University of Cambridge > > MRC Biostatistics Unit Seminars > BSU Seminar: 'Bayesian Covariance Structure Modelling of Clinical Trial Data'

BSU Seminar: 'Bayesian Covariance Structure Modelling of Clinical Trial Data'

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Alison Quenault.

This will be a free hybrid seminar. To register to attend virtually, please click here:

Latent mixed effects models can be used in clinical trials to describe clustered data consisting of multiple outcome types. Observations in the same factor level share a random effect which, when integrated out, yields a positive addition to the covariance between these outcomes.In this research, instead we directly analyse covariance structure models where the covariance structure comes from a multi-level normal latent mixed effect model. This model allows for a positive as well as a negative addition to the covariance between observations in the same factor level. Next, the extension of the parameter range of these covariances to negative values has other benefits in statistical estimation and testing. We construct a novel, efficient and general procedure to perform Bayesian analysis under these covariance structure models, involving a product shifted-inverse gamma prior for the covariance parameters respecting the parameter range. Our leading example will consist of data coming from the BIO -RESORT clinical trial, where we apply our results to construct a Gibbs sampler for type-II interval censored event-time data.

This talk is part of the MRC Biostatistics Unit Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity