gsem: A Stata command for parametric joint modelling of longitudinal and accelerated failure time models

Dil, Elif; Karasoy, Durdu

doi:10.1016/j.cmpb.2020.105612

Cited by 6 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings accord with much of what has been learned about parental GOCs, although given the novelty of the questions posed in this study and of the quantitative approach to providing the answers, comparison with other studies is not direct. Prior research has focused on whether clinicians and parents have similar GOCs, whether parents and adolescents/young adults agree on GOCs, whether GOCs are discussed toward the end of life or earlier, and whether parent understanding of prognosis predicts GOCs . Many of these studies conceptualize the GOCs over time in a simplified binary manner with a shift from curative goals at initial diagnosis to the goal of lessening suffering at the end of life, especially once parents understand the child is likely to die .…”

Section: Discussionmentioning

confidence: 99%

“…To account for missing data due to missed data collections and dropout (but not death), all models were run using multiply imputed data . To account for potential bias due to patient death, parametric joint models (PJM) were run to assess the possible joint association between study outcomes and patient death by using a shared random intercept for each parent between the longitudinal model and a survival model. Two separate logistic PJM models were used to assess if there were (1) any rank order changes in goal rankings or (2) a change in the top goal within parents as a function of the previously measured degree of differentiation of the GOCs importance scores.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Goals of Care Among Parents of Children Receiving Palliative Care

et al. 2023

View full text Add to dashboard Cite

ImportanceWhile knowing the goals of care (GOCs) for children receiving pediatric palliative care (PPC) are crucial for guiding the care they receive, how parents prioritize these goals and how their priorities may change over time is not known.ObjectiveTo determine parental prioritization of GOCs and patterns of change over time for parents of children receiving palliative care.Design, Setting, and ParticipantsA Pediatric Palliative Care Research Network’s Shared Data and Research cohort study with data collected at 0, 2, 6, 12, 18, and 24 months in hospital, outpatient, or home settings from April 10, 2017, to February 15, 2022, at 7 PPC programs based at children’s hospitals across the US. Participants included parents of patients, birth to 30 years of age, who received PPC services.ExposuresAnalyses were adjusted for demographic characteristics, number of complex chronic conditions, and time enrolled in PPC.Main OutcomesParents’ importance scores, as measured using a discrete choice experiment, of 5 preselected GOCs: seeking quality of life (QOL), health, comfort, disease modification, or life extension. Importance scores for the 5 GOCs summed to 100.ResultsA total of 680 parents of 603 patients reported on GOCs. Median patient age was 4.4 (IQR, 0.8-13.2) years and 320 patients were male (53.1%). At baseline, parents scored QOL as the most important goal (mean score, 31.5 [SD, 8.4]), followed by health (26.3 [SD, 7.5]), comfort (22.4 [SD, 11.7]), disease modification (10.9 [SD, 9.2]), and life extension (8.9 [SD, 9.9]). Importantly, parents varied substantially in their baseline scores for each goal (IQRs more than 9.4), but across patients in different complex chronic conditions categories, the mean scores varied only slightly (means differ 8.7 or less). For each additional study month since PPC initiation, QOL was scored higher by 0.06 (95% CI, 0.04-0.08) and comfort scored higher by 0.3 (95% CI, 0-0.06), while the importance score for life extension decreased by 0.07 (95% CI, 0.04-0.09) and disease modification by 0.02 (95% CI, 0-0.04); health scores did not significantly differ from PPC initiation.Conclusions and RelevanceParents of children receiving PPC placed the highest value on QOL, but with considerable individual-level variation and substantial change over time. These findings emphasize the importance of reassessing GOCs with parents to guide appropriate clinical intervention.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Goals of Care Among Parents of Children Receiving Palliative Care

