1
|
Sokol R, Walton M, Lee D, Seewald L, Del Toro VM, Farooqui M, Sallabank G, Zimmerman M, Edberg M, Wang Y, Zakrison T, Tung EL, Hillegass WB, Vearrier L, Zhang L, Kutcher ME, Blachman-Demner D, Carter PM. Advancing Science to Prevent Firearm Violence in Communities: A Process for Harmonizing Studies to Develop Research Infrastructure. PREVENTION SCIENCE : THE OFFICIAL JOURNAL OF THE SOCIETY FOR PREVENTION RESEARCH 2024:10.1007/s11121-024-01723-5. [PMID: 39304578 DOI: 10.1007/s11121-024-01723-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/29/2024] [Indexed: 09/22/2024]
Abstract
The Community Firearm Violence Prevention Network (CFVP Network), funded by the National Institutes of Health (NIH), supports a network of research projects that develop and test interventions through collaborations with community partners to prevent firearm violence, injury, and mortality. The CFVP Network presents a unique opportunity to accelerate the science of preventing firearm injuries. The data harmonization workgroup of the CFVP Network led the process of aligning studies across the three unique inaugural network projects, with particular attention to how the CFVP Network could address current gaps in the science. The goal of the data harmonization workgroup was to align study measures, assessment timelines, and data management and archival processes across projects to enable robust cross-project analyses that accelerate the science of preventing firearm injuries. To accomplish this goal, the workgroup established the infrastructure to facilitate cross-project data collection, data sharing and archiving, and analyses. Among the three inaugural network projects, the workgroup's process resulted in harmonizing two assessment timepoints (baseline and one year post-implementation) and 60 constructs (with 31 identical standardized constructs). These harmonized products provide opportunities for novel analyses across the network projects. We expect that the harmonized study infrastructure developed through this process will catalyze future research focused on preventing firearm injury, including and extending beyond CFVP Network projects. The CFVP data harmonization workgroup's process can serve as a model for future networks that seek to build the science in a particular area.
Collapse
Affiliation(s)
- Rebeccah Sokol
- School of Social Work, University of Michigan, Ann Arbor, USA.
- Institute for Firearm Injury Prevention, Ann Arbor, USA.
| | - Maureen Walton
- Department of Psychiatry, Medical School, University of Michigan, University of Michigan, Ann Arbor, USA
| | - Daniel Lee
- Institute for Firearm Injury Prevention, Ann Arbor, USA
| | - Laura Seewald
- Institute for Firearm Injury Prevention, Ann Arbor, USA
- Department of Emergency Medicine, Medical School, University of Michigan, University of Michigan, Ann Arbor, USA
| | | | | | | | - Marc Zimmerman
- Institute for Firearm Injury Prevention, Ann Arbor, USA
- Department of Health Behavior and Health Education, School of Public Health, University of Michigan, Ann Arbor, USA
| | - Mark Edberg
- Department of Prevention and Community Health, Milken Institute School of Public Health, George Washington University, Washington, D.C, USA
| | - Yan Wang
- Department of Prevention and Community Health, Milken Institute School of Public Health, George Washington University, Washington, D.C, USA
| | - Tanya Zakrison
- Section of Trauma & Acute Care Surgery, University of Chicago, Chicago, USA
| | - Elizabeth L Tung
- Section of General Internal Medicine, University of Chicago, Chicago, USA
