Dataset Information

Appropriate statistical methods for analysing partially nested randomised controlled trials with continuous outcomes: a simulation study.

ABSTRACT: BACKGROUND:In individually randomised trials we might expect interventions delivered in groups or by care providers to result in clustering of outcomes for participants treated in the same group or by the same care provider. In partially nested randomised controlled trials (pnRCTs) this clustering only occurs in one trial arm, commonly the intervention arm. It is important to measure and account for between-cluster variability in trial design and analysis. We compare analysis approaches for pnRCTs with continuous outcomes, investigating the impact on statistical inference of cluster sizes, coding of the non-clustered arm, intracluster correlation coefficient (ICCs), and differential variance between intervention and control arm, and provide recommendations for analysis. METHODS:We performed a simulation study assessing the performance of six analysis approaches for a two-arm pnRCT with a continuous outcome. These include: linear regression model; fully clustered mixed-effects model with singleton clusters in control arm; fully clustered mixed-effects model with one large cluster in control arm; fully clustered mixed-effects model with pseudo clusters in control arm; partially nested homoscedastic mixed effects model, and partially nested heteroscedastic mixed effects model. We varied the cluster size, number of clusters, ICC, and individual variance between the two trial arms. RESULTS:All models provided unbiased intervention effect estimates. In the partially nested mixed-effects models, methods for classifying the non-clustered control arm had negligible impact. Failure to account for even small ICCs resulted in inflated Type I error rates and over-coverage of confidence intervals. Fully clustered mixed effects models provided poor control of the Type I error rates and biased ICC estimates. The heteroscedastic partially nested mixed-effects model maintained relatively good control of Type I error rates, unbiased ICC estimation, and did not noticeably reduce power even with homoscedastic individual variances across arms. CONCLUSIONS:In general, we recommend the use of a heteroscedastic partially nested mixed-effects model, which models the clustering in only one arm, for continuous outcomes similar to those generated under the scenarios of our simulations study. However, with few clusters (3-6), small cluster sizes (5-10), and small ICC (?0.05) this model underestimates Type I error rates and there is no optimal model.

SUBMITTER: Candlish J

PROVIDER: S-EPMC6186141 | biostudies-other | 2018 Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:OBJECTIVE:Randomised controlled trials (RCT) are the gold standard to provide unbiased data. However, when patients have a treatment preference, randomisation may influence participation and outcomes (eg, external and internal validity). The aim of this study was to assess the influence of patients' preference in RCTs by analysing partially randomised patient preference trials (RPPT); an RCT and preference cohort combined. DESIGN:Systematic review and meta-analyses. DATA SOURCES:MEDLINE, Embase, PsycINFO and the Cochrane Library. ELIGIBILITY CRITERIA FOR SELECTING STUDIES:RPPTs published between January 2005 and October 2018 reporting on allocation of patients to randomised and preference cohorts were included. DATA EXTRACTION AND SYNTHESIS:Two independent reviewers extracted data. The main outcomes were the difference in external validity (participation and baseline characteristics) and internal validity (lost to follow-up, crossover and the primary outcome) between the randomised and the preference cohort within each RPPT, compared in a meta-regression using a Wald test. Risk of bias was not assessed, as no quality assessment for RPPTs has yet been developed. RESULTS:In total, 117 of 3734 identified articles met screening criteria and 44 were eligible (24 873 patients). The participation rate in RPPTs was >95% in 14 trials (range: 48%-100%) and the randomisation refusal rate was >50% in 26 trials (range: 19%-99%). Higher education, female, older age, race and prior experience with one treatment arm were characteristics of patients declining randomisation. The lost to follow-up and cross-over rate were significantly higher in the randomised cohort compared with the preference cohort. Following the meta-analysis, the reported primary outcomes were comparable between both cohorts of the RPPTs, mean difference 0.093 (95% CI -0.178 to 0.364, p=0.502). CONCLUSIONS:Patients' preference led to a substantial proportion of a specific patient group refusing randomisation, while it did not influence the primary outcome within an RPPT. Therefore, RPPTs could increase external validity without compromising the internal validity compared with RCTs. PROSPERO REGISTRATION NUMBER:CRD42019094438.

Project description:Pooling biomarker data across multiple studies allows for examination of a wider exposure range than generally possible in individual studies, evaluation of population subgroups and disease subtypes with more statistical power, and more precise estimation of biomarker-disease associations. However, circulating biomarker measurements often require calibration to a single reference assay prior to pooling due to assay and laboratory variability across studies. We propose several methods for calibrating and combining biomarker data from nested case-control studies when reference assay data are obtained from a subset of controls in each contributing study. Specifically, we describe a two-stage calibration method and two aggregated calibration methods, named the internalized and full calibration methods, to evaluate the main effect of the biomarker exposure on disease risk and whether that association is modified by a potential covariate. The internalized method uses the reference laboratory measurement in the analysis when available and otherwise uses the estimated value derived from calibration models. The full calibration method uses calibrated biomarker measurements for all subjects, including those with reference laboratory measurements. Under the two-stage method, investigators complete study-specific analyses in the first stage followed by meta-analysis in the second stage. Our results demonstrate that the full calibration method is the preferred aggregated approach to minimize bias in point estimates. We also observe that the two-stage and full calibration methods provide similar effect and variance estimates but that their variance estimates are slightly larger than those from the internalized approach. As an illustrative example, we apply the three methods in a pooling project of nested case-control studies to evaluate (i) the association between circulating vitamin D levels and risk of stroke and (ii) how body mass index modifies the association between circulating vitamin D levels and risk of cardiovascular disease.

Project description:BACKGROUND:Statistical methods for the analysis of harm outcomes in randomised controlled trials (RCTs) are rarely used, and there is a reliance on simple approaches to display information such as in frequency tables. We aimed to identify whether any statistical methods had been specifically developed to analyse prespecified secondary harm outcomes and non-specific emerging adverse events (AEs). METHODS:A scoping review was undertaken to identify articles that proposed original methods or the original application of existing methods for the analysis of AEs that aimed to detect potential adverse drug reactions (ADRs) in phase II-IV parallel controlled group trials. Methods where harm outcomes were the (co)-primary outcome were excluded. Information was extracted on methodological characteristics such as: whether the method required the event to be prespecified or could be used to screen emerging events; and whether it was applied to individual events or the overall AE profile. Each statistical method was appraised and a taxonomy was developed for classification. RESULTS:Forty-four eligible articles proposing 73 individual methods were included. A taxonomy was developed and articles were categorised as: visual summary methods (8 articles proposing 20 methods); hypothesis testing methods (11 articles proposing 16 methods); estimation methods (15 articles proposing 24 methods); or methods that provide decision-making probabilities (10 articles proposing 13 methods). Methods were further classified according to whether they required a prespecified event (9 articles proposing 12 methods), or could be applied to emerging events (35 articles proposing 61 methods); and if they were (group) sequential methods (10 articles proposing 12 methods) or methods to perform final/one analyses (34 articles proposing 61 methods). CONCLUSIONS:This review highlighted that a broad range of methods exist for AE analysis. Immediate implementation of some of these could lead to improved inference for AE data in RCTs. For example, a well-designed graphic can be an effective means to communicate complex AE data and methods appropriate for counts, time-to-event data and that avoid dichotomising continuous outcomes can improve efficiencies in analysis. Previous research has shown that adoption of such methods in the scientific press is limited and that strategies to support change are needed. TRIAL REGISTRATION:PROSPERO registration: https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=97442.

Dataset Information

Appropriate statistical methods for analysing partially nested randomised controlled trials with continuous outcomes: a simulation study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets