Biostatistics Department Seminar
We will be having two internal speakers, Bonnie Smith and Boyi Guo, present.
Title (Bonnie Smith): Sensitivity analysis for trials with irregular and informative assessment times
Abstract: Many randomized trials are designed to collect outcomes at or around pre-specified times after randomization; however, there is often variability in the times when participants' outcomes are actually assessed. This can pose a challenge to learning the effect of the treatment or intervention, since not all participants have outcome assessments at the target times specified in the study protocol. Additionally, in some studies, the timing of assessments can be related to outcome values, for example with doctors' visits tending to occur at times when participants' outcomes are worse. I discuss the estimands of interest and challenges to estimation in such trials, with comparison to missing data settings. I then present a sensitivity analysis methodology that we have developed for this setting, in which inference for the treatment effect is drawn under a range of different assumptions connecting observed and unobserved outcome distributions. I apply our method to a study of participants with uncontrolled asthma, which lets us examine the way in which inference is impacted if participants tend to be assessed at times when their asthma is more, or less, severe.
Title (Boyi Guo): Identify Molecular Biomarkers through Spatial Genomics
Abstract: TBA
Speakers
Bonnie Smith and Boyi Guo are postdoctoral fellows in the Department of Biostatistics, Bloomberg School of Public Health.
Zoom Registration
If you would like to join via Zoom, please register here.
2023-2024 Monday Seminar Series
All seminars are held at 12:05 PM via Zoom and onsite (Room locations will vary this year-please see above for room location). View all seminar information here.