| | - William B Hillegass
- Department of Data Science, School of Public Health, University of Mississippi Medical Center, Jackson, USA
| | - Laura Vearrier
- Department of Emergency Medicine, School of Medicine, University of Mississippi Medical Center, Jackson, USA
| | - Lei Zhang
- School of Nursing, University of Mississippi Medical Center, Jackson, USA
| | - Matthew E Kutcher
- Department of Surgery-Trauma/Critical Care, School of Medicine, University of Mississippi Medical Center, Jackson, USA
| | - Dara Blachman-Demner
- Office of Behavioral and Social Sciences Research (OBSSR), National Institutes of Health, Bethesda, USA
| | - Patrick M Carter
- Institute for Firearm Injury Prevention, Ann Arbor, USA
- Department of Emergency Medicine, Medical School, University of Michigan, University of Michigan, Ann Arbor, USA
- Department of Health Behavior and Health Education, School of Public Health, University of Michigan, Ann Arbor, USA
| |
Collapse
|
2
|
Mun EY, Zhou Z, Huh D, Tan L, Li D, Tanner-Smith EE, Walters ST, Larimer ME. Brief Alcohol Interventions are Effective through 6 Months: Findings from Marginalized Zero-inflated Poisson and Negative Binomial Models in a Two-step IPD Meta-analysis. PREVENTION SCIENCE : THE OFFICIAL JOURNAL OF THE SOCIETY FOR PREVENTION RESEARCH 2023; 24:1608-1621. [PMID: 35976524 PMCID: PMC10678823 DOI: 10.1007/s11121-022-01420-1] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/02/2022] [Indexed: 12/14/2022]
Abstract
To evaluate and optimize brief alcohol interventions (BAIs), it is critical to have a credible overall effect size estimate as a benchmark. Estimating such an effect size has been challenging because alcohol outcomes often represent responses from a mixture of individuals: those at high risk for alcohol misuse, occasional nondrinkers, and abstainers. Moreover, some BAIs exclusively focus on heavy drinkers, whereas others take a universal prevention approach. Depending on sample characteristics, the outcome distribution might have many zeros or very few zeros and overdispersion; consequently, the most appropriate statistical model may differ across studies. We synthesized individual participant data (IPD) from 19 studies in Project INTEGRATE (Mun et al., 2015b) that randomly allocated participants to intervention and control groups (N = 7,704 participants, 38.4% men, 74.7% White, 58.5% first-year students). We sequentially estimated marginalized zero-inflated Poisson (Long et al., 2014) or negative binomial regression models to obtain covariate-adjusted, study-specific intervention effect estimates in the first step, which were subsequently combined in a random-effects meta-analysis model in the second step. BAIs produced a statistically significant 8% advantage in the mean number of drinks at both 1-3 months (RR = 0.92, 95% CI = [0.85, 0.98]) and 6 months (RR = 0.92, 95% CI = [0.85, 0.99]) compared to controls. At 9-12 months, there was no statistically significant difference in the mean number of drinks between BAIs and controls. In conclusion, BAIs are effective at reducing the mean number of drinks through at least 6 months post intervention. IPD can play a critical role in deriving findings that could not be obtained in original individual studies or standard aggregate data meta-analyses.
Collapse
Affiliation(s)
- Eun-Young Mun
- Department of Health Behavior and Health Systems, School of Public Health, University of North Texas Health Science Center, 3500 Camp Bowie Blvd., Fort Worth, TX, 76107, USA.
| | - Zhengyang Zhou
- Department of Biostatistics and Epidemiology, University of North Texas Health Science Center, Fort Worth, TX, 76107, USA
| | - David Huh
- School of Social Work, University of Washington, Seattle, WA, 98195, USA
| | - Lin Tan
- Department of Health Behavior and Health Systems, School of Public Health, University of North Texas Health Science Center, 3500 Camp Bowie Blvd., Fort Worth, TX, 76107, USA
| | - Dateng Li
- , 121 Westmoreland Ave, White Plains, NY, 10606, USA
| | - Emily E Tanner-Smith
- Department of Counseling Psychology and Human Services, University of Oregon, Eugene, OR, 97403, USA
| | - Scott T Walters
- Department of Health Behavior and Health Systems, School of Public Health, University of North Texas Health Science Center, 3500 Camp Bowie Blvd., Fort Worth, TX, 76107, USA
| | - Mary E Larimer
- Department of Psychiatry and Behavioral Sciences, University of Washington, Seattle, WA, 98195, USA
| |
Collapse
|
3
|
McDaniel HL, Saavedra LM, Morgan-López AA, Bradshaw CP, Lochman JE, Kaihoi CA, Powell NP, Qu L, Yaros AC. Harmonizing Social, Emotional, and Behavioral Constructs in Prevention Science: Digging into the Weeds of Aligning Disparate Measures. PREVENTION SCIENCE : THE OFFICIAL JOURNAL OF THE SOCIETY FOR PREVENTION RESEARCH 2023; 24:1581-1594. [PMID: 36753042 DOI: 10.1007/s11121-022-01467-0] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/08/2022] [Indexed: 02/09/2023]
Abstract
While integrative data analysis (IDA) presents great opportunity, it also necessitates a myriad of methodological decisions related to harmonizing disparate measures collected across multiple studies. There is a lack of step-by-step methodological guidance for harmonizing disparate measures of latent constructs differently conceptualized or operationalized across studies, such as social, emotional, and behavioral constructs often utilized in prevention science. The current paper addressed this gap by providing methodological guidance and a case illustration focused on harmonizing measures of disparately conceptualized and operationalized constructs. We do so by outlining a five-phased harmonization approach paired with an illustrative example of the approach as applied to harmonization of broadband latent emotional and behavioral health constructs assessed with different measures across studies. This approach builds on and expands upon procedures currently recommended in the IDA literature with parallels to best practices in test development procedures. The illustrative example of our phased approach is drawn from an IDA study of 11 randomized controlled trials of Coping Power (Lochman & Wells, 2004), an evidence-based preventive intervention. We demonstrate the harmonization of two constructs, internalizing and externalizing problems, as harmonized across the teacher-reported scales of the Achenbach System of Empirically Based Assessment (Achenbach, 1991a) and the Behavior Assessment System for Children (Reynolds & Kamphaus, 2004). Finally, we consider the potential strengths and limitations of this phased approach, underscoring areas for future methodological research and conclude with some recommendations.
Collapse
Affiliation(s)
- Heather L McDaniel
- School of Education and Human Development, University of Virginia, Charlottesville, VA, USA.
| | - Lissette M Saavedra
- Community Health Research Division, RTI International, Research Triangle Park, NC, USA
| | | | - Catherine P Bradshaw
- School of Education and Human Development, University of Virginia, Charlottesville, VA, USA
| | - John E Lochman
- Center for Youth Development and Intervention, University of Alabama, Tuscaloosa, AL, USA
| | - Chelsea A Kaihoi
- School of Education and Human Development, University of Virginia, Charlottesville, VA, USA
| | - Nicole P Powell
- Center for Youth Development and Intervention, University of Alabama, Tuscaloosa, AL, USA
| | - Lixin Qu
- Center for Youth Development and Intervention, University of Alabama, Tuscaloosa, AL, USA
| | - Anna C Yaros
- Community Health Research Division, RTI International, Research Triangle Park, NC, USA
| |
Collapse
|
4
|
Abstract
Stigma changes over time: it waxes and wanes through history, is manifested within humans who develop over time and is tied to statuses (such as attributes, illnesses and identities) that have varying courses. Despite the inherent fluidity of stigma, theories, research and interventions typically treat associations between stigma and health as stagnant. Consequently, the literature provides little insight into when experiences of stigma are most harmful to health and when stigma interventions should be implemented. In this Perspective, we argue that integrating time into stigma research can accelerate progress towards understanding and intervening in associations between stigma and health inequities. We situate time in relation to key concepts in stigma research, identify three timescales that are relevant for understanding stigma (historical context, human development and status course), and outline a time-based research agenda to improve scientists’ ability to understand and address stigma to improve health. Associations between stigma and health are typically treated as stagnant. In this Perspective, Earnshaw et al. argue that considering stigma in relation to historical, human development and status course timescales can advance progress in understanding and addressing stigma to improve health.
Collapse
|
5
|
Cole VT, Hussong AM, McNeish DM, Ennett ST, Rothenberg WA, Gottfredson NC, Faris RW. The Role of Social Position Within Peer Groups in Distress-Motivated Smoking Among Adolescents. J Stud Alcohol Drugs 2022; 83:420-429. [PMID: 35590183 PMCID: PMC9134997] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Accepted: 11/10/2021] [Indexed: 05/03/2023] Open
Abstract
OBJECTIVE The relationship between smoking and adolescents' peer relationships is complex, with studies showing increased risk of smoking for adolescents of both very high and very low social position. A key question is whether the impact of social position on smoking depends on an adolescent's level of coping motives (i.e., their desire to use smoking to mitigate negative affect). METHOD We assessed how social position predicts nicotine dependence in a longitudinal sample (N = 3,717; 44.8% male; mean age = 13.41 years) of adolescent lifetime smokers measured between 6th and 12th grades. Using both social network analysis and multilevel modeling, we assessed this question at the between-person and within-person level, hypothesizing that within-person decreases in social position would lead to increased risk of nicotine dependence among those with high levels of coping motives. RESULTS In contrast to our hypotheses, only interactions with the between-person measures of social position were found, with a slight negative relationship at low levels of coping motives. In addition, the main effect of coping motives was considerably stronger than that of social position at the between-person level, and social position had no significant within-person main effect on nicotine dependence risk. CONCLUSIONS These results suggest that adolescents with higher overall levels of social position among their peers may have slightly decreased risk for nicotine dependence, but only when coping motives are low. Counter to expectations, higher levels of nicotine dependence risk were not linked to fluctuations in social position.
Collapse
Affiliation(s)
- Veronica T. Cole
- Department of Psychology, Wake Forest University, Winston-Salem, North Carolina
| | - Andrea M. Hussong
- Department of Psychology and Neuroscience, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina
| | | | - Susan T. Ennett
- Department of Psychology and Neuroscience, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina
| | | | - Nisha C. Gottfredson
- Gillings School of Global Public Health, Psychology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina
| | - Robert W. Faris
- Department of Sociology, University of California at Davis, Davis, California
| |
Collapse
|
6
|
Warchoł-Biedermann K, Bugajski P, Budzicz Ł, Ziarko M, Jasielska A, Samborski W, Daroszewski P, Greberski K, Bączyk G, Karoń J, Mojs E. Relationship between stress and alexithymia, emotional processing and negative/positive affect in medical staff working amid the COVID-19 pandemic. J Investig Med 2022; 70:428-435. [PMID: 34815298 PMCID: PMC8616640 DOI: 10.1136/jim-2021-001942] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/28/2021] [Indexed: 11/04/2022]
Abstract
The psychological burden of the COVID-19 pandemic may have a lasting effect on emotional well-being of healthcare workers. Medical personnel working at the time of the pandemic may experience elevated occupational stress due to the uncontrollability of the virus, high perceived risk of infection, poor understanding of the novel virus transmission routes and unavailability of effective antiviral agents. This study used path analysis to analyze the relationship between stress and alexithymia, emotional processing and negative/positive affect in healthcare workers. The sample included 167 nurses, 65 physicians and 53 paramedics. Sixty-two (21.75 %) respondents worked in COVID-19-designated hospitals. Respondents were administered the Toronto Alexithymia Scale-20, Cohen's Perceived Stress Scale, Emotional Processing Scale, and the Positive and Negative Affect Schedule. The model showed excellent fit indices (χ2 (2)=2.642, p=0.267; CFI=0.999, RMSEA=0.034, SRMR=0.015). Multiple group path analysis demonstrated physicians differed from nurses and paramedics at the model level (X2diff (7)=14.155, p<0.05 and X2diff (7)=18.642, p<0.01, respectively). The relationship between alexithymia and emotional processing was stronger in nurses than in physicians (difference in beta=0.27; p<0.05). Individual path χ2 tests also revealed significantly different paths across these groups. The results of the study may be used to develop evidence-based intervention programs promoting healthcare workers' mental health and well-being.
Collapse
Affiliation(s)
| | - Paweł Bugajski
- Department of Cardiovascular Disease Prevention, Poznan University of Medical Sciences, Poznan, Poland
- Department of General and Colorectal Surgery, Józef Strus Hospital, Poznan, Poland
| | - Łukasz Budzicz
- Department of Psychology, University of Zielona Gora, Zielona Gora, Poland
| | - Michał Ziarko
- Institute of Psychology, Uniwersytet im Adama Mickiewicza w Poznaniu, Poznan, Poland
| | - Aleksandra Jasielska
- Faculty of Psychology and Cognitive Sciences (FPCS AMU), Adam Mickiewicz University, Poznan, Poland
| | - Włodzimierz Samborski
- Department of Rheumatology and Rehabilitation, Poznan University of Medical Sciences, Poznan, Poland
| | - Przemysław Daroszewski
- Department of Organization and Management in Health Care, Poznan University of Medical Sciences, Poznan, Poland
| | - Krzysztof Greberski
- Department of Cardiovascular Disease Prevention, Poznan University of Medical Sciences, Poznan, Poland
- Department of Cardiac Surgery, Józef Strus Hospital, Poznan, Poland
| | - Grażyna Bączyk
- Department of Practice Nursing, Poznan University of Medical Sciences, Poznan, Poland
| | - Jacek Karoń
- Department of General and Colorectal Surgery, Józef Strus Hospital, Poznan, Poland
| | - Ewa Mojs
- Department of Clinical Psychology, Poznan University of Medical Sciences, Poznan, Poland
| |
Collapse
|
7
|
Lussier AA, Hawrilenko M, Wang MJ, Choi KW, Cerutti J, Zhu Y, Dunn EC. Genetic susceptibility for major depressive disorder associates with trajectories of depressive symptoms across childhood and adolescence. J Child Psychol Psychiatry 2021; 62:895-904. [PMID: 33125721 PMCID: PMC9886425 DOI: 10.1111/jcpp.13342] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/28/2020] [Revised: 08/08/2020] [Accepted: 09/15/2020] [Indexed: 02/02/2023]
Abstract
BACKGROUND Early-onset depression during childhood and adolescence is associated with a worse course of illness and outcome than adult onset. However, the genetic factors that influence risk for early-onset depression remain mostly unknown. Using data collected over 13 years, we examined whether polygenic risk scores (PRS) that capture genetic risk for depression were associated with depressive symptom trajectories assessed from childhood to adolescence. METHODS Data came from the Avon Longitudinal Study of Parents and Children, a prospective, longitudinal birth cohort (analytic sample = 7,308 youth). We analyzed the relationship between genetic susceptibility to depression and three time-dependent measures of depressive symptoms trajectories spanning 4-16.5 years of age (class, onset, and cumulative burden). Trajectories were constructed using a growth mixture model with structured residuals. PRS were generated from the summary statistics of a genome-wide association study of depression risk using data from the Psychiatric Genomics Consortium, UK Biobank, and 23andMe, Inc. We used MAGMA to identify gene-level associations with these measures. RESULTS Youth were classified into six classes of depressive symptom trajectories: high/renitent (27.9% of youth), high/reversing (9.1%), childhood decrease (7.3%), late childhood peak (3.3%), adolescent spike (2.5%), and minimal symptoms (49.9%). PRS discriminated between youth in the late childhood peak, high/reversing, and high/renitent classes compared to the minimal symptoms and childhood decrease classes. No significant associations were detected at the gene level. CONCLUSIONS This study highlights differences in polygenic loading for depressive symptoms across childhood and adolescence, particularly among youths with high symptoms in early adolescence, regardless of age-independent patterns.
Collapse
Affiliation(s)
| | - Matt Hawrilenko
- University of Washington School of Medicine, Seattle, WA,Veteran Affairs Puget Sound Healthcare System, Seattle, WA
| | - Min-Jung Wang
- Massachusetts General Hospital, Boston, MA,Harvard T.H. Chan School of Public Health, Boston, MA
| | - Karmel W. Choi
- Massachusetts General Hospital, Boston, MA,Harvard Medical School, Boston, MA,Harvard T.H. Chan School of Public Health, Boston, MA
| | | | - Yiwen Zhu
- Massachusetts General Hospital, Boston, MA
| | | | - Erin C. Dunn
- Massachusetts General Hospital, Boston, MA,Harvard Medical School, Boston, MA,Center on the Developing Child at Harvard University, Cambridge, MA
| |
Collapse
|
8
|
DeJoseph ML, Sifre RD, Raver CC, Blair CB, Berry D. Capturing Environmental Dimensions of Adversity and Resources in the Context of Poverty Across Infancy Through Early Adolescence: A Moderated Nonlinear Factor Model. Child Dev 2021; 92:e457-e475. [PMID: 33411404 DOI: 10.1111/cdev.13504] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
Income, education, and cumulative-risk indices likely obscure meaningful heterogeneity in the mechanisms through which poverty impacts child outcomes. This study draws from contemporary theory to specify multiple dimensions of poverty-related adversity and resources, with the aim of better capturing these nuances. Using data from the Family Life Project (N = 1,292), we leveraged moderated nonlinear factor analysis (Bauer, 2017) to establish group- and longitudinally invariant environmental measures from infancy to early adolescence. Results indicated three latent factors-material deprivation, psychosocial threat, and sociocognitive resources-were distinct from each other and from family income. Each was largely invariant across site, racial group, and development and showed convergent and discriminant relations with age-twelve criterion measures. Implications for ensuring socioculturally valid measurements of poverty are discussed.
Collapse
Affiliation(s)
| | | | | | - Clancy B Blair
- New York University.,New York University School of Medicine
| | | |
Collapse
|
9
|
McGrath KV, Leighton EA, Ene M, DiStefano C, Monrad DM. Using Integrative Data Analysis to Investigate School Climate Across Multiple Informants. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT 2020; 80:617-637. [PMID: 32616952 PMCID: PMC7307493 DOI: 10.1177/0013164419885999] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
Survey research frequently involves the collection of data from multiple informants. Results, however, are usually analyzed by informant group, potentially ignoring important relationships across groups. When the same construct(s) are measured, integrative data analysis (IDA) allows pooling of data from multiple sources into one data set to examine information from multiple perspectives within the same analysis. Here, the IDA procedure is demonstrated via the examination of pooled data from student and teacher school climate surveys. This study contributes to the sparse literature regarding IDA applications in the social sciences, specifically in education. It also lays the groundwork for future educational researchers interested in the practical applications of the IDA framework to empirical data sets with complex model structures.
Collapse
Affiliation(s)
| | | | - Mihaela Ene
- University of South Carolina, Columbia,
SC, USA
| | | | | |
Collapse
|
10
|
Cole VT, Hussong AM, Faris RW, Rothenberg WA, Gottfredson NC, Ennett ST. A Latent Variable Approach to Measuring Social Dynamics in Adolescence. JOURNAL OF RESEARCH ON ADOLESCENCE : THE OFFICIAL JOURNAL OF THE SOCIETY FOR RESEARCH ON ADOLESCENCE 2020; 30 Suppl 1:238-254. [PMID: 30566267 PMCID: PMC6584065 DOI: 10.1111/jora.12466] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
In the study of adolescent health, it is useful to derive indices of social dynamics from sociometric data, and to use these indices as predictors of health risk behaviors. In this manuscript, we introduce a flexible latent variable model as a novel way of obtaining estimates of social integration and social status from school-based sociometric data. Such scores provide the flexibility of a regression-based approach while accounting for measurement error in sociometric indicators. We demonstrate the utility of these factor scores in testing complex hypotheses through a combination of structural equation modeling and survival models, showing that deviance mediates the relationship between social status and smoking onset hazard at the transition to high school.
