Sensitivity analyses for unmeasured confounding assuming a marginal structural model for repeated measures

2004 ◽  
Vol 23 (5) ◽  
pp. 749-767 ◽  
Author(s):  
Babette A. Brumback ◽  
Miguel A. Hernán ◽  
Sebastien J. P. A. Haneuse ◽  
James M. Robins
Keyword(s):  
Repeated Measures ◽  
Structural Model ◽  
Sensitivity Analyses ◽  
Marginal Structural Model ◽  
Unmeasured Confounding

The Effect of Serious Offending on Health: A Marginal Structural Model

2018 ◽  
Vol 9 (1) ◽  
pp. 18-32 ◽  
Author(s):  
Valerio Baćak ◽  
Mohammad Ehsanul Karim
Keyword(s):  
Life Course ◽  
Repeated Measures ◽  
Structural Model ◽  
Adult Health ◽  
Marginal Structural Model ◽  
Inverse Probability ◽  
Race And Gender ◽  
National Longitudinal Study ◽  
And Gender ◽  
The Life Course

In this study, we contribute to the emerging scholarship at the intersection of crime and health by estimating the effect of serious offending on offenders’ health. By building on sociological stress research, we identify and adjust for the key life course processes that may intervene on the pathway from offending to health using a rich set of measures available in the panel data from the National Longitudinal Study of Adolescent to Adult Health. Because offending and health share many causes and consequences, a critical challenge is accounting for confounding and mediation that unfold over time. We adjust for these time-varying processes by estimating repeated measures marginal structural models with inverse probability of treatment weights. The results show that offending over the life course is adversely linked to health but not uniformly across race and gender.

Estimating the causal effect of zidovudine on CD4 count with a marginal structural model for repeated measures

2002 ◽  
Vol 21 (12) ◽  
pp. 1689-1709 ◽  
Author(s):  
Miguel A. Hernán ◽  
Babette A. Brumback ◽  
James M. Robins
Keyword(s):  
Repeated Measures ◽  
Structural Model ◽  
Causal Effect ◽  
Cd4 Count ◽  
Marginal Structural Model

scholarly journals The association between continuity of care and surgery in lumbar disc herniation patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Eun-San Kim ◽  
Chang-yup Kim
Keyword(s):  
Continuity Of Care ◽  
Disc Herniation ◽  
Structural Model ◽  
Lumbar Disc ◽  
Quality Care ◽  
Target Population ◽  
National Sample ◽  
Marginal Structural Model ◽  
Lumbar Surgery ◽  
High Level

AbstractContinuity of care is a core dimension of high-quality care in the management of disease. The purpose of this study was to investigate the association between continuity of care and lumbar surgery in patients with moderate disc herniation. The Korean National Sample Cohort was used. The target population consisted of patients who have had disc herniation more than 6 months and didn’t get surgery and red flag signs within 6 months from onset. The population was enrolled from 2004 to 2013. The Bice-Boxerman Continuity of Care was used in measuring continuity of care. The marginal structural model with time dependent survival analysis was used. In total, 29,061 patients were enrolled in the cohort. High level of continuity of care was associated with a lower risk of lumbar surgery (HR, 0.27; 95% CI, 0.20–0.27). When the index was calculated only with outpatient visits to primary care with related specialty, the HR was 0.49 (95% CI: 0.43–0.57). In exploratory analysis, patients with lumbar stenosis and spondylolisthesis had higher risk of having a low level of continuity of care. These results indicate that continuity of care is associated with lower rates of lumbar surgery in patients with moderate disc herniation.

