Bmc Med Res Methodol
-
Network meta-analysis is an extension of the classical pairwise meta-analysis and allows to compare multiple interventions based on both head-to-head comparisons within trials and indirect comparisons across trials. Bayesian or frequentist models are applied to obtain effect estimates with credible or confidence intervals. Furthermore, p-values or similar measures may be helpful for the comparison of the included arms but related methods are not yet addressed in the literature. In this article, we discuss how hypothesis testing can be done in a Bayesian network meta-analysis. ⋯ Test decisions can be based on the proposed index. The index may be a valuable complement to the commonly reported results of network meta-analyses. The method is easy to apply and of no (noticeable) additional computational cost.
-
Bmc Med Res Methodol · Oct 2018
Synthesising conceptual frameworks for patient and public involvement in research - a critical appraisal of a meta-narrative review.
A number of conceptual frameworks for patient and public involvement (PPI) in research have been published in recent years. Although some are based on empirical research and/or existing theory, in many cases the basis of the conceptual frameworks is not evident. In 2015 a systematic review was published by a collaborative review group reporting a meta-narrative approach to synthesise a conceptual framework for PPI in research (hereafter 'the synthesis'). As the first such synthesis it is important to critically scrutinise this meta-narrative review. The 'RAMESES publication standards for meta-narrative reviews' provide a framework for critically appraising published meta-narrative reviews such as this synthesis, although we recognise that these were published concurrently. Thus the primary objective of this research was to appraise this synthesis of conceptual frameworks for PPI in research in order to inform future conceptualisation. ⋯ Although the aims of the authors' synthesis were commendable, and the conceptual framework presented was coherent and attractive, the paper did not demonstrate a transparent and replicable meta-narrative review approach. There is a continuing need for a more rigorous synthesis of conceptual frameworks for PPI.
-
Bmc Med Res Methodol · Oct 2018
The Shiny Balancer - software and imbalance criteria for optimally balanced treatment allocation in small RCTs and cRCTs.
In randomised controlled trials with only few randomisation units, treatment allocation may be challenging if balanced distributions of many covariates or baseline outcome measures are desired across all treatment groups. Both traditional approaches, stratified randomisation and allocation by minimisation, have their own limitations. A third method for achieving balance consists of randomly choosing from a preselected list of sufficiently balanced allocations. As with minimisation, this method requires that heterogeneity between treatment groups is measured by specified imbalance metrics. Although certain imbalance measures are more commonly used than others, to the author's knowledge there is no generally accepted "gold standard", neither for categorical and even less so for continuous variables. ⋯ The Shiny Balancer offers the possibility to visually explore the balancing properties of several well established or newly suggested imbalance metrics, and its use is particularly advocated in clinical studies with few randomisation units, as it is typically the case in cluster randomised trials.
-
Bmc Med Res Methodol · Oct 2018
Assessment of research waste part 2: wrong study populations- an exemplar of baseline vitamin D status of participants in trials of vitamin D supplementation.
Research waste can occur when trials are conducted in the wrong populations. Vitamin D deficient populations are most likely to benefit from vitamin D supplementation. We investigated waste attributable to randomised controlled trials (RCTs) of supplementation in populations that were not vitamin D deficient. ⋯ Up to 70% of RCTs of vitamin D with clinical endpoints, 71% of large completed RCTs, and 100% of ongoing large RCTs could be considered research waste because they studied cohorts that were not vitamin D deficient.
-
Bmc Med Res Methodol · Aug 2018
Heckman imputation models for binary or continuous MNAR outcomes and MAR predictors.
Multiple imputation by chained equations (MICE) requires specifying a suitable conditional imputation model for each incomplete variable and then iteratively imputes the missing values. In the presence of missing not at random (MNAR) outcomes, valid statistical inference often requires joint models for missing observations and their indicators of missingness. In this study, we derived an imputation model for missing binary data with MNAR mechanism from Heckman's model using a one-step maximum likelihood estimator. We applied this approach to improve a previously developed approach for MNAR continuous outcomes using Heckman's model and a two-step estimator. These models allow us to use a MICE process and can thus also handle missing at random (MAR) predictors in the same MICE process. ⋯ In the presence of MAR predictors, we proposed a simple approach to address MNAR binary or continuous outcomes under a Heckman assumption in a MICE procedure.