Collapse
Affiliation(s)
- Veronica T Cole
- University of North Carolina at Chapel Hill
- University of California at Davis
| | - Andrea M Hussong
- University of North Carolina at Chapel Hill
- University of California at Davis
| | - Robert W Faris
- University of North Carolina at Chapel Hill
- University of California at Davis
| | | | - Nisha C Gottfredson
- University of North Carolina at Chapel Hill
- University of California at Davis
| | - Susan T Ennett
- University of North Carolina at Chapel Hill
- University of California at Davis
| |
Collapse
|
11
|
Mun EY, Huo Y, White HR, Suzuki S, de la Torre J. Multivariate Higher-Order IRT Model and MCMC Algorithm for Linking Individual Participant Data From Multiple Studies. Front Psychol 2019; 10:1328. [PMID: 31244727 PMCID: PMC6582193 DOI: 10.3389/fpsyg.2019.01328] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2018] [Accepted: 05/21/2019] [Indexed: 11/23/2022] Open
Abstract
Many clinical and psychological constructs are conceptualized to have multivariate higher-order constructs that give rise to multidimensional lower-order traits. Although recent measurement models and computing algorithms can accommodate item response data with a higher-order structure, there are few measurement models and computing techniques that can be employed in the context of complex research synthesis, such as meta-analysis of individual participant data or integrative data analysis. The current study was aimed at modeling complex item responses that can arise when underlying domain-specific, lower-order traits are hierarchically related to multiple higher-order traits for individual participant data from multiple studies. We formulated a multi-group, multivariate higher-order item response theory (HO-IRT) model from a Bayesian perspective and developed a new Markov chain Monte Carlo (MCMC) algorithm to simultaneously estimate the (a) structural parameters of the first- and second-order latent traits across multiple groups and (b) item parameters of the model. Results from a simulation study support the feasibility of the MCMC algorithm. From the analysis of real data, we found that a bivariate HO-IRT model with different correlation/covariance structures for different studies fit the data best, compared to a univariate HO-IRT model or other alternate models with unreasonable assumptions (i.e., the same means and covariances across studies). Although more work is needed to further develop the method and to disseminate it, the multi-group multivariate HO-IRT model holds promise to derive a common metric for individual participant data from multiple studies in research synthesis studies for robust inference and for new discoveries.
Collapse
Affiliation(s)
- Eun-Young Mun
- University of North Texas Health Science Center, Fort Worth, TX, United States
| | - Yan Huo
- Educational Testing Service, Princeton, NJ, United States
| | - Helene R White
- Rutgers University Center of Alcohol Studies, Piscataway, NJ, United States
| | - Sumihiro Suzuki
- University of North Texas Health Science Center, Fort Worth, TX, United States
| | | |
Collapse
|
12
|
Hussong AM, Gottfredson NC, Bauer DJ, Curran PJ, Haroon M, Chandler R, Kahana SY, Delaney JAC, Altice FL, Beckwith CG, Feaster DJ, Flynn PM, Gordon MS, Knight K, Kuo I, Ouellet LJ, Quan VM, Seal DW, Springer SA. Approaches for creating comparable measures of alcohol use symptoms: Harmonization with eight studies of criminal justice populations. Drug Alcohol Depend 2019; 194:59-68. [PMID: 30412898 PMCID: PMC6312501 DOI: 10.1016/j.drugalcdep.2018.10.003] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/04/2018] [Revised: 10/16/2018] [Accepted: 10/17/2018] [Indexed: 11/28/2022]
Abstract
BACKGROUND With increasing data archives comprised of studies with similar measurement, optimal methods for data harmonization and measurement scoring are a pressing need. We compare three methods for harmonizing and scoring the AUDIT as administered with minimal variation across 11 samples from eight study sites within the STTR (Seek-Test-Treat-Retain) Research Harmonization Initiative. Descriptive statistics and predictive validity results for cut-scores, sum scores, and Moderated Nonlinear Factor Analysis scores (MNLFA; a psychometric harmonization method) are presented. METHODS Across the eight study sites, sample sizes ranged from 50 to 2405 and target populations varied based on sampling frame, location, and inclusion/exclusion criteria. The pooled sample included 4667 participants (82% male, 52% Black, 24% White, 13% Hispanic, and 8% Asian/ Pacific Islander; mean age of 38.9 years). Participants completed the AUDIT at baseline in all studies. RESULTS After logical harmonization of items, we scored the AUDIT using three methods: published cut-scores, sum scores, and MNLFA. We found greater variation, fewer floor effects, and the ability to directly address missing data in MNLFA scores as compared to cut-scores and sum scores. MNLFA scores showed stronger associations with binge drinking and clearer study differences than did other scores. CONCLUSIONS MNLFA scores are a promising tool for data harmonization and scoring in pooled data analysis. Model complexity with large multi-study applications, however, may require new statistical advances to fully realize the benefits of this approach.
Collapse
Affiliation(s)
| | | | - Dan J Bauer
- University of North Carolina at Chapel Hill, United States.
| | | | - Maleeha Haroon
- University of North Carolina at Chapel Hill, United States.
| | - Redonna Chandler
- National Institute on Drug Abuse/National Institutes of Health, United States
| | - Shoshana Y Kahana
- National Institute on Drug Abuse/National Institutes of Health, United States.
| | | | | | | | | | | | | | | | - Irene Kuo
- The George Washington University, United States.
| | | | - Vu M Quan
- Johns Hopkins University, United States.
| | - David W Seal
- Tulane University School of Public Health and Tropical Medicine, United States.
| | | |
Collapse
|
13
|
Hansen WB, Chen SH, Saldana S, Ip EH. An Algorithm for Creating Virtual Controls Using Integrated and Harmonized Longitudinal Data. Eval Health Prof 2018; 41:183-215. [PMID: 29724115 DOI: 10.1177/0163278718772882] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
Abstract
We introduce a strategy for creating virtual control groups-cases generated through computer algorithms that, when aggregated, may serve as experimental comparators where live controls are difficult to recruit, such as when programs are widely disseminated and randomization is not feasible. We integrated and harmonized data from eight archived longitudinal adolescent-focused data sets spanning the decades from 1980 to 2010. Collectively, these studies examined numerous psychosocial variables and assessed past 30-day alcohol, cigarette, and marijuana use. Additional treatment and control group data from two archived randomized control trials were used to test the virtual control algorithm. Both randomized controlled trials (RCTs) assessed intentions, normative beliefs, and values as well as past 30-day alcohol, cigarette, and marijuana use. We developed an algorithm that used percentile scores from the integrated data set to create age- and gender-specific latent psychosocial scores. The algorithm matched treatment case observed psychosocial scores at pretest to create a virtual control case that figuratively "matured" based on age-related changes, holding the virtual case's percentile constant. Virtual controls matched treatment case occurrence, eliminating differential attrition as a threat to validity. Virtual case substance use was estimated from the virtual case's latent psychosocial score using logistic regression coefficients derived from analyzing the treatment group. Averaging across virtual cases created group estimates of prevalence. Two criteria were established to evaluate the adequacy of virtual control cases: (1) virtual control group pretest drug prevalence rates should match those of the treatment group and (2) virtual control group patterns of drug prevalence over time should match live controls. The algorithm successfully matched pretest prevalence for both RCTs. Increases in prevalence were observed, although there were discrepancies between live and virtual control outcomes. This study provides an initial framework for creating virtual controls using a step-by-step procedure that can now be revised and validated using other prevention trial data.
Collapse
Affiliation(s)
| | - Shyh-Huei Chen
- 2 Department of Biostatistical Sciences, Division of Public Health Sciences, School of Medicine, Wake Forest University, Winston-Salem, NC, USA
| | - Santiago Saldana
- 2 Department of Biostatistical Sciences, Division of Public Health Sciences, School of Medicine, Wake Forest University, Winston-Salem, NC, USA
| | - Edward H Ip
- 2 Department of Biostatistical Sciences, Division of Public Health Sciences, School of Medicine, Wake Forest University, Winston-Salem, NC, USA
| |
Collapse
|