Adam S Lauring, Mark W Tenforde, James D Chappell, Manjusha Gaglani, Adit A Ginde, Tresa McNeal, Shekhar Ghamande, David J Douin, H Keipp Talbot, Jonathan D Casey, Nicholas M Mohr, Anne Zepeski, Nathan I Shapiro, Kevin W Gibbs, D Clark Files, David N Hager, Arber Shehu, Matthew E Prekker, Heidi L Erickson, Matthew C Exline, Michelle N Gong, Amira Mohamed, Nicholas J Johnson, Vasisht Srinivasan, Jay S Steingrub, Ithan D Peltan, Samuel M Brown, Emily T Martin, Arnold S Monto, Akram Khan, Catherine L Hough, Laurence W Busse, Caitlin C Ten Lohuis, Abhijit Duggal, Jennifer G Wilson, Alexandra June Gordon, Nida Qadir, Steven Y Chang, Christopher Mallow, Carolina Rivas, Hilary M Babcock, Jennie H Kwon, Natasha Halasa, Carlos G Grijalva, Todd W Rice, William B Stubblefield, Adrienne Baughman, Kelsey N Womack, Jillian P Rhoads, Christopher J Lindsell, Kimberly W Hart, Yuwei Zhu, Katherine Adams, Stephanie J Schrag, Samantha M Olson, Miwako Kobayashi, Jennifer R Verani, Manish M Patel, Wesley H Self
<p><strong>Objectives: </strong>To characterize the clinical severity of covid-19 associated with the alpha, delta, and omicron SARS-CoV-2 variants among adults admitted to hospital and to compare the effectiveness of mRNA vaccines to prevent hospital admissions related to each variant.</p><p><strong>Design: </strong>Case-control study.</p><p><strong>Setting: </strong>21 hospitals across the United States.</p><p><strong>Participants: </strong>11 690 adults (≥18 years) admitted to hospital: 5728 with covid-19 (cases) and 5962 without covid-19 (controls). Patients were classified into SARS-CoV-2 variant groups based on viral whole genome sequencing, and, if sequencing did not reveal a lineage, by the predominant circulating variant at the time of hospital admission: alpha (11 March to 3 July 2021), delta (4 July to 25 December 2021), and omicron (26 December 2021 to 14 January 2022).</p><p><strong>Main outcome measures: </strong>Vaccine effectiveness calculated using a test negative design for mRNA vaccines to prevent covid-19 related hospital admissions by each variant (alpha, delta, omicron). Among patients admitted to hospital with covid-19, disease severity on the World Health Organization's clinical progression scale was compared among variants using proportional odds regression.</p><p><strong>Results: </strong>Effectiveness of the mRNA vaccines to prevent covid-19 associated hospital admissions was 85% (95% confidence interval 82% to 88%) for two vaccine doses against the alpha variant, 85% (83% to 87%) for two doses against the delta variant, 94% (92% to 95%) for three doses against the delta variant, 65% (51% to 75%) for two doses against the omicron variant; and 86% (77% to 91%) for three doses against the omicron variant. In-hospital mortality was 7.6% (81/1060) for alpha, 12.2% (461/3788) for delta, and 7.1% (40/565) for omicron. Among unvaccinated patients with covid-19 admitted to hospital, severity on the WHO clinical progression scale was higher for the delta versus alpha variant (adjusted proportional odds ratio 1.28, 95% confidence interval 1.11 to 1.46), and lower for the omicron versus delta variant (0.61, 0.49 to 0.77). Compared with unvaccinated patients, severity was lower for vaccinated patients for each variant, including alpha (adjusted proportional odds ratio 0.33, 0.23 to 0.49), delta (0.44, 0.37 to 0.51), and omicron (0.61, 0.44 to 0.85).</p><p><strong>Conclusions: </strong>mRNA vaccines were found to be highly effective in preventing covid-19 associated hospital admissions related to the alpha, delta, and omicron variants, but three vaccine doses were required to achieve protection against omicron similar to the protection that two doses provided against the delta and alpha variants. Among adults admitted to hospital with covid-19, the omicron variant was associated with less severe disease than the delta variant but still resulted in substantial morbidity and mortality. Vaccinated patients admitted to hospital with cov
{"title":"Clinical severity of, and effectiveness of mRNA vaccines against, covid-19 from omicron, delta, and alpha SARS-CoV-2 variants in the United States: prospective observational study.","authors":"Adam S Lauring, Mark W Tenforde, James D Chappell, Manjusha Gaglani, Adit A Ginde, Tresa McNeal, Shekhar Ghamande, David J Douin, H Keipp Talbot, Jonathan D Casey, Nicholas M Mohr, Anne Zepeski, Nathan I Shapiro, Kevin W Gibbs, D Clark Files, David N Hager, Arber Shehu, Matthew E Prekker, Heidi L Erickson, Matthew C Exline, Michelle N Gong, Amira Mohamed, Nicholas J Johnson, Vasisht Srinivasan, Jay S Steingrub, Ithan D Peltan, Samuel M Brown, Emily T Martin, Arnold S Monto, Akram Khan, Catherine L Hough, Laurence W Busse, Caitlin C Ten Lohuis, Abhijit Duggal, Jennifer G Wilson, Alexandra June Gordon, Nida Qadir, Steven Y Chang, Christopher Mallow, Carolina Rivas, Hilary M Babcock, Jennie H Kwon, Natasha Halasa, Carlos G Grijalva, Todd W Rice, William B Stubblefield, Adrienne Baughman, Kelsey N Womack, Jillian P Rhoads, Christopher J Lindsell, Kimberly W Hart, Yuwei Zhu, Katherine Adams, Stephanie J Schrag, Samantha M Olson, Miwako Kobayashi, Jennifer R Verani, Manish M Patel, Wesley H Self","doi":"10.1136/bmj-2021-069761","DOIUrl":"10.1136/bmj-2021-069761","url":null,"abstract":"<p><strong>Objectives: </strong>To characterize the clinical severity of covid-19 associated with the alpha, delta, and omicron SARS-CoV-2 variants among adults admitted to hospital and to compare the effectiveness of mRNA vaccines to prevent hospital admissions related to each variant.</p><p><strong>Design: </strong>Case-control study.</p><p><strong>Setting: </strong>21 hospitals across the United States.</p><p><strong>Participants: </strong>11 690 adults (≥18 years) admitted to hospital: 5728 with covid-19 (cases) and 5962 without covid-19 (controls). Patients were classified into SARS-CoV-2 variant groups based on viral whole genome sequencing, and, if sequencing did not reveal a lineage, by the predominant circulating variant at the time of hospital admission: alpha (11 March to 3 July 2021), delta (4 July to 25 December 2021), and omicron (26 December 2021 to 14 January 2022).</p><p><strong>Main outcome measures: </strong>Vaccine effectiveness calculated using a test negative design for mRNA vaccines to prevent covid-19 related hospital admissions by each variant (alpha, delta, omicron). Among patients admitted to hospital with covid-19, disease severity on the World Health Organization's clinical progression scale was compared among variants using proportional odds regression.</p><p><strong>Results: </strong>Effectiveness of the mRNA vaccines to prevent covid-19 associated hospital admissions was 85% (95% confidence interval 82% to 88%) for two vaccine doses against the alpha variant, 85% (83% to 87%) for two doses against the delta variant, 94% (92% to 95%) for three doses against the delta variant, 65% (51% to 75%) for two doses against the omicron variant; and 86% (77% to 91%) for three doses against the omicron variant. In-hospital mortality was 7.6% (81/1060) for alpha, 12.2% (461/3788) for delta, and 7.1% (40/565) for omicron. Among unvaccinated patients with covid-19 admitted to hospital, severity on the WHO clinical progression scale was higher for the delta versus alpha variant (adjusted proportional odds ratio 1.28, 95% confidence interval 1.11 to 1.46), and lower for the omicron versus delta variant (0.61, 0.49 to 0.77). Compared with unvaccinated patients, severity was lower for vaccinated patients for each variant, including alpha (adjusted proportional odds ratio 0.33, 0.23 to 0.49), delta (0.44, 0.37 to 0.51), and omicron (0.61, 0.44 to 0.85).</p><p><strong>Conclusions: </strong>mRNA vaccines were found to be highly effective in preventing covid-19 associated hospital admissions related to the alpha, delta, and omicron variants, but three vaccine doses were required to achieve protection against omicron similar to the protection that two doses provided against the delta and alpha variants. Among adults admitted to hospital with covid-19, the omicron variant was associated with less severe disease than the delta variant but still resulted in substantial morbidity and mortality. Vaccinated patients admitted to hospital with cov","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"43 1","pages":"e069761"},"PeriodicalIF":0.0,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8905308/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86913270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.1177/00811750211071129
Amelie Pedneault, Dale W. Willits
Contextual effects refer to the process by which responses given to survey questions can be affected by question order. Generally, contextual effects harm data measurement validity by introducing bias and increasing measurement error; the risk is that responses to a survey’s later questions are partly affected not only by the substance of the question but also by the preceding questions. Two opposite effects are possible: a carryover effect refers to the assimilation of later questions into those previously asked, and a backfire effect refers to the contrasting of earlier and later questions. In the case where a stereotype is activated in earlier questions of a survey, the previous literature suggests a carryover effect is more likely. The present study tests whether this is also the case in factorial vignette research by examining the influence of first presenting a vignette that corresponds more closely to a stereotypical view of sexual abuse. Results indicate a backfire effect, pointing to the distinctively different way in which vignette scenarios activate stereotypes compared to general survey questions. The results also highlight the need for researchers to control for contextual ordering effects when modeling factorial vignette data.
{"title":"Asking about the Worst First: An Examination of Contextual Effects in Factorial Vignettes","authors":"Amelie Pedneault, Dale W. Willits","doi":"10.1177/00811750211071129","DOIUrl":"https://doi.org/10.1177/00811750211071129","url":null,"abstract":"Contextual effects refer to the process by which responses given to survey questions can be affected by question order. Generally, contextual effects harm data measurement validity by introducing bias and increasing measurement error; the risk is that responses to a survey’s later questions are partly affected not only by the substance of the question but also by the preceding questions. Two opposite effects are possible: a carryover effect refers to the assimilation of later questions into those previously asked, and a backfire effect refers to the contrasting of earlier and later questions. In the case where a stereotype is activated in earlier questions of a survey, the previous literature suggests a carryover effect is more likely. The present study tests whether this is also the case in factorial vignette research by examining the influence of first presenting a vignette that corresponds more closely to a stereotypical view of sexual abuse. Results indicate a backfire effect, pointing to the distinctively different way in which vignette scenarios activate stereotypes compared to general survey questions. The results also highlight the need for researchers to control for contextual ordering effects when modeling factorial vignette data.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"52 1","pages":"103 - 118"},"PeriodicalIF":3.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42651125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-01DOI: 10.1177/00811750211071130
S. Yuen, Gary Tang, Francis L. F. Lee, Edmund W. Cheng
Protest survey is a standard tool for scholars to understand protests. However, although protest survey methods are well established, the occurrence of spontaneous and leaderless protests has created new challenges for researchers. Not only do their unpredictable occurrences hinder planning, their fluidity also creates problems in obtaining representative samples. This article addresses these challenges based on our research during Hong Kong’s Anti-Extradition Law Amendment Bill Movement. We propose a mixed-mode sampling method combining face-to-face survey and smartphone-based online survey (onsite and post hoc), which can maximize sample sizes while ensuring representativeness in a cost-effective manner. Test results indicate that key variables from the survey modes are not statistically different in a consistent manner, except for age. Our findings show mixed-mode sampling can better capture protesters’ characteristics in contemporary protests and is replicable in other contexts.
{"title":"Surveying Spontaneous Mass Protests: Mixed-mode Sampling and Field Methods","authors":"S. Yuen, Gary Tang, Francis L. F. Lee, Edmund W. Cheng","doi":"10.1177/00811750211071130","DOIUrl":"https://doi.org/10.1177/00811750211071130","url":null,"abstract":"Protest survey is a standard tool for scholars to understand protests. However, although protest survey methods are well established, the occurrence of spontaneous and leaderless protests has created new challenges for researchers. Not only do their unpredictable occurrences hinder planning, their fluidity also creates problems in obtaining representative samples. This article addresses these challenges based on our research during Hong Kong’s Anti-Extradition Law Amendment Bill Movement. We propose a mixed-mode sampling method combining face-to-face survey and smartphone-based online survey (onsite and post hoc), which can maximize sample sizes while ensuring representativeness in a cost-effective manner. Test results indicate that key variables from the survey modes are not statistically different in a consistent manner, except for age. Our findings show mixed-mode sampling can better capture protesters’ characteristics in contemporary protests and is replicable in other contexts.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"52 1","pages":"75 - 102"},"PeriodicalIF":3.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49169680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1177/00811750211053370
Jeffrey L. Jensen, Daniel Karell, Cole Tanigawa-Lau, Nizar Habash, Mai Oudah, Dhia Fairus Shofia Fani
Computational methods have become widespread in the social sciences, but probabilistic language models remain relatively underused. We introduce language models to a general social science readership. First, we offer an accessible explanation of language models, detailing how they estimate the probability of a piece of language, such as a word or sentence, on the basis of the linguistic context. Second, we apply language models in an illustrative analysis to demonstrate the mechanics of using these models in social science research. The example application uses language models to classify names in a large administrative database; the classifications are then used to measure a sociologically important phenomenon: the spatial variation of religiosity. This application highlights several advantages of language models, including their effectiveness in classifying text that contains variation around the base structures, as is often the case with localized naming conventions and dialects. We conclude by discussing language models’ potential to contribute to sociological research beyond classification through their ability to generate language.
{"title":"Language Models in Sociological Research: An Application to Classifying Large Administrative Data and Measuring Religiosity","authors":"Jeffrey L. Jensen, Daniel Karell, Cole Tanigawa-Lau, Nizar Habash, Mai Oudah, Dhia Fairus Shofia Fani","doi":"10.1177/00811750211053370","DOIUrl":"https://doi.org/10.1177/00811750211053370","url":null,"abstract":"Computational methods have become widespread in the social sciences, but probabilistic language models remain relatively underused. We introduce language models to a general social science readership. First, we offer an accessible explanation of language models, detailing how they estimate the probability of a piece of language, such as a word or sentence, on the basis of the linguistic context. Second, we apply language models in an illustrative analysis to demonstrate the mechanics of using these models in social science research. The example application uses language models to classify names in a large administrative database; the classifications are then used to measure a sociologically important phenomenon: the spatial variation of religiosity. This application highlights several advantages of language models, including their effectiveness in classifying text that contains variation around the base structures, as is often the case with localized naming conventions and dialects. We conclude by discussing language models’ potential to contribute to sociological research beyond classification through their ability to generate language.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"52 1","pages":"30 - 52"},"PeriodicalIF":3.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48332990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-28DOI: 10.1177/00811750211046307
Ryan P. Thombs, Xiaorui Huang, Jared Berry Fitzgerald
Modeling asymmetric relationships is an emerging subject of interest among sociologists. York and Light advanced a method to estimate asymmetric models with panel data, which was further developed by Allison. However, little attention has been given to the large-N, large-T case, wherein autoregression, slope heterogeneity, and cross-sectional dependence are important issues to consider. The authors fill this gap by conducting Monte Carlo experiments comparing the bias and power of the fixed-effects estimator to a set of heterogeneous panel estimators. The authors find that dynamic misspecification can produce substantial biases in the coefficients. Furthermore, even when the dynamics are correctly specified, the fixed-effects estimator will produce inconsistent and unstable estimates of the long-run effects in the presence of slope heterogeneity. The authors demonstrate these findings by testing for directional asymmetry in the economic development–CO2 emissions relationship, a key question in macro sociology, using data for 66 countries from 1971 to 2015. The authors conclude with a set of methodological recommendations on modeling directional asymmetry.
{"title":"What Goes Up Might Not Come Down: Modeling Directional Asymmetry with Large-N, Large-T Data","authors":"Ryan P. Thombs, Xiaorui Huang, Jared Berry Fitzgerald","doi":"10.1177/00811750211046307","DOIUrl":"https://doi.org/10.1177/00811750211046307","url":null,"abstract":"Modeling asymmetric relationships is an emerging subject of interest among sociologists. York and Light advanced a method to estimate asymmetric models with panel data, which was further developed by Allison. However, little attention has been given to the large-N, large-T case, wherein autoregression, slope heterogeneity, and cross-sectional dependence are important issues to consider. The authors fill this gap by conducting Monte Carlo experiments comparing the bias and power of the fixed-effects estimator to a set of heterogeneous panel estimators. The authors find that dynamic misspecification can produce substantial biases in the coefficients. Furthermore, even when the dynamics are correctly specified, the fixed-effects estimator will produce inconsistent and unstable estimates of the long-run effects in the presence of slope heterogeneity. The authors demonstrate these findings by testing for directional asymmetry in the economic development–CO2 emissions relationship, a key question in macro sociology, using data for 66 countries from 1971 to 2015. The authors conclude with a set of methodological recommendations on modeling directional asymmetry.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"52 1","pages":"1 - 29"},"PeriodicalIF":3.0,"publicationDate":"2021-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42559507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sequence analysis (SA) has gained increasing interest in social sciences for theholistic analysis of life course and other longitudinal data. The usual approach isto construct sequences, calculate dissimilarities, group similar sequences with clusteranalysis, and use cluster membership as a dependent or independent variable in a linear or nonlinear regression model.This approach may be problematic as the cluster memberships are assumed to befixed known characteristics of the subjects in subsequent analysis. Furthermore, often it is more reasonable to assume that individual sequences are mixtures of multiple ideal types rather than equal members of some group. Failing to account for these issues may lead to wrong conclusions about the nature of the studied relationships.In this paper, we bring forward and discuss the problems of the "traditional" useof SA clusters and compare four approaches for different types of data. We conduct a simulation study and an empirical study, demonstrating the importance of considering how sequences and outcomes are related and the need to adjust the analysis accordingly. In many typical social science applications, the traditional approach is prone to result in wrong conclusions and so-called position-dependent approaches such as representativeness should be preferred.
{"title":"From sequences to variables – Rethinking the relationship between sequences and outcomes","authors":"S. Helske, Jouni Helske, Guilherme Kenji Chihaya","doi":"10.31235/osf.io/srxag","DOIUrl":"https://doi.org/10.31235/osf.io/srxag","url":null,"abstract":"Sequence analysis (SA) has gained increasing interest in social sciences for theholistic analysis of life course and other longitudinal data. The usual approach isto construct sequences, calculate dissimilarities, group similar sequences with clusteranalysis, and use cluster membership as a dependent or independent variable in a linear or nonlinear regression model.This approach may be problematic as the cluster memberships are assumed to befixed known characteristics of the subjects in subsequent analysis. Furthermore, often it is more reasonable to assume that individual sequences are mixtures of multiple ideal types rather than equal members of some group. Failing to account for these issues may lead to wrong conclusions about the nature of the studied relationships.In this paper, we bring forward and discuss the problems of the \"traditional\" useof SA clusters and compare four approaches for different types of data. We conduct a simulation study and an empirical study, demonstrating the importance of considering how sequences and outcomes are related and the need to adjust the analysis accordingly. In many typical social science applications, the traditional approach is prone to result in wrong conclusions and so-called position-dependent approaches such as representativeness should be preferred.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"1 1","pages":""},"PeriodicalIF":3.0,"publicationDate":"2021-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45045791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-01Epub Date: 2021-03-04DOI: 10.1177/0081175021993503
Jennie E Brand, Jiahui Xu, Bernard Koch, Pablo Geraldo
