Clinical Trial

Working Paper abstract In longitudinal studies participants can often experience the outcome(s) of interest multiple times during the observation period, creating recurrent event data. Depending on the primary research objective, advanced statistical methods are required to correctly analyze this special type of data.

We extend the Bayesian hierarchical modeling framework from efficacy assessment studies in basket trial design to characterize the treatment’s safety profile. We propose Bayesian multi-level count models adopting different likelihood options with additional focus placed on the choice of prior for the basket-level standard deviation.

abstract Background A health department survey revealed nearly half employ laboratory-based HIV and HCV testing (LBT) over rapid testing (RT) in nonhospital settings such as drug detoxification centers. LBT has higher sensitivity for acute HIV infection compared to RT but LBT is not point of care and may result in fewer diagnoses due to loss to follow-up before result delivery.