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Previous research has measured the variable of satisfaction by using a n -point Likert scale in a survey and has analyzed the model with some linear-kind method such covariance-based structural equation modelling (CB-SEM) or partial least square SEM (PLS-SEM) from linear and multivariate regression ( Al-Fraihat et al, 2020 ; Chiu et al, 2007 ; Sun et al, 2008 ). However, when more than one dependent variable is gauged at discrete values (e.g., positive integer and count data) as a latent variable, GSEM, which can estimate such variables in a nonlinear manner (e.g., logistic regression and negative binomial regression), obtaining robust results could be more reasonably expected ( Bartus, 2017 ; Dil & Karasoy, 2020 ; Palmer & Sterne, 2015 ; StataCorp, 2021 ).…”

Section: Discussionmentioning

confidence: 99%

“…As independent variables concurrently affect the two dependent variables of overall satisfaction and recommendation, the analytical method of simultaneous equations or structural equations that estimate several related equations ( Kennedy, 2008 ) with ordinal logistic regression could be more appropriate than those with linear regression. In particular, when one or more equations in n equations are nonlinear relational expressions, such as ordinal logistic or probit regression caused by survey data (i.e., n -point Likert scale) in the multilevel estimation model, it could be reasonable for researchers to utilize the generalized structural equation model (GSEM) rather than the structural equation model (SEM) ( Bartus, 2017 ; Dil & Karasoy, 2020 ; Palmer & Sterne, 2015 ; StataCorp, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

Interaction and online courses for satisfactory university learning during the COVID-19 pandemic

Kang

Park²

2022

The International Journal of Management Education

View full text Add to dashboard Cite

“…Mediation was further examined using parametric survival models (Weibull GSEM), optimal for causal mediation in survival analysis [ 34 ]. Within GSEM, time to dementia (TD) was modeled as the outcome.…”

Section: Methodsmentioning

confidence: 99%

Pathways explaining racial/ethnic and socio-economic disparities in dementia incidence: the UK Biobank study

Beydoun,

Fanelli-Kuczmarski

et al. 2023

Aging

View full text Add to dashboard Cite

Background: Pathways explaining racial/ethnic disparities in dementia risk are under-evaluated. Methods: We examine those disparities and their related pathways among UK Biobank study respondents (50–74 y, N = 323,483; 3.6% non-White minorities) using a series of Cox proportional hazards and generalized structural equations models (GSEM). Results: After ≤15 years, 5,491 all-cause dementia cases were diagnosed. Racial minority status (RACE_ETHN, Non-White vs. White) increased dementia risk by 24% (HR = 1.24, 95% CI: 1.07–1.45, P = 0.005), an association attenuated by socio-economic status (SES), (HR = 1.12, 95% CI: 0.96–1.31). Total race-dementia effect was mediated through both SES and Life’s Essential 8 lifestyle sub-score (LE8 LIFESTYLE ), combining diet, smoking, physical activity, and sleep factors. SES was inversely related to dementia risk (HR = 0.69, 95% CI: 0.67, 0.72, P < 0.001). Pathways explaining excess dementia risk among racial minorities included ‘RACE_ETHN(−) → SES(−) → DEMENTIA’, ‘RACE_ETHN(−) → SES(−) → Poor cognitive performance, COGN(+) → DEMENTIA’ and ‘RACE_ETHN(−) → SES(+) → LE8 LIFESTYLE (−) → DEMENTIA’. Conclusions: Pending future interventions, lifestyle factors including diet, smoking, physical activity, and sleep are crucial for reducing racial and socio-economic disparities in dementia.

show abstract

gsem: A Stata command for parametric joint modelling of longitudinal and accelerated failure time models

Cited by 6 publications

References 26 publications

Goals of Care Among Parents of Children Receiving Palliative Care

Goals of Care Among Parents of Children Receiving Palliative Care

Interaction and online courses for satisfactory university learning during the COVID-19 pandemic

Pathways explaining racial/ethnic and socio-economic disparities in dementia incidence: the UK Biobank study

Contact Info

Product

Resources

About