Biostatistics Professor at @Sydney_Uni and @TrialsCentre
Joined September 2017
- Tweets66
- Following126
- Followers149
- Likes71
Non-concurrent controls occur in adaptive platform trials. Our paper gives a new more rigorous definition based on randomization cohort rather than time. Cohort adjustment and implications for databases & software are discussed.
@austrim_cre
@TrialsCentre
onlinelibrary.wiley.com/doi/…
Recent @TheLancet trial uses confidence distribution to conclude “the confidence that the risk ratio is lower than 1 is 97.2%”. Full confidence distribution plot in supplementary material. Excellent way to present trial results as described in Reference 24
thelancet.com/journals/lance…
Ian Marschner retweeted
“Removing the advanced mathematics prerequisite does nothing to address the decline in mathematics enrolments at schools and sends the wrong signal to students.”
science.org.au/news-and-even…
Confidence distributions are distributional summaries of evidence. They’re like Bayesian posteriors but without prior distribution assumptions. I wrote a tutorial paper in Statistics in Medicine for clinical trial statisticians @austrim_cre @TrialsCentre
onlinelibrary.wiley.com/doi/…
We developed a reporting framework for adaptive clinical trials. It uses the embedded fixed designs within an adaptive trial, which yield unbiased concurrently randomised cohorts. Paper is out in @BMJMedicine
@ascot_trial
@TrialsCentre
@austrim_cre
bmjmedicine.bmj.com/content/…
Ian Marschner retweeted
I'll be chairing our Panel Discussion at #SCT2023 next week on how best #ClinicalTrials can impact clinical practice.
The session is called "Academic trials for regulatory (and payer) use" but discussion will be broader.
This one's going to be fascinating. Come, join us!
1/6
ALT Screenshot from session in the SCT2023 app
ALT opening page for SCT app
New paper in Stat Methods Med Res from PhD student Anne Lyngholm Sørensen. Novel methodology to investigate effect modification in sub-group meta-analysis while maintaining within-study randomised comparisons
@biostat_ucph
@TrialsCentre
@MQMathsStats
journals.sagepub.com/doi/10.…
Ian Marschner retweeted
Adaptive platform trials lead to a patchwork of potential time-specific comparisons. Ian Marschner and Manjula Schou propose adapting network meta-analysis methods to this context. @IanMarschner @TrialsCentre @SCTorg @Sydney_Uni #FDA
journals.sagepub.com/doi/pdf…
New paper + commentary on adaptive #PlatformTrials (APTs). We re-purposed network meta-analysis principles to separate randomised and non-randomised evidence from the embedded fixed designs in APTs. Non-concurrent controls and confounding are discussed.
doi.org/10.1177%2F1740774522…
NSW begins opening with 70% 16+ vaxed. Welcome relief but need to be aware the 70% is unevenly spread over age. Only 53% in highly mobile 20-29 group. As I said months ago, vax targets should have been age-specific. Will be crucial to follow the rules for vaxed and unvaxed.
Glad my research quoted but need to avoid 2 common covid mortality mistakes. Deaths divided by cases underestimates mortality as active cases are in denominator but not numerator. Also earlier outbreaks were in older people so recent mortality seems low
abc.net.au/news/2021-09-10/d…
