scholarly journals Structural Nested Mean Models to Estimate the Effects of Time-Varying Treatments on Clustered Outcomes

2015 ◽  
Vol 11 (2) ◽  
Author(s):  
Jiwei He ◽  
Alisa Stephens-Shields ◽  
Marshall Joffe
Keyword(s):  
Repeated Measures ◽  
Regression Method ◽  
Time Varying ◽  
Treatment Allocation ◽  
Individual Level ◽  
Nested Models ◽  
Unit Level ◽  
Effect Of Treatment ◽  
Structural Nested Models ◽  
The Individual

AbstractIn assessing the efficacy of a time-varying treatment structural nested models (SNMs) are useful in dealing with confounding by variables affected by earlier treatments. These models often consider treatment allocation and repeated measures at the individual level. We extend SNMMs to clustered observations with time-varying confounding and treatments. We demonstrate how to formulate models with both cluster- and unit-level treatments and show how to derive semiparametric estimators of parameters in such models. For unit-level treatments, we consider interference, namely the effect of treatment on outcomes in other units of the same cluster. The properties of estimators are evaluated through simulations and compared with the conventional GEE regression method for clustered outcomes. To illustrate our method, we use data from the treatment arm of a glaucoma clinical trial to compare the effectiveness of two commonly used ocular hypertension medications.

Marginal structural models to estimate the effects of time-varying treatments on clustered outcomes in the presence of interference

2017 ◽  
Vol 28 (2) ◽  
pp. 613-625 ◽  
Author(s):  
Jiwei He ◽  
Alisa Stephens-Shields ◽  
Marshall Joffe
Keyword(s):  
Structural Models ◽  
Marginal Structural Models ◽  
Time Varying ◽  
Nested Models ◽  
Unit Level ◽  
Inverse Probability Weights ◽  
Effect Of Treatment ◽  
Working Correlation ◽  
Structural Nested Models ◽  
Cluster Level

Marginal structural models are a class of causal models useful for characterizing the effect of treatment in the presence of time-varying confounding. They are more widely used than structural nested models, partly because these models are easier to understand and to implement. We extend marginal structural models to situations with clustered observations with unit- and cluster-level treatment and introduce an appropriate inferential method. We consider how to formulate models with cluster-level and unit-level treatments. For unit-level treatments, we consider cases with and without interference. We also consider the use of unit-specific inverse probability weights and certain working correlation structures to improve the efficiency of estimators in some situations. We apply our method to different scenarios including 2 or 3 units per cluster and a mixture of larger clusters. Simulation examples and data from the treatment arm of a glaucoma clinical trial were used to illustrate our method.

scholarly journals Comparison Between Non-Invasive Methane Measurement Techniques in Cattle

Animals ◽  
2019 ◽  
Vol 9 (8) ◽  
pp. 563 ◽  
Author(s):  
Rey ◽  
Atxaerandio ◽  
Ruiz ◽  
Ugarte ◽  
González-Recio ◽  
...  
Keyword(s):  
Repeated Measures ◽  
Measurement Techniques ◽  
Genetic Selection ◽  
Mitigation Strategies ◽  
Population Means ◽  
Individual Level ◽  
Non Invasive ◽  
Ch4 Concentration ◽  
The Individual ◽  
Methane Measurement

The aim of this trial was to study the agreement between the non-dispersive infrared methane analyzer (NDIR) method and the hand held laser methane detector (LMD). Methane (CH4) was measured simultaneously with the two devices totaling 164 paired measurements. The repeatability of the CH4 concentration was greater with the NDIR (0.42) than for the LMD (0.23). However, for the number of peaks, repeatability of the LMD was greater (0.20 vs. 0.14, respectively). Correlation was moderately high and positive for CH4 concentration (0.73 and 0.74, respectively) and number of peaks (0.72 and 0.72, respectively), and the repeated measures correlation and the individual-level correlation were high (0.98 and 0.94, respectively). A moderate concordance correlation coefficient was observed for the CH4 concentration (0.62) and for the number of peaks (0.66). A moderate-high coefficient of individual agreement for the CH4 concentration (0.83) and the number of peaks (0.77) were observed. However, CH4 concentrations population means and all variance components differed between instruments. In conclusion, methane concentration measurements obtained by means of NDIR and LMD cannot be used interchangeably. The joint use of both methods could be considered for genetic selection purposes or for mitigation strategies only if sources of disagreement, which result in different between-subject and within-subject variabilities, are identified and corrected for.