Associations of Endometriosis and Hormone Therapy With Risk of Hyperlipidemia

2020 ◽  
Author(s):  
Cherry Yin-Yi Chang ◽  
Chih-Hsin Muo ◽  
Yi-Chun Yeh ◽  
Chung-Yen Lu ◽  
William Wu-Chou Lin ◽  
...  
Keyword(s):  
Hormone Therapy ◽  
Structural Model ◽  
Proportional Hazards ◽  
Proportional Hazards Model ◽  
Cox Proportional Hazards ◽  
Cox Proportional Hazards Model ◽  
Marginal Structural Model ◽  
Bilateral Oophorectomy ◽  
Hazards Model ◽  
Increased Risk

Abstract Using claims data from the universal health insurance program of Taiwan, we conducted a retrospective cohort study to investigate whether endometriosis and hormone therapy are associated with the risk of developing hyperlipidemia. We selected 9,155 women aged 20–55 years with endometriosis diagnosed during the period 2000–2013 and 212,641 women without endometriosis with a median follow-up time of 7 years. Among patients with endometriosis, 86% of cases were identified on the basis of diagnosis codes with an ultrasound claim, and 14% were defined by diagnostic laparoscopy or surgical treatments. In a Cox proportional hazards model, the adjusted hazard ratio was 1.30 (95% confidence interval (CI): 1.19, 1.41) for all women, 1.04 (95% CI: 0.81, 1.32) for women under 35 years of age, 1.17 (95% CI: 1.03, 1.32) for women aged 35–44 years, and 1.34 (95% CI: 1.18, 1.52) for women aged 45–54 years. Hysterectomy and/or bilateral oophorectomy accounted for 46.9% of the association between endometriosis and hyperlipidemia, and hormone therapy accounted for 21.6%. Among women with endometriosis, the marginal structural model approach adjusting for time-varying hysterectomy/bilateral oophorectomy showed no association between use of hormone medications and risk of hyperlipidemia. We concluded that women with endometriosis are at increased risk of hyperlipidemia; use of hormone therapy by these women was not independently associated with the development of hyperlipidemia.

Post hoc analysis of a randomised, placebo-controlled, active-reference 6-week study of brexpiprazole in acute schizophrenia

2020 ◽  
Vol 32 (3) ◽  
pp. 153-158 ◽  
Author(s):  
Stephen R. Marder ◽  
Hans Eriksson ◽  
Yudong Zhao ◽  
Mary Hobart
Keyword(s):  
Adverse Events ◽  
Repeated Measures ◽  
Mixed Model ◽  
Least Square ◽  
Analysis Of Covariance ◽  
Sensitivity Analyses ◽  
Symptom Improvement ◽  
Syndrome Scale ◽  
Quetiapine Xr ◽  
Post Hoc

AbstractObjective:We provide a closer look at the result of a randomised, placebo-controlled, active-reference (quetiapine XR), flexible-dose, 6-week study of brexpiprazole in schizophrenia, which did not meet its primary endpoint – change from baseline in Positive and Negative Syndrome Scale (PANSS) total score. We also investigate potential expectancy bias from the well-known side-effect profile of the active reference that could have affected the study outcome.Methods:Pre-specified sensitivity analyses of the primary end point were performed using analysis of covariance (ANCOVA) last observation carried forward (LOCF) and observed cases (OC). Post hoc analyses of change from baseline in PANSS total score were performed using the mixed model for repeated measures approach with treatment groups split by having typical adverse events with potential for functional unblinding, for example, somnolence, increase in weight, dizziness, dry mouth and sedation.Results:Pre-specified sensitivity analyses showed separation from placebo for brexpiprazole at week 6: LOCF, ANCOVA: −4.3 [95% CI (−8.0, −0.5), p = 0.0254]. OC, ANCOVA: −3.9 [95% CI (−7.3, −0.5), p = 0.0260]. Patients treated with brexpiprazole experiencing typical adverse events with potential for functional unblinding before or at Week 2 had a least square (LS) mean PANSS change of −29.5 (improvement), with a difference in change from baseline to Week 6 in PANSS total score between brexpiprazole and placebo of −13.5 [95% CI (−23.1, −4.0), p = 0.0057], and those who did not had an LS mean change of −18.9 and a difference between brexpiprazole and placebo of −2.9 [95% CI (−7.2, 1.4), p = 0.1809].Conclusion:Pre-specified sensitivity analyses showed separation from placebo for brexpiprazole at Week 6. A post hoc analysis suggested a potential confounding of efficacy rating towards symptom improvement in patients who experience known side effects of quetiapine XR.