Individuals do not respond uniformly to treatments, such as events or interventions. Sociologists routinely partition samples into subgroups to explore how the effects of treatments vary by selected covariates, such as race and gender, on the basis of theoretical priors. Data-driven discoveries are also routine, yet the analyses by which sociologists typically go about them are often problematic and seldom move us beyond our biases to explore new meaningful subgroups. Emerging machine learning methods based on decision trees allow researchers to explore sources of variation that they may not have previously considered or envisaged. In this article, the authors use tree-based machine learning, that is, causal trees, to recursively partition the sample to uncover sources of effect heterogeneity. Assessing a central topic in social inequality, college effects on wages, the authors compare what is learned from covariate and propensity score-based partitioning approaches with recursive partitioning based on causal trees. Decision trees, although superseded by forests for estimation, can be used to uncover subpopulations responsive to treatments. Using observational data, the authors expand on the existing causal tree literature by applying leaf-specific effect estimation strategies to adjust for observed confounding, including inverse propensity weighting, nearest neighbor matching, and doubly robust causal forests. We also assess localized balance metrics and sensitivity analyses to address the possibility of differential imbalance and unobserved confounding. The authors encourage researchers to follow similar data exploration practices in their work on variation in sociological effects and offer a straightforward framework by which to do so.
{"title":"Uncovering Sociological Effect Heterogeneity Using Tree-Based Machine Learning.","authors":"Jennie E Brand, Jiahui Xu, Bernard Koch, Pablo Geraldo","doi":"10.1177/0081175021993503","DOIUrl":"10.1177/0081175021993503","url":null,"abstract":"<p><p>Individuals do not respond uniformly to treatments, such as events or interventions. Sociologists routinely partition samples into subgroups to explore how the effects of treatments vary by selected covariates, such as race and gender, on the basis of theoretical priors. Data-driven discoveries are also routine, yet the analyses by which sociologists typically go about them are often problematic and seldom move us beyond our biases to explore new meaningful subgroups. Emerging machine learning methods based on decision trees allow researchers to explore sources of variation that they may not have previously considered or envisaged. In this article, the authors use tree-based machine learning, that is, causal trees, to recursively partition the sample to uncover sources of effect heterogeneity. Assessing a central topic in social inequality, college effects on wages, the authors compare what is learned from covariate and propensity score-based partitioning approaches with recursive partitioning based on causal trees. Decision trees, although superseded by forests for estimation, can be used to uncover subpopulations responsive to treatments. Using observational data, the authors expand on the existing causal tree literature by applying leaf-specific effect estimation strategies to adjust for observed confounding, including inverse propensity weighting, nearest neighbor matching, and doubly robust causal forests. We also assess localized balance metrics and sensitivity analyses to address the possibility of differential imbalance and unobserved confounding. The authors encourage researchers to follow similar data exploration practices in their work on variation in sociological effects and offer a straightforward framework by which to do so.</p>","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"51 2","pages":"189-223"},"PeriodicalIF":3.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9897445/pdf/nihms-1849062.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10652104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-25DOI: 10.1177/00811750211016033
Scott W. Duxbury
Panel data analysis is common in the social sciences. Fixed effects models are a favorite among sociologists because they control for unobserved heterogeneity (unexplained variation) among cross-sectional units, but estimates are biased when there is unobserved heterogeneity in the underlying time trends. Two-way fixed effects models adjust for unobserved time heterogeneity but are inefficient, cannot include unit-invariant variables, and eliminate common trends: the portion of variance in a time-varying variable that is invariant across cross-sectional units. This article introduces a general panel model that can include unit-invariant variables, corrects for unobserved time heterogeneity, and provides the effect of common trends while also allowing for unobserved unit heterogeneity, time-varying coefficients, and time-invariant variables. One-way and two-way fixed effects models are shown to be restrictive forms of this general model. Other restrictive forms are also derived that offer all the usual advantages of one-way and two-way fixed effects models but account for unobserved time heterogeneity. The author uses the models to examine the increase in state incarceration rates between 1970 and 2015.
