black–white inequalities has increased substantially, whereas prejudice and bigotry have decreased slightly. Because these changes have been larger on the political left than on the political right, the attitudes have gained in overall predictive power.

The linear dependence of age, period, and birth cohort is a challenge for the analysis of social change. With either repeated cross-sectional data or conventional panel data, raw change cannot be decomposed into over-time differences that are attributable to the effects of common experiences of alternative birth cohorts, features of the periods under observation, and the cumulation of lifecourse aging. This article proposes a rolling panel model for cohort, period, and aging effects, suggested by and tuned to the treble panel data collected for the General Social Survey from 2006 through 2014. While the model does not offer a general solution for the identification of the classical age-period-cohort accounting model, it yields warranted interpretations under plausible assumptions that are reasonable for many outcomes of interest. In particular, if aging effects can be assumed to be invariant over the course of an observation interval, and if separate panel samples of the full age distribution overlap within the same observation interval, then period and aging effects can be parameterized and interpreted separately, adjusted for cohort differences that pulse through the same observation interval. The estimated cohort effects during the observation interval are then interpretable as effects during the observation interval of entangled period and cumulated aging differences from before the observation interval.

The linear dependence of age, period, and birth cohort is a challenge for the analysis of social change. With either repeated cross-sectional data or conventional panel data, raw change cannot be decomposed into over-time differences that are attributable to the effects of common experiences of alternative birth cohorts, features of the periods under observation, and the cumulation of lifecourse aging. This article proposes a rolling panel model for cohort, period, and aging effects, suggested by and tuned to the treble panel data collected for the General Social Survey (GSS) from 2006 through 2014. While the model does not offer a general solution for the identification of the classical age-period-cohort (APC) accounting model, it yields warranted interpretations under plausible assumptions that are reasonable for many outcomes of interest. In particular, if aging effects can be assumed to be invariant over the course of an observation interval, and if separate panel samples of the full age distribution overlap within the same observation interval, then period and aging effects can be parameterized and interpreted separately, adjusted for cohort differences that pulse through the same observation interval. The estimated cohort effects during the observation interval are then interpretable as effects during the observation interval of entangled period and cumulated aging differences from before the observation interval.

In the United States, women are more likely than men to enter and complete college, but they remain underrepresented among baccalaureates in science-related majors. We show that in a cohort of college entrants who graduated from high school in 2004, men were more than twice as likely as women to complete baccalaureate degrees in science, technology, engineering, and mathematics (STEM) fields, including premed fields, and more likely to persist in STEM/biomed after entering these majors by sophomore year. Conversely, women were more than twice as likely as men to earn baccalaureates in a health field, although persistence in health was low for both genders. We show that gender gaps in high school academic achievement, self-assessed math ability, and family-work orientation are only weakly associated with gender gaps in STEM completion and persistence. Gender differences in occupational plans, by contrast, are strongly associated with gender gaps in STEM outcomes, even in models that assume plans are endogenous to academic achievement, self-assessed math ability, and family-work orientation. These results can inform efforts to mitigate gender gaps in STEM attainment.

After an explanation of the structure of the 2006-2014 rolling panel of the General Social Survey (GSS), this report details models that estimate six sets of alternative predicted probabilities of attrition for all baseline sample members. The report then explains the cross-sectional GSS weights distributed with the data, and it shows how the estimated probabilities of attrition can be used to specify panel weights that adjust for attrition. Alternative approaches are discussed in conclusion. Code and data are provided in the associated repository.

Through an analysis of validated voters in the 2016 American National Election Study, this article considers the voters who supported Obama in 2012 and Trump in 2016. More than 5.7 million in total, Obama-to-Trump voters were crucial to Trump’s victory in the Electoral College. They were more likely to be white, working class, and resident in the Midwest. They had lower levels of political interest, were centrist in both party affiliation and ideology, and were late deciders for the 2016 election. On economic interests, they were centrists, except for trade policy, which they viewed, on average, as a greater threat than other voters. They claimed to have more experience with economic vulnerability than Democratic loyalists of comparable social standing. On racial attitudes, including the racialized economic topic of immigration, they had a profile similar to Republican loyalists. While their support of Trump may be attributable to surging white nativism, this article argues for an alternative explanation. Voters who were attracted by Trump’s economic populism only joined his coalition if they could accept his racialized rhetoric. As a result, the Trump bandwagon predominantly attracted generically bigoted voters with racial attitudes similar to Republican loyalists.

Through an analysis of validated voters in the 2016 American National Election Study, this article considers the voters who supported Obama in 2012 and Trump in 2016. More than 5.7 million in total, Obama-to-Trump voters were essential to Trump’s victory in the Electoral College. They were more likely to be white, working class, and resident in the Midwest. They had lower levels of political interest, were centrist in both party affiliation and ideology, and were late deciders for the 2016 election. On economic interests, they were centrists, except for trade policy, which they viewed, on average, as a greater threat than other voters. They claimed to have more experience with economic vulnerability than Democratic loyalists of comparable social standing. On racial attitudes, including the racialized economic topic of immigration, they had a profile similar to Republican loyalists. While their support of Trump may be attributable to surging white nativism, this article argues for an alternative explanation. Voters who were attracted by Trump’s economic populism only joined his coalition if they could accept his racialized rhetoric. As a result, the Trump bandwagon predominantly attracted generically bigoted voters with racial attitudes similar to Republican loyalists.

The author thanks Professor Mutz for her informative reaction to his article. In this six-part response, the author first addresses Professor Mutz’s new claim that “Morgan’s interpretation suggests a misunderstanding of the panel models.” The author explains that this concern with his understanding can be set aside because Mutz’s interpretations of her own fixed-effects models are incorrect. The author then discusses very briefly four areas of disagreement that readers will want to judge on their own: the value of prejudice-incorporating explanations in comparison with status threat–only explanations, measurement assumptions about support for free trade, the value of adjustments for party identification, and how best to consider the political preferences of nonwhite voters when evaluating the status-threat explanation. The author concludes with a defense of two of his own prior published articles that Mutz critiques in her comment in an apparent attempt to widen the field of contestation.