scholarly journals Conducting sensitivity analysis for unmeasured confounding in observational studies using E-values: The evalue package

2020 ◽  
Vol 20 (1) ◽  
pp. 162-175 ◽  
Author(s):  
Ariel Linden ◽  
Maya B. Mathur ◽  
Tyler J. VanderWeele
Keyword(s):  
Observational Studies ◽  
Specific Treatment ◽  
Sensitivity Analyses ◽  
Unmeasured Confounding ◽  
Unmeasured Confounder ◽  
Point Estimates ◽  
Hazard Ratios ◽  
Mean Differences ◽  
Rate Ratios ◽  
Strength Of Association

In this article, we introduce the evalue package, which performs sensitivity analyses for unmeasured confounding in observational studies using the methodology proposed by VanderWeele and Ding (2017, Annals of Internal Medicine 167: 268–274). evalue reports E-values, defined as the minimum strength of association on the risk-ratio scale that an unmeasured confounder would need to have with both the treatment assignment and the outcome to fully explain away a specific treatment-outcome association, conditional on the measured covariates. evalue computes E-values for point estimates (and optionally, confidence limits) for several common outcome types, including risk and rate ratios, odds ratios with common or rare outcomes, hazard ratios with common or rare outcomes, standardized mean differences in outcomes, and risk differences.

scholarly journals Perceived Discrimination Trajectories and Depressive Symptoms Among Middle-Aged and Older Black Adults

2020 ◽  
Vol 4 (5) ◽  
Author(s):  
Kellee White ◽  
Bethany A Bell ◽  
Shuo J Huang ◽  
David R Williams
Keyword(s):  
Mental Health ◽  
Older Adults ◽  
Depressive Symptoms ◽  
Racial Discrimination ◽  
Repeated Measures ◽  
Negative Binomial ◽  
Perceived Discrimination ◽  
Sensitivity Analyses ◽  
Middle Aged ◽  
Time Point

Abstract Background and Objectives Perceived discrimination is a risk factor for poor mental health. However, most studies measure discrimination at one time point, which does not account for heterogeneity in the cumulative patterning of exposure to discrimination. To address this gap, we examine the association between discrimination trajectories and depressive symptoms among black middle-aged and older adults. Research Design and Methods Data were analyzed from a subsample of black Health and Retirement Study respondents (2006–2018, N = 2926, older than 50 years). General discrimination and racial discrimination trajectories were constructed based on the Everyday Discrimination Scale using repeated measures latent profile analyses. We examined the extent to which the association between discrimination trajectories are differentially associated with depressive symptoms (8-item Center for Epidemiological Studies-Depression scale) using negative binomial regression models adjusted for potential confounders. Effect modification by age and gender was tested. Results Individuals in the persistently high (incident rate ratio [IRR]: 1.70; 95% confidence interval [CI]: 1.49–1.95) and moderate general discrimination trajectories (IRR: 1.19; 95% CI: 1.06–1.33) were more likely to have elevated depressive symptoms in comparison to those in the persistently low trajectory. This relationship was strongest among older adults aged older than 65 years. Respondents in the persistently high racial discrimination trajectory (IRR: 1.50; 95% CI: 1.29–1.73) had a higher risk of elevated depressive symptoms in comparison to respondents in the persistently low trajectory. Sensitivity analyses indicated that there was an independent association between persistently high racial discrimination trajectory class and elevated depressive symptoms, after adjusting for racial discrimination measured at a single time point. Discussion and Implications Characterizing longitudinal patterns of perceived discrimination may facilitate the stratification of mental health risk and vulnerability among black middle-aged and older adults. Trajectories of racial discrimination may inform risk of worse depressive symptoms more accurately than a single assessment of discrimination.

Sign in / Sign up

Export Citation Format

Share Document