Biases in multilevel analyses caused by cluster-specific fixed-effects imputation

Speidel, Matthias; Drechsler, Jörg; Sakshaug, Joseph W.

doi:10.3758/s13428-017-0951-1

Cited by 12 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Imputation models included child (sex, age, ethnicity and year group) and school level covariates (school size, free school meal eligibility and school average BMIz) and all covariates used in the analysis (trial arm, baseline individual and school outcomes). School (cluster) was included as a fixed effect [29]. Thirty imputed datasets were created, analysis conducted on each dataset and combined to form one set of results using Rubin's rules.…”

Section: Discussionmentioning

confidence: 99%

Effectiveness and cost-effectiveness of The Daily Mile on childhood weight outcomes and wellbeing: a cluster randomised controlled trial

Breheny

Passmore²,

Adab

et al. 2020

Int J Obes

View full text Add to dashboard Cite

Background The Daily Mile is designed to increase physical activity levels with children running or walking around school grounds for 15-min daily. It has been adopted by schools worldwide and endorsed as a solution to tackle obesity, despite no robust evidence of its benefits. We conducted a cluster randomised controlled trial to determine its clinical and costeffectiveness. Methods Forty schools were randomly assigned (1:1) to either the Daily Mile intervention or control group in which only the usual school health and wellbeing activities were implemented. The primary outcome was BMI z-score (BMIz) at 12 months follow-up from baseline, with planned subgroup analysis to examine differential effects. Primary economic analysis outcome was incremental cost per Quality-Adjusted-Life-Year (QALY) gained. Results Using a constrained randomisation approach, balanced on school size, baseline BMIz and proportion of pupils eligible for free school meals, 20 schools were allocated to intervention (n = 1,153 participants) and 20 to control (n = 1,127); 3 schools withdrew (2 intervention, 1 control). At 12 months, BMIz data were available for 18 intervention schools (n = 850) and 19 control schools (n = 820 participants). Using intention-to-treat analysis the adjusted mean difference (MD) in BMIz (intervention − control) was −0.036 (95% CI: −0.085 to 0.013, p = 0.146). Pre-specified subgroup analysis showed a significant interaction with sex (p = 0.001) suggesting a moderate size benefit of The Daily Mile in girls (MD −0.097, 95% CI −0.156 to −0.037). This was consistent with the exploratory economic results that showed The Daily Mile to be highly cost-effective in girls (£2,492 per QALY), but not in boys, and overall to have a 76% chance of costeffectiveness for the whole sample, at the commonly applied UK threshold of £20,000 per QALY. Conclusions Overall the Daily Mile had a small but non-significant effect on BMIz, however, it had a greater effect in girls suggesting that it might be considered as a cost-effective component of a system-wide approach to childhood obesity prevention.

show abstract

Section: Discussionmentioning

confidence: 99%

Effectiveness and cost-effectiveness of The Daily Mile on childhood weight outcomes and wellbeing: a cluster randomised controlled trial

Breheny

Passmore²,

Adab

et al. 2020

Int J Obes

View full text Add to dashboard Cite

show abstract

“…However, as stated in the trial protocol, we proposed to estimate using LOCF [ 25 ], which we considered to add a final sensitivity analysis (complete cases, ITT LOCF, and multiple imputed). No difference was found in the results, probably due to limited losses [ 54 , 55 , 56 , 57 ].…”

Section: Discussionmentioning

confidence: 97%

How to Improve Healthcare for Patients with Multimorbidity and Polypharmacy in Primary Care: A Pragmatic Cluster-Randomized Clinical Trial of the MULTIPAP Intervention

del-Cura-González

López-Rodríguez

Leiva-Fernández

et al. 2022

JPM

View full text Add to dashboard Cite

(1) Purpose: To investigate a complex MULTIPAP intervention that implements the Ariadne principles in a primary care population of young-elderly patients with multimorbidity and polypharmacy and to evaluate its effectiveness for improving the appropriateness of prescriptions. (2) Methods: A pragmatic cluster-randomized clinical trial was conducted involving 38 family practices in Spain. Patients aged 65–74 years with multimorbidity and polypharmacy were recruited. Family physicians (FPs) were randomly allocated to continue usual care or to provide the MULTIPAP intervention based on the Ariadne principles with two components: FP training (eMULTIPAP) and FP patient interviews. The primary outcome was the appropriateness of prescribing, measured as the between-group difference in the mean Medication Appropriateness Index (MAI) score change from the baseline to the 6-month follow-up. The secondary outcomes were quality of life (EQ-5D-5 L), patient perceptions of shared decision making (collaboRATE), use of health services, treatment adherence, and incidence of drug adverse events (all at 1 year), using multi-level regression models, with FP as a random effect. (3) Results: We recruited 117 FPs and 593 of their patients. In the intention-to-treat analysis, the between-group difference for the mean MAI score change after a 6-month follow-up was −2.42 (95% CI from −4.27 to −0.59) and, between baseline and a 12-month follow-up was −3.40 (95% CI from −5.45 to −1.34). There were no significant differences in any other secondary outcomes. (4) Conclusions: The MULTIPAP intervention improved medication appropriateness sustainably over the follow-up time. The small magnitude of the effect, however, advises caution in the interpretation of the results given the paucity of evidence for the clinical benefit of the observed change in the MAI. Trial registration: Clinicaltrials.gov NCT02866799.

show abstract

“…It would be interesting to compare the possible approaches in the context of a random slope model because it is likely that the performance of these approaches are quite different [ 57 ]. With random slopes, the single- and two-level imputation models with extensions, particularly those which use DIs, might lead to biased estimates and can often be infeasible with a large number of clusters [ 58 ]. In addition, if explanatory variables with random slopes or interaction effects are incomplete, MI as implemented in standard software (the “reversed” imputation strategy) may no longer be valid [ 31 ].…”

Section: Discussionmentioning

confidence: 99%

Evaluation of approaches for multiple imputation of three-level data

Wijesuriya

Moreno‐Betancur

Lee

2020

BMC Med Res Methodol

View full text Add to dashboard Cite

Background: Three-level data arising from repeated measures on individuals who are clustered within larger units are common in health research studies. Missing data are prominent in such longitudinal studies and multiple imputation (MI) is a popular approach for handling missing data. Extensions of joint modelling and fully conditional specification MI approaches based on multilevel models have been developed for imputing three-level data. Alternatively, it is possible to extend single-and two-level MI methods to impute three-level data using dummy indicators and/or by analysing repeated measures in wide format. However, most implementations, evaluations and applications of these approaches focus on the context of incomplete two-level data. It is currently unclear which approach is preferable for imputing three-level data. Methods: In this study, we investigated the performance of various MI methods for imputing three-level incomplete data when the target analysis model is a three-level random effects model with a random intercept for each level. The MI methods were evaluated via simulations and illustrated using empirical data, based on a case study from the Childhood to Adolescence Transition Study, a longitudinal cohort collecting repeated measures on students who were clustered within schools. In our simulations we considered a number of different scenarios covering a range of different missing data mechanisms, missing data proportions and strengths of level-2 and level-3 intra-cluster correlations. Results: We found that all of the approaches considered produced valid inferences about both the regression coefficient corresponding to the exposure of interest and the variance components under the various scenarios within the simulation study. In the case study, all approaches led to similar results. Conclusion: Researchers may use extensions to the single-and two-level approaches, or the three-level approaches, to adequately handle incomplete three-level data. The two-level MI approaches with dummy indicator extension or the MI approaches based on three-level models will be required in certain circumstances such as when there are longitudinal data measured at irregular time intervals. However, the single-and two-level approaches with the DI extension should be used with caution as the DI approach has been shown to produce biased parameter estimates in certain scenarios.

show abstract

Biases in multilevel analyses caused by cluster-specific fixed-effects imputation

Cited by 12 publications

References 32 publications

Effectiveness and cost-effectiveness of The Daily Mile on childhood weight outcomes and wellbeing: a cluster randomised controlled trial

Effectiveness and cost-effectiveness of The Daily Mile on childhood weight outcomes and wellbeing: a cluster randomised controlled trial

How to Improve Healthcare for Patients with Multimorbidity and Polypharmacy in Primary Care: A Pragmatic Cluster-Randomized Clinical Trial of the MULTIPAP Intervention

Evaluation of approaches for multiple imputation of three-level data

Contact Info

Product

Resources

About