Kylie Lange

@klange-au.bsky.social

Statistician working in clinical trials methodology & nutrition and diabetes clinical research | South Australian Health & Medical Research Institute (SAHMRI); Adelaide University

Is multiple imputation more powerful than complete case analysis in clinical trials? A systematic review by Thomas Sullivan found multiple imputation often led to noticeable changes in the effect estimate but did not demonstrate consistent precision advantages. #ClinicalTrials

Bild

🚨New publication! The final piece of my PhD was to translate the earlier theoretical work into a free sample size calculator for designing partially clustered trials. Really happy to now see this out there to help researchers plan high quality trials. Paper is linked below ⬇️ Calculator is here:

Partially clustered sample size calculatorSample size calculator for partially clustered trials

klange.shinyapps.io

AusTriM CRE@austrim-cre.bsky.social · 6mo ago

"An online sample size calculator for designing partially clustered trials" (@klange-au.bsky.social et al) has now been published in Clinical Trials! doi.org/10.1177/1740... This free and user-friendly online calculator makes it easier to ensure a trial is appropriately powered ✅

Time for some updates! 🎓Celebrated the official end of my PhD journey with graduation from The University of Adelaide. PhDONE! 💼Now fully settled in as a postdoc in the Biostatistics Unit at @sahmri.bsky.social ⚕️Pleased to also be continuing my role supporting clinical research at UofA

Front page of a PhD thesis titled 'Design Issues for Partially Clustered Trials'

📣New publication alert! The latest paper from my PhD is now online at Statistics in Medicine, presenting new sample size formulas for clinical trials that include partial clustering. Really happy to see this work out in the world! 🧵1/4 dx.doi.org/10.1002/sim....

Sample Size Calculations for Partially Clustered Trials

Partially clustered trials are defined as trials where some observations belong to a cluster and others are independent. For example, neonatal trials may include infants from a single, twin, or tripl...

dx.doi.org

One of the motivating examples of partial clustering for my PhD research is the inclusion of infants from multiple births in neonatal trials. Kristy Robledo has just published a review of how multiple births are dealt with in these trials - and the news isn't great! 1/2 fn.bmj.com/content/earl...

We should do better in accounting for multiple births in neonatal randomised trials: a methodological systematic review

Objective To conduct a methodological systematic review of multicentre trials of premature infants to (1) determine if and how multiple births have been considered in the design, analysis and reportin...

fn.bmj.com