On the estimation of intracluster correlation for time-to-event outcomes in cluster randomized trials

Kalia, Sumeet; Klar, Neil; Donner, Allan

doi:10.1002/sim.7145

Cited by 15 publications

(23 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unadjusted ICCs were calculated for all outcomes except the primary outcome because estimation of the ICC for a survival outcome is not straightforward. 62 We estimated approximate ICCs using log-transformed observed event times and also by using the censoring indicator and treating the outcome as binary. We also obtained an approximate estimate of the correlation by fitting marginal generalised estimating equation models.…”

Section: Methodsmentioning

confidence: 99%

A contingency management intervention to reduce cannabis use and time to relapse in early psychosis: the CIRCLE RCT

Rains

Marwaha

Strang

et al. 2019

Health Technol Assess

View full text Add to dashboard Cite

Background Cannabis is the most prevalent illicit substance among people with psychosis, and its use is associated with poorer clinical and social outcomes. However, so far, there has been limited evidence that any treatment is effective for reducing use. Contingency management (CM) is an incentive-based intervention for substance misuse that has a substantial evidence base across a range of substances and cohorts. However, to date there have been no randomised controlled trials (RCTs) of CM as a treatment for cannabis use specifically in psychosis. Objective To conduct a RCT investigating the clinical effectiveness and cost-effectiveness of CM in reducing cannabis use among Early Intervention in Psychosis (EIP) service users. Design The CIRCLE (Contingency Intervention for Reduction of Cannabis in Early Psychosis) trial was a rater-blinded, multicentre RCT with two arms. Participants were randomised 1 : 1 to either an CM arm, in which participants received CM for cannabis use alongside an optimised treatment-as-usual programme including structured psychoeducation, or a control arm in which participants received the treatment as usual only. Setting EIP services across the Midlands and the south-east of England. Participants The main eligibility criteria were EIP service users with a history of psychosis, aged 18–36 years, and having used cannabis at least once per week during 12 of the previous 24 weeks. Intervention The CM intervention offered financial incentives (i.e. shopping vouchers) for cannabis abstinence over 12 once-weekly sessions, confirmed using urinalysis. The maximum value in vouchers that participants could receive was £240. Main outcome measures The main outcome was time to relapse, operationalised as admission to an acute mental health service or hospital. The primary outcome was assessed at 18 months post inclusion using electronic patient records. Secondary outcomes assessed the clinical effectiveness and cost-effectiveness of the intervention, for which data were collected at 3 and 18 months. Results A total of 278 participants were randomised to the CM arm and 273 were randomised to the control arm. In total, 530 (96%) participants were followed up for the primary outcome. There was no significant difference in time to admission between trial arms by 18 months following consent (hazard ratio 1.03, 95% confidence interval 0.76 to 1.40). There were no statistically significant differences in most secondary outcomes, including cannabis use, at either follow-up assessment. There were 58 serious adverse events, comprising 52 inpatient episodes, five deaths and one arrest. Limitations Participant retention was low at 18 months, limiting the assessment of secondary outcomes. A different CM intervention design or reward level may have been effective. Conclusions The CM intervention did not appear to be effective in reducing cannabis use and acute relapse among people with early psychosis and problematic cannabis use. Future work Cannabis use is still a significant clinical concern in this population. A pressing need remains to identify suitable treatments. A wider perspective on the social circumstances of young people with psychosis may be needed for a successful intervention to be found. Trial registration Current Controlled Trials ISRCTN33576045. Funding This project was funded by the National Institute for Health Research (NIHR) Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol. 23, No. 45. See the NIHR Journals Library website for further project information.

show abstract

Section: Methodsmentioning

confidence: 99%

A contingency management intervention to reduce cannabis use and time to relapse in early psychosis: the CIRCLE RCT

Rains

Marwaha

Strang

et al. 2019

Health Technol Assess

View full text Add to dashboard Cite

show abstract

“…To our knowledge, two main strategies have been proposed to estimate the ICC for TTE outcomes: the first is to estimate the ICC from the binary censoring indicators [16] the other is to estimate the ICC from observed event times (excluding observations from censored participants) [23]. A recent simulation study [24] compared these two strategies and concluded that neither approach can be recommended because of bias and inconsistent results.…”