scholarly journals Bearing the Weight of Imprisonment: The Relationship Between Prison Climate and Well-Being

2019 ◽  
Vol 46 (10) ◽  
pp. 1385-1404 ◽  
Author(s):  
Esther F. J. C. van Ginneken ◽  
Hanneke Palmen ◽  
Anouk Q. Bosma ◽  
Miranda Sentse
Keyword(s):  
The Netherlands ◽  
Multilevel Analysis ◽  
Well Being ◽  
Group Level ◽  
Individual Level ◽  
Unit Level ◽  
Positive Effects ◽  
Individual Perceptions ◽  
The Individual ◽  
The Relationship

Little is known about the relative influence of shared and individual perceptions of prison climate on adjustment to incarceration. This study investigated the relationship between prison climate and well-being among a sample of 4,538 adults incarcerated in the Netherlands. Prison climate dimensions were considered both as prison unit-level variables and as individual-level perceptions. Multilevel analysis results showed that most variance for well-being is found at the individual rather than the unit level. This implies that it does not make much of a difference for well-being in which prison unit someone resides. Positive effects of prison climate on well-being were primarily found for individual perceptions of prison climate, rather than for the aggregate unit measures. More research is needed to determine whether this finding holds true in other countries. The findings confirm the importance of disentangling the contribution of prison climate at the individual and group level.

scholarly journals Multi-scale immunoepidemiological modeling of within-host and between-host HIV dynamics: systematic review of mathematical models

PeerJ ◽  
2017 ◽  
Vol 5 ◽  
pp. e3877 ◽  
Author(s):  
Nargesalsadat Dorratoltaj ◽  
Ryan Nikin-Beers ◽  
Stanca M. Ciupe ◽  
Stephen G. Eubank ◽  
Kaja M. Abbas
Keyword(s):  
Systematic Review ◽  
Population Level ◽  
Transmission Dynamics ◽  
Time Varying ◽  
Individual Level ◽  
Multi Scale ◽  
Hiv Dynamics ◽  
Single Scale ◽  
Scale Models ◽  
The Individual

Objective The objective of this study is to conduct a systematic review of multi-scale HIV immunoepidemiological models to improve our understanding of the synergistic impact between the HIV viral-immune dynamics at the individual level and HIV transmission dynamics at the population level. Background While within-host and between-host models of HIV dynamics have been well studied at a single scale, connecting the immunological and epidemiological scales through multi-scale models is an emerging method to infer the synergistic dynamics of HIV at the individual and population levels. Methods We reviewed nine articles using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework that focused on the synergistic dynamics of HIV immunoepidemiological models at the individual and population levels. Results HIV immunoepidemiological models simulate viral immune dynamics at the within-host scale and the epidemiological transmission dynamics at the between-host scale. They account for longitudinal changes in the immune viral dynamics of HIV+ individuals, and their corresponding impact on the transmission dynamics in the population. They are useful to analyze the dynamics of HIV super-infection, co-infection, drug resistance, evolution, and treatment in HIV+ individuals, and their impact on the epidemic pathways in the population. We illustrate the coupling mechanisms of the within-host and between-host scales, their mathematical implementation, and the clinical and public health problems that are appropriate for analysis using HIV immunoepidemiological models. Conclusion HIV immunoepidemiological models connect the within-host immune dynamics at the individual level and the epidemiological transmission dynamics at the population level. While multi-scale models add complexity over a single-scale model, they account for the time varying immune viral response of HIV+ individuals, and the corresponding impact on the time-varying risk of transmission of HIV+ individuals to other susceptibles in the population.

scholarly journals Understanding how Victoria, Australia gained control of its second COVID-19 wave

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
James M. Trauer ◽  
Michael J. Lydeamore ◽  
Gregory W. Dalton ◽  
David Pilcher ◽  
Michael T. Meehan ◽  
...  
Keyword(s):  
Time Varying ◽  
Population Mobility ◽  
School Closures ◽  
Individual Level ◽  
Risk Of Death ◽  
Policy Interventions ◽  
Australian State ◽  
The Individual ◽  
Individual Health Services ◽  
Second Wave

AbstractDuring 2020, Victoria was the Australian state hardest hit by COVID-19, but was successful in controlling its second wave through aggressive policy interventions. We calibrated a detailed compartmental model of Victoria’s second wave to multiple geographically-structured epidemic time-series indicators. We achieved a good fit overall and for individual health services through a combination of time-varying processes, including case detection, population mobility, school closures, physical distancing and face covering usage. Estimates of the risk of death in those aged ≥75 and of hospitalisation were higher than international estimates, reflecting concentration of cases in high-risk settings. We estimated significant effects for each of the calibrated time-varying processes, with estimates for the individual-level effect of physical distancing of 37.4% (95%CrI 7.2−56.4%) and of face coverings of 45.9% (95%CrI 32.9−55.6%). That the multi-faceted interventions led to the dramatic reversal in the epidemic trajectory is supported by our results, with face coverings likely particularly important.

HPWS and climate for inclusion: a moral legitimacy lens

2018 ◽  
Vol 37 (5) ◽  
pp. 491-505
Author(s):  
Jennifer A. Harrison ◽  
Janet A. Boekhorst ◽  
Yin Yu
Keyword(s):  
High Performance ◽  
Minority Groups ◽  
Moral Identity ◽  
Employee Perceptions ◽  
Moral Legitimacy ◽  
Content Type ◽  
Individual Level ◽  
Unit Level ◽  
Collective Levels ◽  
The Individual

PurposeThe purpose of this paper is to apply insights from the moral legitimacy theory to understand how climate for inclusion (CFI) is cultivated at the individual and collective levels, thereby highlighting the influence of employee perceptions of inclusion-oriented high-performance work systems (HPWS) on CFI.Design/methodology/approachA multi-level conceptual framework is introduced to explain how employee perceptions develop about the moral legitimacy of inclusion-oriented HPWS and the subsequent influence on CFI.FindingsCFI is theorized to manifest when employees perceive inclusion-oriented HPWS as morally legitimate according to four unit-level features. Employees with a strong moral identity will be particularly attuned to the moral legitimacy of each of the unit-level HPWS features, thereby strengthening the perceived HPWS and CFI relationship at the individual level. The convergence of individual-level perceptions of CFI to the collective level will be strongest when climate variability is low for majority and minority groups.Practical implicationsOrganizations seeking to develop CFI should consider the role of HPWS and the perceived moral legitimacy of such systems. This consideration may involve policy amendments to include a broadened scope of HPWS.Originality/valueThis paper explores how employee perceptions of the moral legitimacy of HPWS can help or hinder CFI, thereby offering a novel framework for future inclusion and human resource management research.

scholarly journals Association of workplace social capital with psychological distress: results from a longitudinal multilevel analysis of the J-HOPE Study

BMJ Open ◽  
2018 ◽  
Vol 8 (12) ◽  
pp. e022569 ◽  
Author(s):  
Hisashi Eguchi ◽  
Akizumi Tsutsumi ◽  
Akiomi Inoue ◽  
Hiroyuki Hikichi ◽  
Ichiro Kawachi
Keyword(s):  
Mental Health ◽  
Social Capital ◽  
Psychological Distress ◽  
Repeated Measures ◽  
Individual Level ◽  
Unit Level ◽  
Repeated Measures Design ◽  
Distress Scale ◽  
The Impact ◽  
Workplace Social Capital