{"title":"A General Panel Model for Unobserved Time Heterogeneity with Application to the Politics of Mass Incarceration","authors":"Scott W. Duxbury","doi":"10.1177/00811750211016033","DOIUrl":"https://doi.org/10.1177/00811750211016033","url":null,"abstract":"Panel data analysis is common in the social sciences. Fixed effects models are a favorite among sociologists because they control for unobserved heterogeneity (unexplained variation) among cross-sectional units, but estimates are biased when there is unobserved heterogeneity in the underlying time trends. Two-way fixed effects models adjust for unobserved time heterogeneity but are inefficient, cannot include unit-invariant variables, and eliminate common trends: the portion of variance in a time-varying variable that is invariant across cross-sectional units. This article introduces a general panel model that can include unit-invariant variables, corrects for unobserved time heterogeneity, and provides the effect of common trends while also allowing for unobserved unit heterogeneity, time-varying coefficients, and time-invariant variables. One-way and two-way fixed effects models are shown to be restrictive forms of this general model. Other restrictive forms are also derived that offer all the usual advantages of one-way and two-way fixed effects models but account for unobserved time heterogeneity. The author uses the models to examine the increase in state incarceration rates between 1970 and 2015.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"51 1","pages":"348 - 377"},"PeriodicalIF":3.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1177/00811750211016033","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48076745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-24DOI: 10.1177/00811750211014242
Bianca Manago, Trenton D. Mize, Long Doan
Laboratory experiments have a long history within sociology, with their ability to test causality and their utility for directly observing behavior providing key advantages. One influential social psychological field, status characteristics and expectation states theory, has almost exclusively used laboratory experiments to test the theory. Unfortunately, laboratory experiments are resource intensive, requiring a research pool, laboratory space, and considerable amounts of time. For these and other reasons, social scientists are increasingly exploring the possibility of moving experiments from the lab to an online platform. Despite the advantages of the online setting, the transition from the lab is challenging, especially when studying behavior. In this project, we develop methods to translate the traditional status characteristics experimental setting from the laboratory to online. We conducted parallel laboratory and online behavioral experiments using three tasks from the status literature, comparing each task’s ability to differentiate on the basis of status distinctions. The tasks produce equivalent results in the online and laboratory environment; however, not all tasks are equally sensitive to status differences. Finally, we provide more general guidance on how to move vital aspects of laboratory studies, such as debriefing, suspicion checks, and scope condition checks, to the online setting.
{"title":"Can You Really Study an Army on the Internet? Comparing How Status Tasks Perform in the Laboratory and Online Settings","authors":"Bianca Manago, Trenton D. Mize, Long Doan","doi":"10.1177/00811750211014242","DOIUrl":"https://doi.org/10.1177/00811750211014242","url":null,"abstract":"Laboratory experiments have a long history within sociology, with their ability to test causality and their utility for directly observing behavior providing key advantages. One influential social psychological field, status characteristics and expectation states theory, has almost exclusively used laboratory experiments to test the theory. Unfortunately, laboratory experiments are resource intensive, requiring a research pool, laboratory space, and considerable amounts of time. For these and other reasons, social scientists are increasingly exploring the possibility of moving experiments from the lab to an online platform. Despite the advantages of the online setting, the transition from the lab is challenging, especially when studying behavior. In this project, we develop methods to translate the traditional status characteristics experimental setting from the laboratory to online. We conducted parallel laboratory and online behavioral experiments using three tasks from the status literature, comparing each task’s ability to differentiate on the basis of status distinctions. The tasks produce equivalent results in the online and laboratory environment; however, not all tasks are equally sensitive to status differences. Finally, we provide more general guidance on how to move vital aspects of laboratory studies, such as debriefing, suspicion checks, and scope condition checks, to the online setting.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"51 1","pages":"319 - 347"},"PeriodicalIF":3.0,"publicationDate":"2021-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1177/00811750211014242","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49371565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-22DOI: 10.1177/00811750211003922
R. Agans, D. Zeng, B. Shook‐Sa, Marcella H. Boynton, N. Brewer, E. Sutfin, A. Goldstein, S. Noar, Q. Vallejos, Tara L Queen, J. Bowling, K. Ribisl
Random digit dialing (RDD) telephone sampling, although experiencing declining response rates, remains one of the most accurate and cost-effective data collection methods for generating national population-based estimates. Such methods, however, are inefficient when sampling hard-to-reach populations because the costs of recruiting sufficient sample sizes to produce reliable estimates tend to be cost prohibitive. The authors implemented a novel respondent-driven sampling (RDS) approach to oversample cigarette smokers and lesbian, gay, bisexual, and transgender (LGBT) people. The new methodology selects RDS referrals or seeds from a probability-based RDD sampling frame and treats the social networks as clusters in the weighting and analysis, thus eliminating the intricate assumptions of RDS. The authors refer to this approach as RDD+RDS. In 2016 and 2017, a telephone survey was conducted on tobacco-related topics with a national sample of 4,208 U.S. adults, as well as 756 referral-based respondents. The RDD+RDS estimates were comparable with stand-alone RDD estimates, suggesting that the addition of RDS responses from social networks improved the precision of the estimates without introducing significant bias. The authors also conducted an experiment to determine whether the number of recruits would vary on the basis of how the RDS recruitment question specified the recruitment population (closeness of relationship, time since last contact, and LGBT vs. tobacco user), and significant differences were found in the number of referrals provided on the basis of question wording. The RDD+RDS sampling approach, as an adaptation of standard RDD methodology, is a practical tool for survey methodologists that provides an efficient strategy for oversampling rare or elusive populations.
{"title":"Using Social Networks to Supplement RDD Telephone Surveys to Oversample Hard-to-Reach Populations: A New RDD+RDS Approach","authors":"R. Agans, D. Zeng, B. Shook‐Sa, Marcella H. Boynton, N. Brewer, E. Sutfin, A. Goldstein, S. Noar, Q. Vallejos, Tara L Queen, J. Bowling, K. Ribisl","doi":"10.1177/00811750211003922","DOIUrl":"https://doi.org/10.1177/00811750211003922","url":null,"abstract":"Random digit dialing (RDD) telephone sampling, although experiencing declining response rates, remains one of the most accurate and cost-effective data collection methods for generating national population-based estimates. Such methods, however, are inefficient when sampling hard-to-reach populations because the costs of recruiting sufficient sample sizes to produce reliable estimates tend to be cost prohibitive. The authors implemented a novel respondent-driven sampling (RDS) approach to oversample cigarette smokers and lesbian, gay, bisexual, and transgender (LGBT) people. The new methodology selects RDS referrals or seeds from a probability-based RDD sampling frame and treats the social networks as clusters in the weighting and analysis, thus eliminating the intricate assumptions of RDS. The authors refer to this approach as RDD+RDS. In 2016 and 2017, a telephone survey was conducted on tobacco-related topics with a national sample of 4,208 U.S. adults, as well as 756 referral-based respondents. The RDD+RDS estimates were comparable with stand-alone RDD estimates, suggesting that the addition of RDS responses from social networks improved the precision of the estimates without introducing significant bias. The authors also conducted an experiment to determine whether the number of recruits would vary on the basis of how the RDS recruitment question specified the recruitment population (closeness of relationship, time since last contact, and LGBT vs. tobacco user), and significant differences were found in the number of referrals provided on the basis of question wording. The RDD+RDS sampling approach, as an adaptation of standard RDD methodology, is a practical tool for survey methodologists that provides an efficient strategy for oversampling rare or elusive populations.","PeriodicalId":48140,"journal":{"name":"Sociological Methodology","volume":"51 1","pages":"270 - 289"},"PeriodicalIF":3.0,"publicationDate":"2021-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1177/00811750211003922","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43305520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：