Section: Discussionmentioning

confidence: 99%

Methodological review showed that time-to-event outcomes are often inadequately handled in cluster randomized trials

Caille

Tavernier

Taljaard

et al. 2021

Journal of Clinical Epidemiology

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

“…To estimate the Type I error of each design we repeat the above process with the true vaccine efficacy set to 0. To measure the magnitude of clustering in the cRCT we report the design effect, defined as , where ρ is the intracluster correlation coefficient (ICC) calculated using (13), which is likely an underestimate of the ICC for time-toevent data (14), and m is the average size of a study cluster. The design effect increases with ICC, as subjects in the same cluster are more similar, and with the size of each cluster, as there are fewer, larger groups of similar individuals.…”

Section: Discussionmentioning

confidence: 99%

Competing Effects of Indirect Protection and Clustering on the Power of Cluster-Randomized Controlled Vaccine Trials

Hitchings

Lipsitch

Wang

et al. 2018

American Journal of Epidemiology

View full text Add to dashboard Cite

Power considerations for trials evaluating vaccines against infectious diseases are complicated by indirect protective effects of vaccination. While cluster-randomized trials (cRCTs) are less statistically efficient than individually randomized trials (iRCT), a cRCT's ability to measure direct and indirect vaccine effects may mitigate the loss of efficiency due to clustering. Within cRCTs, the number and size of clusters affects three determinants of power: the effect size being measured, disease incidence, and intra-cluster correlation. We simulate trials conducted in a collection of small communities to assess how indirect protection and clustering affect the power of cRCTs and iRCTs during an emerging epidemic. Across diverse parameters, we find that within the same trial population, cRCTs are never more powerful than iRCTs, although the difference can be small. We also identify two effects that attenuate the loss of cRCT power traditionally associated with increased cluster size. First, if enrollment of fewer, larger clusters is performed to achieve higher vaccine coverage within vaccinated communities, this increases the effect to be measured and, consequently, power. Second, the greater rate of imported transmission in larger communities may increase the attack rate and similarly mitigate loss of power relative to a trial in many, smaller communities. Cluster-randomized controlled trials (cRCTs) have become an increasingly common method for evaluating interventions for infectious diseases, including vaccines. Compared to individually randomized controlled trials (iRCTs), cRCTs may offer logistical, operational, and acceptability advantages (1), and allow the measurement of direct and indirect effects of vaccination, which are often relevant for policy-makers (2). The statistical theory of cRCT design has largely focused on the effect of clustering, commonly measured by intracluster correlation, on power (3-5). Intracluster correlation arises because outcomes of members of the same cluster are more similar than those from different clusters. Therefore, increasing the number of individuals within a cluster provides less information than would adding the same number of individuals in a new cluster.When the trial outcome is an infectious disease, correlation arises also because each case in a cluster can transmit infection to other cluster members. Thus, trials of vaccines against infectious diseases exhibit a more complicated relationship between statistical power and sample size than in trials for non-infectious outcomes (6, 7); in particular, the total or overall vaccine effect measured by a cRCT is generally larger than the direct effect measured by an iRCT. In principle, this increased effect size in a cRCT might partially or fully offset the loss of power due to within-cluster correlation. Understanding these complexities can aid in vaccine trial design for emerging epidemics. While an important consideration in any clinical trial, maximizing efficiency is particularly crucial in trials during ...

show abstract

On the estimation of intracluster correlation for time-to-event outcomes in cluster randomized trials

Cited by 15 publications

References 71 publications

A contingency management intervention to reduce cannabis use and time to relapse in early psychosis: the CIRCLE RCT

A contingency management intervention to reduce cannabis use and time to relapse in early psychosis: the CIRCLE RCT

Methodological review showed that time-to-event outcomes are often inadequately handled in cluster randomized trials

Competing Effects of Indirect Protection and Clustering on the Power of Cluster-Randomized Controlled Vaccine Trials

Contact Info

Product

Resources

About