ObjectivesWorkplace social capital (WSC) is increasingly recognised as a social contextual determinant of workers’ mental health, but longitudinal data are sparse. We aimed to evaluate the impact of changes in unit-level WSC on psychological distress among Japanese employees using a prospective multilevel repeated-measures design.Participants and study designWe conducted a 2-year prospective cohort study with 1,944 men and 786 women aged 18–65 years. Participants worked at two manufacturing worksites in Japan and were free from mental illness from the first to third study waves. We used a three-level multilevel regression design to evaluate the prospective association of unit-level WSC with individual-level psychological distress. WSC was measured using a validated six-item instrument and individual-level psychological distress with the Kessler Psychological Distress Scale (K6).ResultsThe null model indicated a significant degree of between-work unit variation in psychological distress (intraclass correlation=0.1%, p<0.001). In the full model, each SD increase in unit-level WSC was associated with 0.69 point improvement in K6 scores (95% CI −1.12 to −0.26).ConclusionsThis prospective study builds on existing knowledge by showing an association between unit-level WSC and modest improvements in mental health among employees in Japan. We recommend that WSC is considered alongside other contextual influences when assessing employees’ mental health risks.

Emergence of interpersonal helping in times of crises: a theoretical model of prosperity and eradication of interpersonal helping in organizations

2020 ◽  
Vol 58 (10) ◽  
pp. 2257-2273
Author(s):  
Shih Yung Chou ◽  
Charles Ramser ◽  
Tree Chang ◽  
Bo Han
Keyword(s):  
Theoretical Model ◽  
Design Methodology ◽  
Job Crafting ◽  
Future Research ◽  
Content Type ◽  
Individual Level ◽  
Unit Level ◽  
Organizational Crises ◽  
Interpersonal Helping ◽  
The Individual

PurposeThe purpose of this article is to develop a cross-level, theoretical model describing the process by which interpersonal helping becomes conspicuous, as well as the process by which interpersonal helping subsequently prospers or becomes eradicated in the organization.Design/methodology/approachA theoretical analysis was performed by drawing upon various management-related theories.FindingsWe propose that organizational crises foster the emergence of interpersonal helping. Additionally, the positive relationship between organizational crises and interpersonal helping is stronger (or weaker) when individuals possess higher levels of other-oriented (or self-oriented) motives. Furthermore, we propose that a sympathetic climate at the unit level and employee job crafting at the individual level result in the prosperity of interpersonal helping, whereas interpersonal helping is eradicated by a sarcastic atmosphere at the unit level and citizenship pressure at the individual level.Originality/valueTheoretically, we advance the literature by providing future research with a theoretical base for understanding interpersonal helping from a temporal and cross-level perspective. Practically, this article offers some managerial recommendations that help managers nurture interpersonal helping in organizations effectively.

Individual and Social Network Predictors of Physical Bullying: A Longitudinal Study of Taiwanese Early Adolescents

2014 ◽  
Vol 29 (4) ◽  
pp. 701-716 ◽  
Author(s):  
Hsi-Sheng Wei ◽  
Wonjae Lee
Keyword(s):  
Social Network ◽  
Repeated Measures ◽  
Economic Status ◽  
Friendship Networks ◽  
Friendship Network ◽  
Individual Level ◽  
School Year ◽  
Bullying Experiences ◽  
The Individual ◽  
Physical Bullying

This study followed 125 7th-grade students in Taiwan for the entire school year and analyzed the individual and social network factors predicting their involvement in physical bullying over 5 waves of data. Using self-reports of bullying experiences, 20 classroom-level networks of bullying and friendship were constructed for 4 classrooms and 5 temporal points, from which 4 individual-level network measures were calculated. They included bully and victim centrality, popularity, and embeddedness in friendship networks. A series of mixed models for repeated measures were constructed to predict students’ bully and victim centrality in bullying network at time t + 1. Compared to girls, boys were more likely to be both the bullies and victims. Lower self-esteem and higher family economic status contributed to victim centrality. Having parents married and living together predicted lower bully centrality. Higher educational level of parents predicted lower victim and bully centrality. Regarding the social network factors, students’ bully centrality at t positively predicted their bully centrality at t + 1, whereas victim centrality predicted their subsequent victim centrality. Interaction effects between friendship network and bullying network were observed. Embeddedness in friendship network reduced victim centrality at t + 1 except for those students with low victim centrality at t. For those with high victim centrality at t, popularity increased their risk of physical victimization over time. Implications for research and practice are discussed.

Sign in / Sign up

Export Citation Format

Share Document